Home

Canadian Travel Survey Microdata User's Guide

1. 14 CTS Mienodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey of the trip If the respondent travelled twice to the same location during the same trip only one visit is recorded at that location Person visit Visit taken by a traveller either single or travelling as a group If four persons go on a visit together it counts as four person visits Origin Starting point of a trip is the respondent s place of residence Destination Place reported by the respondent as the destination of a trip If a respondent visited more than one place during a trip the destination is the place furthest from their home Trip distance Refers to the one way distance between the trip origin and its destination expressed in kilometres Traveller Any person who completes a trip Any person who does not take a trip may be described as a non traveller Intraprovincial travel Travel within a province by its residents e g Ontario residents travelling in Ontario Interprovincial travel Travel by the resident of one province to and in another province e g Ontario residents travelling elsewhere in Canada Statistics Canada Catalogue 87M0006GPE CTS Wicradata User s Guide 15 Canadian Travel Survey Non resident travel Travel by residents from another province to a specific province e g travel of Canadians except Ontario residents to Ontario Census Metropolitan Area
2. When the unweighted estimate is satisfactory the user should look at the weighted estimate to see if it satisfies the release criteria The release cutoffs for the weighted estimates of the CTS can be found in the Data Quality Report Chapter 10 Using the The standard error of an estimate is frequently coefficient of expressed as a percentage of the estimate itself in S t which case it is called the coefficient of variation variation C V Whereas the standard error is measured in the same units as the estimate the coefficient of variation is simply a ratio This makes it easier to use as a criterion for the reliability of any estimate For example suppose that based upon the survey results one estimates that 25 9 of Canadians aged 15 or more took at least one trip in March 1996 and this estimate is found to have standard error of 0 009 Then the coefficient of variation of the estimate is calculated as Statistics Canada Catalogue 87M0006GPE CTS WUcerodata User s Guide 91 Canadian Travel Survey 009 100 3 47 259 The coefficients of variation C V are derived using the variance formula for simple random sampling and incorporating a factor which reflects the multi stage clustered nature of the sample design This factor known as the design effect was determined by first calculating design effects for a wide range of characteristics and then choosing from among these a conservative value to be used in
3. CMA Main labour market area of an urbanized core having 100 000 or more population For more details refer to the Standard Geographical Classification SGC 1991 Census Division CD Areas established by provincial laws which are intermediate geographic areas between the municipality Census Subdivision and the province level Census Divisions represent counties regional districts regional municipalities and other types of provincially legislated areas For more details refer to the Standard Geographical Classification SGC 1991 Tourism region From a touristic point of view homogeneous regions defined by each province See map included with the CTS documentation Mode of transportation Mode of transportation used to travel the greatest distance during a trip if two modes of transportation were used to travel equal distances the mode used to reach the destination is recorded Purpose Main reason the respondent to the survey went on a trip regardless of the reason 16 CTS Mienodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey anyone else from the household had for taking the same trip Categories included in this variable are the following visiting friends and relatives pleasure personal business and non business convention Package deal Package deals cover the expenses of two or more components of a trip but in most cases the costs are not identified separately Th
4. In some cases the interviewers will not interview the selected CTS individuals with the following characteristics gt incapacity for example deafness mental retardation etc v language difficulties a person speaks a language other than English or French and no one in the household is available to translate v respondents away at school or on business outside the local dialing area v respondents who are in a hospital v respondents who move out of the household between the time the LFS demographic component was completed and the CTS is completed Non respon se For all households responding to the LFS the next to the CTS stage of data collection is to administer the Canadian Travel Survey Overall the response rate for the CTS is around 90 Response rates for the CTS reflect the proportion of respondents eligible for the Canadian Travel Survey who has reported information These response rates are not cumulative that is they don t take into account those people who would have been eligible for CTS but have been non respondents to LFS This is because those individuals who don t respond to the LFS are not even asked if they would like to answer 36 CTS Wierodata User e Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey the Canadian Travel Survey Thus they cannot be considered as non respondents to the CTS More detailed information on response rates is presented in
5. according to Statistics Canada s definition of a trip a person must have travelled for 80 km or more from home and must have travelled to a Canadian destination Do not forget to make the proper selection on the variables DISTANC distance and DEPROV province of destination when defining the eligible population 72 CTS Wierodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey Having this additional information will allow the user to compile information such as the socio demographic profile of persons who visited the Avalon tourism region places visited by travellers whose destination was Vancouver etc To link the person trip and the visit files one has to sort the person trip file by MONTH UNIQID TRIPNUM and ADCH The visit files should be sorted by MONTH UNIQID TRIPNUM ADCH the province where money was spent REXPROV and the location of visit REALTYPE depending of the file one is using These sorting sequences are the ones required to properly link those files together The linking between those two files can be done using the UNIQID and TRIPNUM variables When compiling visit information one has to use the person trip weight PTRIPWT provided on the datasets One must also make the proper selection of visit records by using only the ones where the visit flag VISFLAG is equal to 1 When compiling reallocated expenditures information one has to use the household trip weig
6. be collected classified and linked It provides a measurement of the economic demand for and Statistics Canada Catalogue 87M0006GPE CTS Wieradata User s Guide 7 Canadian Travel Survey production of tourism commodities It makes it possible to evaluate the direct contribution of tourism expenses to Canada s Gross Domestic Product GDP For further information on the TSA refer to the winter 1997 issue of Travel log Catalogue 87 003 which is prepared by the Tourism Statistics Program of Statistics Canada One can also refer to the list of other tourism data sources included on the CD ROM to get more specific information on the TSA and on other data on tourism 8 CTS Wicrodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey ry iad CONCEPTS AND DEFINITIONS This chapter outlines concepts and definitions of interest to the users The concepts and definitions used in the Labour Force Survey LFS are described in the first part while those specific to the Canadian Travel Survey are given in the next part Users are referred to the CTS questionnaire included with the CTS documentation on CD ROM for an electronic copy of the computer assisted interviewing questionnaire LFS concepts m and definitions Target population Civilian non institutionalised population 15 years of age and over in Canada s ten provinces Specifically excluded from LFS coverage are residents of the Y
7. it is not additive with other time periods Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 61 Canadian Travel Survey Trip dataset available only for microdata files users The trip dataset provides information on the trip characteristics taken by travellers It contains one record for each trip taken It can be used only when linked to the person dataset and provides information on the travel incidence based on selected trip characteristics It is useful to answer questions such as How many persons flew at least once during January How many persons took at least one business trip in July To get this information and additional trip information on travellers one has to link the selected monthly person dataset with the appropriate monthly trip dataset using the unique person identifier UNIQID The person file should be sorted by the UNIQID and the trip file should be sorted by the UNIQID as well as the trip number identifier TRIPNUM These sorting sequences are the ones required to properly link those two files together After producing the merged file duplicate records will appear on the file for travellers who reported more than one trip To avoid double counting duplicate records of the same traveller have to be eliminated based on selected trip characteristics For example if one wants to know how many travellers flew at least once in January one has to eliminate any record with the same U
8. trips that did not originate in Canada trips longer than a year Only the microdata files include all trips regardless of destination or distance in the Statistics Canada Catalogue 87M0006GPE CTS Microdata User s Guide 13 Canadian Travel Survey case of overnight trips and same day trips from Ontario of at least 40 km Household trip Trip involving one or more persons from the same household leaving and returning together If four persons from the same household go on a trip together that is they leave and return together it counts as one household trip If the same household takes two trips it counts as two household trips Person trip Trip taken by one person If this person took more than one trip and or travelled with other members of the same household we will count as many person trips as there are trips and persons who took these trips If four persons from the same household go on a trip together it counts as four person trips If the same person takes two trips it counts as two person trips Person night Night spent away from home by a person taking a trip If two persons take a trip involving three nights away from home there is a count of six person nights Same day trip Trip which does not include a night away from home Overnight trip Trip that includes at least one night away from home Visit Place of overnight stay of the traveller or for a same day trip the location of destination
9. users with some indication of the magnitude of this sampling error This chapter of the documentation outlines the measures of sampling error which Statistics Canada commonly uses and which it urges users producing estimates from these microdata files to use also The basis for measuring the potential size of sampling errors is the standard error of the estimates derived from survey results The Canadian Travel Survey is based upon a complex design with stratification and multiple stages of selection and unequal probabilities of selection of respondents Using data from such complex surveys presents problems to analysts because the survey design and the selection probabilities affect the estimation and variance calculation procedures that should be used While many analysis procedures found in statistical packages allow weights to be used the meaning or definition of the weight in these procedures differ from that which is appropriate in a sample survey framework with the result that while in many cases the estimates produced by the packages are correct Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 89 Canadian Travel Survey the variances that are calculated are almost meaningless For many analysis techniques for example linear regression logistic regression analysis of variance a method exists which can make the application of standard packages more meaningful If the weights on the records
10. 15 years of age or older Response burden is minimized for the elderly 70 years of age or older by carrying forward their responses for the initial interview to the subsequent five months in the survey LFS sam ple The sample size of eligible persons in the LFS is a determined so as to meet the statistical precision size requirements for various labour force characteristics at the provincial and subprovincial level to meet the requirements of federal provincial and municipal governments as well as a host of other data users The monthly LFS sample consists of approximately 59 000 dwellings After excluding vacant dwellings dwellings demolished or converted to non residential uses dwellings containing only ineligible persons dwellings under construction and seasonal dwellings about 52 350 dwellings remain which are occupied by eligible persons From these dwellings LFS information is obtained for about 102 000 civilians aged 15 or over LFS sam p le The LFS employs a panel design whereby the entire monthly sample of dwellings consists of six panels rotation or rotation groups of approximately equal size Each of these panels can be considered by itself to Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 29 Canadian Travel Survey be representative of the entire LFS population All dwellings in a rotation group remain in the LFS sample for six consecutive months after which time they are replace
11. 87M0006GPE Canadian Travel Survey Preliminary editing Linking to the LFS Geographic coding the application will assign an incomplete code for that individual The data files transmitted from the regional offices are downloaded to the Special Surveys Division computers for processing The data are edited in a series of iterations to detect errors in the data and to prepare the data files for subsequent weighting and expenditure imputation At this step of preliminary editing duplicate records are detected and some minor edits are performed The CTS files received from the regional offices contain an identifier which is used to link the records to their respective Labour Force Survey information Once the data have been unduplicated in the preceding step records are linked to the LFS files to retrieve information required for weighting to geo code the respondents place of residence to pick up demographic variables age education industry occupation LFS status etc and to derive the response status of each record This step involves the geographic coding of the trip and location information to derive the province Census Metropolitan Area tourism region and Census Division of each origin destination and location on the file Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 39 Canadian Travel Survey The trip origin is the respondent s place of residence unless this has changed
12. AGEGRP tile in the row dimension although it is not necessary to look at age groups to get the estimated number Beyond 20 20 does not allow you to use only one variable gt Apply the _PERSWT and load the data Because only one weight is included on the person file data are already weighted For the other extracts one will have to apply a weight factor and then load the data In the top left corner cell you will have the denominator total population 23 537 562 and in that same row where the column title yes you will have the numerator number of people who took at least one non business overnight interprovincial trip in 1996 11 375 951 gt To get a proportion divide the numerator by the denominator 11 375 951 23 537 562 0 48 Statistics Canada Catalogue 87M0006GPE CTS WUcerodata User s Guide 83 Canadian Travel Survey Tabulation of quantitative estimates Quantitative estimates can be obtained by multiplying the value of the variable of interest by the final weight for each record then summing this quantity over all records of interest Example using the Beyond 20 20 person trip file To obtain an estimate of the total reported expenditures for the first quarter of 1996 from the Beyond 20 20 person trip file gt drag the QUARTER tile into the column dimension of the table gt apply the HHTRWT gt drag drop and sum the REPCOST tile into the cell area of the table view and lo
13. Canada Catalogue 87M0006GPE Canadian Travel Survey Statistical profiles and customized products may also be obtained from the subdivision Microdata files are also available for users who wish to produce their own outputs The Beyond 20 20 software is also available with the microdata files for easier manipulation of data in tables and charts Other sources of tourism data include CANSIM Statistics Canada s machine readable database and retrieval system As well analytical articles regarding the Canadian Travel Survey and other tourism data can be found in Travel log Catalogue 87 003 a quarterly publication produced by the Tourism Statistics Program Uses of the The CTS data is used in different ways The main CTS data users of the data are the Canadian Tourism Commission the provinces and tourism boards Other users include the media businesses consultants as well as researchers They refer to the data to better understand the habits of Canadian travellers as well as their socio demographic characteristics The survey allows them to get information on their destinations the purpose of their trips the length of their stay the places they visited the activities they participated in as well as the expenditures involved in the trip The survey also provides input into the Tourism Satellite Account TSA This is a structured information system that allows the statistics describing all the measurable aspects of tourism to
14. LFS sample the derivation of weights for the survey records is clearly tied to the weighting procedure used for the LFS The LFS as well as the CTS weighting procedures are briefly described below In the LFS the final weight attached to each record is the product of the following factors the basic weight the cluster sub weight the balancing factor for non response and the province age sex ratio adjustment factor Each is described below Basic Weight In a probability sample the sample design itself determines weights which must be used to produce unbiased estimates of the population Each record must be weighted by the inverse of the probability of selecting the person to whom the record refers In the example of a 2 simple random sample this probability would be 02 for each person and the records must be weighted by 1 02 50 Because all eligible individuals in a dwelling are interviewed directly or by proxy this probability is essentially the same as the probability with which the dwelling is selected Statistics Canada Catalogue 87M0006GPE CTS Wicradata User s Guide 51 Canadian Travel Survey Cluster Sub weight The cluster delineation is such that the number of dwellings in the sample increases very slightly with moderate growth in the housing stock Substantial growth can be tolerated in an isolated cluster before the additional sample represents a field collection problem However if growth takes place in
15. Montreal to Vancouver using his own car and sleeping in motels in Sault Ste Marie Winnipeg Calgary and Vancouver The expenditures will be redistributed according to the number of nights spent in each location that is in Ontario Manitoba Alberta and British Columbia at the provincial level Vehicle rental expenditures Includes all operation rental or users fees encountered for the use of any vehicle such as an automobile a truck motorcycle bicycle boat motor home snowmobile etc including insurance Vehicle operation expenditures It includes expenditures related to the operation of a private or rental vehicle namely gasoline repairs and parking costs while on the trip Local transportation expenditures Local transportation means within a city or metropolitan area that is intracity transportation It includes the cost of taxis city bus fares subway fares and such things as bus Statistics Canada Catalogue 87M0006GPE CTS Wicradata User s Guide 19 Canadian Travel Survey tours in the place of visit and or destination while on the trip Intercity transportation expenditures Includes expenses between cities or metropolitan areas to get to or from the destination These transportation expenditures include ticket fares for intercity aircrafts boats hovercrafts trains buses as well as intercity ferries Food or beverages purchased at restaurants or bars Includes the total amount spen
16. Survey 4 DATA COLLECTION LFS data Data collection for the LFS is carried out each month during the week following the LFS reference collection week usually the third week of the month Statistics Canada interviewers who are part time employees hired and trained specifically to carry out the Labour Force Survey contact each of the sampled dwellings to obtain the required labour force information Each interviewer contacts approximately 70 dwellings per month Dwellings new to the sample are contacted through a personal visit The interviewer first obtains socio demographic information for each household member and then obtains labour force information for all eligible members Provided there is a telephone in the dwelling and permission has been granted subsequent interviews are conducted by telephone As a result approximately 85 of all dwellings are interviewed by telephone In these subsequent monthly interviews as they are called the interviewer confirms the socio demographic information collected in the first month and collects the labour force information for the current month Collection by computer assisted interviewing refer to Chapter 4 CTS data collection is decentralised interviewers generally work at home They carry out the interview by telephone or at the 32 CTS Mierodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey respondents home and transmit thei
17. at least one record for every visit made for every person trip found on the person trip dataset Each monthly CTS visit file is provided at four different geographic levels that is the province Census Metropolitan Area tourism region and 68 CTS Wierodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey Census Division level Depending on which level of geography one wants to obtain visit information one has to use the corresponding file The visits are recorded at the level of geography represented on the file For example a person who takes a trip from Vancouver to Edmonton and spends one night in Calgary and one in Edmonton would show one visit to Alberta on the provincial visit file This traveller would also show one visit to Calgary and one visit to Edmonton on the CMA visit file The records on the CMA visit file would show 1 ORCMA CMA of origin Vancouver DECMA CMA of destination Edmonton REALTYPE CMA visited code Edmonton 2 ORCMA CMA of origin Vancouver DECMA CMA of destination Edmonton REALTYPE CMA visited code Calgary Each monthly CTS visit dataset also includes reallocated expenditures information refer to Chapter 2 for definition Again the reallocated expenditures included on each file would represent money spent in each location Depending on which level of geography one wants to get reallocated expenditures information one has to use the correspo
18. more than one cluster in an interviewer assignment the cumulative effect of all increases may create a workload problem In clusters where substantial growth has taken place sub sampling is used as a means of keeping interviewer assignments manageable The cluster sub weight represents the inverse of this sub sampling ratio in clusters where sub sampling has occurred Non response Notwithstanding the strict controls of the LFS some non response is inevitable despite all the attempts made by the interviewers The LFS non response rate is approximately 5 For certain types of non response e g household temporarily absent refusal data from a previous month s interview with the household if any is brought forward and used as the current month s data for the household In other cases non response is compensated for by proportionally increasing the weights of responding households The weight of each responding record is increased by the ratio of the number of households that should have been interviewed divided by the number that were actually 52 CTS Mierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey interviewed This adjustment is done separately for non response areas which are defined by employment insurance region type of area and rotation group It is based on the assumption that the households that have been interviewed represent the characteristics of those that should h
19. rotation group is representative of the population and also ensures that every member of the economic family is assigned the same weight The principles behind the calculation of the weights for the Canadian Travel Survey are identical to those for the LFS However further adjustments are made to the LFS weights in order to derive a final weight for the individual records on the Canadian Travel Survey microdata file l An adjustment to account for the use of a two sixths or three sixths sub sample instead of the full LFS sample Note that this adjustment may differ depending on the sample month and the province 2 An adjustment to account for the additional non response to the supplementary survey 1 e non response to the Canadian Travel Survey for individuals who did respond to the LFS or for which previous month s LFS data was brought forward 3 An adjustment to account for all persons eligible for CTS within a household 54 CTS Mierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey 4 A readjustment to account for independent province age sex projections after the above adjustments are made 5 A readjustment to account for independent economic region Census Metropolitan Area projections after the above adjustments are made The first two adjustments are taken into account by multiplying the LFS sub weight for each responding Canadian Travel Survey record by sum of LFS
20. sampled systematically This represents the final stage of sampling Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 27 Canadian Travel Survey Labour Force Survey Sample Design 1995 Province EIR ER Intersection 76 4 Urban Areas 5 6 70 8 Apartment List Frame Area Frame 0 6 5 0 69 2 0 8 0 8 Low Income Regular Regular High Low Apartments Apartments Area Income Population Frame Area Frame Density stratum stratum stratum stratum stratum i i i i i 1 1 I 1 I 1 building building cluster amp cluster amp town EA EA 1 1 I 1 1 1 1 1 I 1 I dwelling dwelling dwelling dwelling cluster i dwelling 22 6 1 0 Rural Areas Remote Areas 18 3 4 3 High Low Population Population Density Density stratum stratum stratum h i i 1 1 I 1 EA EA group Place EA 1 1 1 1 I 1 I dwelling dwelling dwelling level of stratification stage of sampling EIR Employment Insurance Region ER Economic Region percentage of total sample EA Census Enumeration Area cluster set of blockfaces 28 CTS Microdata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey Person selection Demographic information is obtained for all persons for whom the selected dwelling is the usual place of residence LFS information is obtained for all civilian household members
21. since the previous month recall that the month of interview is the month following the CTS reference month Information from the LFS is used to determine the place of residence The trip destination and locations and the origin in cases where the respondent has moved consist of place names which were entered in the computer by the interviewer These place names are matched to files containing all of the place names registered in the Standard Geographic Classification SGC and supplementary files containing the names of destinations outside Canada Each place name on these files has a standard geographic code and can be matched to a tourism region code In addition the longitude and latitude can be determined for each geo code this is used to compute the distance between the origin and destination All records requiring destination and location coding have key information copied to coding files Trip place names which match to the SGC files are automatically coded on these files Place names which do not find a match are reviewed manually to determine an appropriate code When all geocoding is complete geocodes are linked back to the CTS data files Once the files have been fully geo coded they proceed to the secondary editing process described next 40 CTS Wierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey Secondary editing Weighting Consistency edits Expenditure imputat
22. subweights from each household responding to LFS sum of LFS subweights from each household responding to CTS to obtain a non response adjusted Canadian Travel Survey sub weight The CTS sub weight is further adjusted by multiplying it by the number of eligible persons for the CTS within a household WEIGHT1 Adjustment 4 is calculated by multiplying WEIGHT for each Canadian Travel Survey respondent by population total for province sex age group i sum of WEIGHT for survey respondents in province sex agegroup i The resulting weight WEIGHT is then used in adjustment 5 by multiplying by another factor population total for ER CMA j sum of WEIGHT for survey respondents in ER CMA j Statistics Canada Catalogue 87M0006GPE CTS Wicradata User s Guide 55 Canadian Travel Survey Steps 4 and 5 are repeated iteratively until the adjustment factors converge to 1 The resulting person weight called PERSONWT or _PERSWT is the final weight which appears on the Canadian Travel Survey microdata files This weight is then used to calculate the person trip weight PTRIPWT or _PTRIPWT and the household trip weight called HHTRIPWT or _HHTRWT and Person Trip and Household Trip Weighting Once the person weight has been created the person trip weight and household trip weight are calculated For each trip the person weight of the respondent who took the trip is multiplied by the sum of the number of identical trips ta
23. the look up tables which would then apply to the entire set of characteristics To have more information on the design effects sample sizes and population counts by province that were used to produce the Approximate Sampling Variability Tables for person weights refer to the Data Quality Report Chapter 10 Note that Approximate Sampling Variability Tables are also available for person trip weights household trip weights person night weights and expenditures weights In the Data Quality Report provided with this Guide a set of Approximate Sampling Variability Tables has been provided to give microdata users some approximate coefficients of variation for groups of estimates at a time such as all estimates pertaining to a particular province In most cases these will be adequate to determine whether an 92 CTS Mierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey TABLE 5 Acceptable levels of the coefficient of variation Approximate coefficient of variation 0 0 16 5 16 6 25 0 25 1 33 3 33 4 or greater Restriction on use ACCEPTABLE Estimates can be considered for general unrestricted release MARGINAL Estimates can be considered for general unrestricted release but should be accompanied by a warning cautioning subsequent users of the high sampling variability associated with the estimates CONFIDENTIAL Estimates can be considered for general unr
24. values Donor expenditure averages are calculated by type of trip since expenditures vary considerably depending on the characteristics of the trip Averages are computed for trips which have the following characteristics in common destination Canada U S other country duration overnight or same day number of persons on the trip reason for the trip business or non business type s of accommodation and mode of transportation used There must be at least three donor records for each imputation category if not the trip characteristics are collapsed i e less specific and a set of averages are calculated for this next level of trip types If there are insufficient donors for this level the trip characteristics are collapsed further and another set of averages is computed This process is repeated until all levels of trip collapsing have donor averages computed For example the first level of imputation may be for all trips to a Canadian destination with one or more nights duration a party of two adults hotel accommodation mode of travel by air and business as the reason for the trip If insufficient numbers of donors are available at this level then the trip characteristics will be collapsed to include trips with any type of commercial accommodation if sufficient donors are still not available the 42 CTS Wierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey characteristic
25. 0 20 users Except for the month of December the monthly person datasets are not included on the Beyond 20 20 microdata files 60 CTS Wierodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey For Beyond 20 20 users To define if a person is a domestic traveller or a non traveller one should use the variables YRSAMEPR and YRCANADA If these variables are NOs the person is a non traveller within Canada otherwise that person is considered as a domestic traveller For microdata files users To define if a person is a traveller or a non traveller one should use the variable TOTTRIP total number of trips If TOTTRIP is 0 the person is a non traveller otherwise that person is considered as a traveller regardless of the number of trips taken This variable includes all overnight trips regardless of distance and same day trips of 80 km or more from home 40 km in Ontario to any destination Besides the annual travellers information provided on the December dataset microdata file users also have access to the monthly travellers information Available are twelve monthly person datasets providing socio demographic information on travellers and non travellers for specific reference months Each person dataset can be used on a monthly basis only because the question asked in the CTS relates to trips taken within the last month only Contrary to the information included in the other datasets
26. Canadian Travel Survey Microdata User s Guide aussi disponible en fran ais 87M0006GPF VE Canada Canadian navel Survey CTS Table of contents Page OVERVIEW 0309 35 he ea EA aoe ed a tee wes 1 1 INTRODUCTION TO CTS aoe Wade RRA GAIA bs 3 Back Grounds reli reis 3 Objectives tl ic M neh Naa ee eat eet rea 5 CTS products i eee a eee wh Se Et ied Hie ae ene tins 6 Uses of the CTS data aii debe re heer Sri hie aaa Bees 7 2 CONCEPTS AND DEFINITIONS 202000 0220020220022444 9 LFS concepts and definitions 0 ec cee n cence een 4 424 9 CTS concepts and definitions Soio nen e E E cece ence een eee 13 de SAMPLE 1 2 2 Dee em se dd ENDS D E CRA NRO eae ees RN dads 22 LFS population coverage 0 ee d D D E R r bbl a a a tenet nee n eens 22 LFS sample design 22 2242202458 ad Eee NCA TA NEAR ne Cai 23 LFS sample Size mn 253 dt 29 LES sample rotation ii Ree gets eee A A ee ee bk ES E 29 CIS asasupplement sireno sioe A wee ae alo sete 8 30 4 DATA COLLECTION korrei 04 8 22240224 76 8 BOG REN is ines 32 LES dataicollecttom 7 5 4 5 el so A Mey Ad bleeds le i ees 32 LES IMter Vie Wer 324 24 4 3005 da as 33 Non response to the DES 3 4424 Ricca cde Ad E 494 a en BAA AGA ad dea SNA 34 CTS data collection Pe eee ae ns ta ab roth tate Be aaah ts 35 Non response to ths CIS iii code cane iD pa Re EEE Kee area Ae es 36 Statistics Canada Ca
27. IEW The Canadian Travel Survey CTS is a biennial survey whose purpose is to gather information on domestic trips and travellers The CTS is a supplement using the Labour Force Survey LFS sampling frame The survey collects more than 30 characteristics which include socio demographic information on travellers trips and expenditures In 1996 a monthly sample of approximately 16 000 persons was interviewed That same year additional information was also collected For the first time the CTS is measuring the number of visits and providing reallocated expenditures at the national provincial and sub provincial level The Canadian Travel Survey was conducted by Statistics Canada in 1996 with the cooperation and support of the Canadian Tourism Commission and the ten provincial governments This document has been produced to facilitate the manipulation of the Beyond 20 20 files as well as the microdata files of the survey results Any questions about the data sets or their use should be directed to Statistics Canada Catalogue 87M0006GPE CTS Wieradata User s Guide 1 Canadian Travel Survey Sylvie Bonhomme ourism Statistics Program Culture Tourism and the Center for Education Statistics Statistics Canada 3 K R H Coats Building Tunney s Pasture Ottawa Ontario K1A OT6 Tel 951 1672 Fax 951 2909 Questions concerning the collection and processing of these data should be directed to Jack Beauregard _ Speci
28. NIQID i e the same traveller having more than one record where the mode of transport is air Counts on the number of travellers who flew at least once in January can then be produced 62 CTS Wierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey When using the trip dataset merged with the person dataset only the person weight can be used The trip file cannot be used alone no weight is included on this file Remember according to Statistics Canada s definition of a trip a person must have travelled for 80 km or more from home and must have travelled to a Canadian destination Do not forget to make the proper selection on the variables DISTANC distance and DEPROV province of destination when defining the eligible population Contrary to the monthly person dataset it is not possible to link the additional information included on the December person dataset to the monthly December trip dataset to gather information on trip characteristics of those people who travelled at least once during the year The information on the trip file only provides information on characteristics of trips taken in December For example one cannot find out the main purpose or the mode of transport of those travellers who went to the United States at least once during the year from the December trip file The monthly trip datasets are not included on the Beyond 20 20 microdata files Person trip The per
29. Survey Reallocated expenditures weight for Beyond 20 20 users only Using the data dictionary This weight should be used to compile reallocated expenditures information using the visit files It can be associated only with reallocated expenditures related variables refer to table 4 For example one would apply the reallocated expenditures weight to know how much money was spent on recreation and entertainment in the Niagara Regional Municipality Census Division located in Ontario The electronic data dictionary provided with this package presents the complete information about each variable on the Beyond 20 20 files and on the microdata files For each variable is shown the variable name the description or definition code lists with descriptions or alternatively the range of values that the variable can take on Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 77 Canadian Travel Survey TABLE 4 Use of weights in association with different variables Person Person Household Person Reallocated trip trip visit expenditures Socio demographic characteristics Age group Y Y Y Sex Y Y Y Marital status Y Y Y Relation to family reference person Y Y Y Class of worker Y Y Y Educational attainment Y Y Y Labour force status Y Y Y Household income Y Y Y Trip characteristics Province of origin Y Y CD of origin Y Y CMA of origin Y Y Tourism region of origin Y Y Province of destination
30. Y Y CD of destination Y Y CMA of destination Y Y Tourism region of destination Y Y Distance one way Y Y Total number of nights Y Y Nights spent in Newfoundland Y Y Nights spent in hotel Y Y Mode of transportation Y Y Main purpose of trip Y Y Activities Y Y Visit characteristics Number of visit nights Y Number of visit nights hotel Y Expenditures variables Total cost of packages Y Reported expenditures variables Y Reallocated expenditures variables Y Y For microdata files users only 78 CTS Wierodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey Rounding guidelines GUIDELINES FOR ANALYSIS AND PRESENTATION This chapter outlines the guidelines to be adhered to by users tabulating and analysing any data derived from the survey Beyond 20 20 files and microdata files With the aid of these guidelines users of microdata should be able to produce the same figures as those produced by Statistics Canada and at the same time will be able to develop currently unpublished figures in a manner consistent with these established guidelines Once it has been determined whether the results obtained are reliable the level of rounding indicates the level of precision that the data can actually support The following guidelines for rounding should be used Estimates of population subgroups should be rounded to the nearest thousand units Rates and perce
31. ad the data The total reported expenditures for all persons who travelled in the first quarter of 1996 can be found under the first quarter column 3 731 742 037 To obtain a weighted average of the form X Y the numerator X is calculated as for a quantitative estimate and the denominator Y is calculated as for a categorical estimate For example to estimate the average expenditures per person who travelled in the first quarter of 1996 gt estimate the total expenditures as described above 3 731 742 037 84 CTS Wierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey gt estimate the number of person trips by using the Beyond 20 20 person trip file and applying the _PTRIPWT weight To do this drag and drop the QUARTER tile into the column dimension of the table drag and drop the ORPROV tile all trips have a province of origin into the row dimension of the table apply the _PTRIPWT and load the data The total number of person trips will be found at the first quarter row 31 193 087 divide the first estimate by the second estimate 3 731 742 037 31 193 087 119 63 Statistics Canada Catalogue 87M0006GPE CTS Wicrodata User s Guide 85 Canadian Travel Survey 9 GUIDELINES FOR RELEASE ee DATA QUALITY Microdata users should apply the rules for assessing data quality below to all estimates they produce and retain only those that satisfy the releas
32. al Surveys Division Statistics Canada 5D 7 Jean Talon Building Tunney s Pasture Ottawa Ontario K1A 0T6 Tel 951 3328 Fax 951 0562 2 CTS Wierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey a L Background INTRODUCTION TO CTS The tourism and travel industry is an important driving force in the Canadian economy In 1996 tourism spending amounted to 41 8 billion up from 39 9 billion in 1995 an increase of 4 7 The industry employed 491 900 people in 1996 a 2 increase over 1995 over the same period there was little or no growth in employment in the overall business sector of the economy Statistics Canada Catalogue No 13 220 XPB and Catalogue No 13 009 XPB The Canadian Travel Survey along with other surveys such as the International Travel Survey are important sources of data to measure the impact and state of the tourism and travel industry in Canada The Canadian Travel Survey was developed to measure the volume characteristics and economic impact of domestic travel by Canadians In official publications only those trips having a Canadian destination of 80 kilometres or more from home are included However the survey collects information for all overnight trips regardless of distance and for all same day trips having a one way distance from home of 80 kilometres or more 40 km in Ontario regardless of the destination Canada or other countries The surv
33. are rescaled so that the average weight is one 1 then the results produced by the standard packages will be more reasonable they still will not take into account the stratification and clustering of the sample s design but they will take into account the unequal probabilities of selection The rescaling can be accomplished by dividing each weight by the overall average weight before the analysis is conducted In order to provide a means of assessing the quality of tabulated estimates Statistics Canada has produced a set of Approximate Sampling Variability Tables commonly referred to as C V Tables for the Canadian Travel Survey These tables can be used to obtain approximate coefficients of variation for categorical type estimates and proportions Refer to Chapter 10 for more details 90 CTS Wierodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey Minimum sizes Before releasing and or publishing any estimate P from these microdata files users should first of estimates for determine the number of respondents who release contribute to the calculation of the estimate If this number is less than 30 the weighted estimate should not be released regardless of the value of the coefficient of variation for this estimate For weighted estimates based on sample sizes of 30 or more users should determine the coefficient of variation of the rounded estimate and follow the guidelines given in Table 5
34. ation of expenditures model is more refined than it was in 1994 Knowing that the amount of money spent on accommodation depends on the type of accommodation see table 3 page 50 it is possible to redistribute expenditures according to the number of nights spent in each location and the type of accommodation used Example of expenditure reallocation for accommodation A traveller reports having spent 350 in accommodation He spent two nights in a hotel in Ottawa and three nights camping in Mont Tremblant Considering that on average travellers spend 72 night when staying in a hotel and 13 night when camping the money spent in accommodation can be redistributed as Average spending per night in hotel 72 x 2 nights 144 Average spending per night camping 13 x 3 nights 39 Total average amount spent 183 Actual amount spent 350 Amount spent in hotel 144 183 350 275 41 Amount spent camping 39 183 350 74 59 Using this approach the Ottawa region would have 275 41 allocated in accommodation and the Mont Tremblant region would have 74 59 Using the 1994 approach the Ottawa region would have had 140 whereas the Mont Tremblant region would have had 210 Statistics Canada Catalogue 87M0006GPE CTS Wicradata User s Guide 45 Canadian Travel Survey Food or beverages bought in restaurants or bars and food or beverages bought in stores during the trip Spending in these categories de
35. ave been interviewed To the extent that this assumption is not true the estimates will be somewhat biased LFS Sub Weight The product of the previously described weighting factors is called the LFS sub weight All members of the same sampled dwelling have the same sub weight Subprovincial and Province Age Sex Adjustments The sub weight can be used to derive a valid estimate of any characteristic for which information is collected by the LFS In particular estimates are produced of the total number of persons 15 in provincial economic regions and the 24 large metropolitan areas as well as of designated age sex groups in each of the ten provinces Independent estimates are available monthly for various age and sex groups by province These are population projections based on the 1991 Census data records of births and deaths and estimates of migration In the final step this auxiliary information is used to transform the sub weight into the final weight This is done using a calibration method This method ensures that the Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 53 Canadian Travel Survey Weighting procedures for the CTS final weights it produces sum to the census projections for the auxiliary variables namely various age sex groups economic regions Census Metropolitan Areas and rotation groups This weighting procedure ensures consistency with external Census counts and that each
36. avel Survey numerator is an estimate of the total number of trips taken same day and overnight by persons who took at least one trip during the reference month and its denominator is the number of persons who took at least one trip during the reference month Examples of Quantitative Questions Q How many nights were you away from home on this trip R T I lnights Q Including yourself how many persons now living in this household went on this trip R __ people Tabulation of Categorical estimates of the number of people with z a certain characteristic can be obtained from the categ orical Beyond 20 20 files or from the microdata files by estimates applying the weight to the records possessing the characteristic s of interest Proportions and ratios of the form X Y are obtained by gt applying the weights of records having the characteristic of interest for the numerator X gt applying the weights of records having the characteristic of interest for the denominator Y then gt dividing the numerator estimate by the denominator estimate 82 CTS Wierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey Example using the Beyond 20 20 person file From the Beyond 20 20 person file to obtain an estimate of the number of people who took at least one non business overnight interprovincial trip in 1996 gt drag the YRSAMEPR tile in the column dimension and the
37. ble population Visit dataset The introduction of the visit concept in 1996 gives data users a more thorough picture of Canadians travelling to a specific region Besides providing Statistics Canada Catalogue 87M0006GPE CTS WUcerodata User s Guide 67 Canadian Travel Survey trip information main destination length of trip etc it also provides information on place s visited by those travellers whether it was their main destination or an overnight stop on their journey In addition to providing visit information the visit dataset also includes reallocated expenditures information A visit represents a trip as a whole or part of a trip A visit is defined as the place of overnight stay of the traveller or for a same day trip the location of destination of the trip If the respondent travelled twice to the same location during the same trip only one visit is recorded to that location For instance for a person going on a same day trip to Toronto from Kingston the count of visits and person trips would be the same that is one However for a person leaving Montreal in destination of Winnipeg who spent a night in Ottawa and then spent a night in Winnipeg we would have one record of a person trip to Winnipeg as a destination but two records of person visits one in Ottawa Hull and one in Winnipeg The visit concept is used to measure the number of person visits who went to a specific location The visit files have
38. can also be used with trip information to calculate incidences based on certain trip characteristics For example how many persons flew at least once during the month of January However proper selection has to be made when combining the person weight with 74 CTS Wccrodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey trip information refer to Chapter 7 person and trip dataset The person weight cannot be used to measure the volume of person trips because even used with a trip record it does not take into account the identical trips nor the number of persons who went on the trip Person trip This weight can only be associated with those iaht people who have taken a trip that is the travellers welig It can be used to measure the volume of person trips refer to Chapter 7 Person trip dataset It can be associated with the socio demographic characteristics of the travellers as well as the trip characteristics such as origin destination or purpose It cannot be associated with expenditures of trips because these represent the household expenditures and not just the traveller s expenses For microdata files users only The person trip weight is also used to calculate the number of person visits when using the person visit and reallocated expenditures file Househo Id trip The household trip weight can be associated with iaht the trip characteristics as well as the expenditures welg info
39. d rotated out of the sample by a new panel of dwellings selected from the same or similar clusters This rotation pattern was adopted to minimize any problems of non response or respondent burden that would occur if households were to remain in the sample for longer than six months It also has the statistical advantage of providing a common sample base for short term month to month comparisons of LFS characteristics Because of the rotation group feature it is possible to readily conduct supplementary surveys using the LFS design but employing less than the full size sample CTS asa The Canadian Travel Survey used two of the six rotation groups in the 1996 LFS sample in all supp lement provinces except in Newfoundland where the sample was augmented to three rotation groups For the Canadian Travel Survey the coverage of the LFS remains the same that is it includes all members of the household aged 15 and over However unlike the LFS where information is collected for all eligible household members the Canadian Travel Survey only collects information from one household member and proxy responses are not permitted 30 CTS Wierodata User e Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey For further information on the CTS sample size by month and by province refer to the Data Quality Report Chapter 10 Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 31 Canadian Travel
40. ditures are reported in Canadian dollars and include all taxes and tips As described above these expenditures are reported in different categories They do not represent where money was spent on a specific trip but rather how much money was spent and in which category of expenditures It is associated with a trip as a whole Reallocated expenditures Refers to the process by which the respondent s reported expenditures are redistributed to specific geographic regions where money was spent The CTS uses an expenditure reallocation model by which money included in each expenditure category is redistributed to a geographic region according to specific rules Generally money is allocated at the destination location in the case of same day trips and redistributed according to the number of nights spent in each geographic region in the case of overnight trips However this rule may vary according to the expenditure item for more details refer to Chapter 5 Once redistributed the expenditures are referred to as reallocated expenditures 18 CTS Mienodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey The level of geography for which the expenditures are redistributed in the CTS are the following province tourism region Census Metropolitan Area CMA and Census Division CD Here is an example of the reallocation process for accommodation expenditures declared by a respondent going from
41. e criteria Estimates that do not satisfy the release criteria are not reliable Introduction The guidelines for release and publication make use of the concept of sampling variability to determine whether estimates obtained from the microdata files are reliable Sampling variability is the error in the estimates caused by the fact that we survey a sample rather than the entire population The concept of standard error and the related concept of coefficient of variation and confidence interval provide an indication of the magnitude of the sampling variability The standard error and coefficient of variation do not measure any systematic biases in the survey data which might affect the estimate Rather they are based on the assumption that the sampling errors follow a normal probability distribution Subject to this assumption it is possible to estimate the extent to which different samples that have the same design and the same number of observations 86 CTS Wierodata User s Guide Statistics Canada Catalogue 87 MO006GPE Canadian Travel Survey would give different results This indicates the margin of error that is likely to be included in the estimates derived from our single sample For a detailed description of the measures of sampling variability see A Satin and W Shastry Survey Sampling A Non Mathematical Guide Statistics Canada Catalogue Number 12 602E Survey errors The survey produces estimates based on i
42. e to LFS interviewers than other areas For administrative purposes this portion of the 24 CTS Mierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey population is sampled separately through the remote area frame Some populations not congregated in places of 25 or more people are excluded from the sampling frame Secondary stratification In urban areas with sufficiently large numbers of apartment buildings the strata are subdivided into apartment frames and area frames The apartment list frame is a register which is based upon information supplied by Canadian Mortgage and Housing Corporation and is maintained in the 18 largest cities across Canada The purpose of this is to ensure better representation of apartment dwellers in the sample as well as to minimize the effect of growth in clusters due to construction of new apartment buildings In the major cities the apartment strata are further stratified into low income strata and regular strata Where it is possible and or necessary the urban area frame is further stratified into regular strata high income strata and low population density strata Most urban areas fall into the regular urban strata which in fact cover the majority of Canada s population High income strata are found in major urban areas while low density urban strata consist of small towns that are geographically scattered In rural areas the population densit
43. ese items may be a combination of transportation and accommodation or accommodation with food and beverages etc A package deal is usually purchased from a travel agency or social organization Expenditures Trip expenditures made by all household members who went on the trip Expenditures may have been paid for by individuals by government or by a private sector business In the CTS the expenditures are broken down in the following categories vehicle rental vehicle operation local transportation intercity transportation food or beverages purchased at restaurants or bars food or beverages purchased at stores during the trip accommodation recreation and entertainment clothing and other expenditures The following items are excluded gt food purchased before the trip for use while on the trip items purchased to be resold or used in business including items used on farm gt vehicles such as cars caravans boats gt capital investments such as real estate works of arts rare articles and stocks Statistics Canada Catalogue 87MO006GPE CTS Microdata User s Guide 17 Canadian Travel Survey gt cash given to relatives or friends during a holiday trip which does not represent payment of tourism goods or services as well as donations made to institutions Reported expenditures Reported expenditures are the expenditures made by the respondent and other household members who went on the trip Expen
44. estricted release only when exact coefficients of variation have been calculated on a cost recovery basis and are found to be acceptable Otherwise such estimates should not be used or released UNACCEPTABLE Estimates should not be used or released under any circumstances Statistics Canada Catalogue 87M0006GPE CTS Wicrodata User s Guide 93 Canadian Travel Survey estimate can be released The Data Quality Report Chapter 10 explains how to obtain the approximate CV from the tables depending on whether the estimate is a simple population count or a percentage difference or ratio of population subgroups In the case of numeric totals or means the CV is generally larger than the CV of the population count on which it is based All coefficients of variation in the Approximate Sampling Variability Tables are approximate and therefore unofficial Estimates of actual variance for specific variables may be obtained from Statistics Canada on a cost recovery basis The use of actual variance estimates would allow users to release otherwise unreleaseable estimates 1 e estimates with coefficients of variation in the confidential range Remember if the number of observations on which an estimate is based is less than 30 the weighted estimate should not be released regardless of the value of the coefficient of variation for this estimate This is because the formulas used for estimating the variance do not hold
45. ests Household income Total household income before taxes and deductions including income from wages salaries tips commissions pensions interest rents etc for all household members for the year preceding the reference year 12 CTS Mienodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey CTS concepts and definitions Educational attainment Highest level of schooling completed by the respondent Relationship to the family reference person Relationship of the respondent to the person who has been identified as the family reference person who is normally an adult with responsibility for the care or support of the family CTS reference month Month that ended before the collection period For example if the collection period is in February we are collecting information on trips that ended in January The collection period for the CTS includes the two weeks following the LFS reference week Trip For the purposes of the CTS a trip is defined as travel by the respondent accompanied or not by one or more household members for any reason except as noted below to a Canadian destination of at least 80 km one way from home The following types of travel are excluded travel to and from work or school 1 e commuting one way travel involving a change of residence travel of operating crew members of buses airplanes boats etc travel in an ambulance to a hospital or clinic
46. ey was first conducted in 1979 and beginning in 1980 has been conducted every two years Statistics Canada Catalogue 87M0006GPE CTS Wieradata User s Guide 3 Canadian Travel Survey Changes to the sampling frame have been introduced in the last few years From 1980 to the first quarter of 1992 the survey had been conducted on a quarterly basis that is the respondents were contacted at the end of the three month period and had to recall all trips taken in that period Because it was hard to remember all the trips taken in such a long period starting at the second quarter of 1992 the same respondent was contacted every month in that three month period This lead to trips being under reported by the second and third months of collection To improve the data quality in 1994 the collection method was changed again to have a new sample of respondents every month However the improvement in the collection method represents a break in the series Even though the 1992 data has been adjusted to be comparable with the historical series since 1980 the 1994 data have not been and therefore are not comparable with those of previous years The 1996 data however is comparable to the 1994 data Other changes concerning the content of the survey questionnaire have also been introduced For example for the first time in 1996 the survey collected information on visits at the subprovincial level Previously in terms of geographic info
47. family of two adults and two children going to the Zoo using the household trip concept they would all go through the turnstile as a group and would be counted as one household trip Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 65 Canadian Travel Survey A user would apply the household trip concept to know how many business trips were taken within the last year how many groups of people went on business trips within the year or how many trips were taken by plane in July how many groups of people went on trips by air in July Notice that the socio demographic characteristics CANNOT be associated with the household trip weight When compiling household trip information one has to use the household trip weight available on the files called LHHTRWT on the Beyond 20 20 files and HHTRIPWT on the microdata files Both the person trip and household trip information provided on each monthly person trip file is additive It is possible to obtain monthly quarterly or annual information for each variable on the person trip dataset Beyond 20 20 users only have to make the proper preselection on the variables MONTH reference month or QUARTER quarter and then produce the required table Microdata file users have to first combine the monthly person trip files to create the file for the required time period Then by making the proper selection when defining their population on the variables MONTH or QUARTER
48. ght is calculated by adjusting the person trip weight in the following way PERSON TRIP WEIGHT number of adults from same household who went on the trips The weights are then used to produce the appropriate estimates A description of the different weights and their uses is provided in Chapter 7 Using the Microdata Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 57 Canadian Travel Survey 77 ES File description Person dataset USING THE MICRODATA The Beyond 20 20 microdata files contain three different annual datasets with one being provided at four different geographic levels that is the visit dataset provided at the province Census Metropolitan Area tourism region and Census Division level It also contains a person and person trip dataset The information provided on those files is for trips of 80 km or more with a Canadian destination The CTS microdata files contain four different monthly datasets with one being provided at four different geographic levels that is the person visit dataset provided at the province Census Metropolitan Area tourism region and Census Division level It also contains a person trip and person trip dataset The information provided on those files is for same day trips of 80 km or more 40 km in Ontario and all overnight trips regardless of distance Following is a description of each dataset The person dataset provides information on travellers and
49. had 80 whereas the Mont Tremblant region would have had 120 Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 47 Canadian Travel Survey TABLE 1 Allocation of expenditures at a sub provincial level same day trips 1996 Location Location of origin of desti nation SAME DAY TRIPS Vehicle rental X Vehicle operation X PU Local transportation Intercity transportation X Food or beverages bought in X restaurants or bars Food or beverages bought in X stores during the trip Accommodation Recreation and entertainment Clothing x lt Xx ii ad Other expenses 48 CTS Wierodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey TABLE 2 Allocation of expenditures at a sub provincial level overnight trips 1996 OVERNIGHT TRIPS Loc of origin Vehicle rental primary mode automobile primary mode commercial Vehicle operation Local transportation x Food or beverages bought in X 2 restaurants or bars Food or beverages bought in X 2 stores during the trip Accommodation X 2 Recreation and entertainment Cimin L X Clothing X EMES 1 If main mode of transportation is airplane train buses or boat then vehicle rental expenditures are allocated to the province of destination If main mode of transportation is a car or other vehicle rental fees are allocated to the pro
50. ht HHTRIPWT provided on the datasets Using the CTS The sample design used for the Canadian Travel Survey is not self weighting When producing weights simple estimates including the production of ordinary statistical tables users must apply the Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 73 Canadian Travel Survey Person weight proper sampling weight This part describes the use of the different weights associated with the survey If proper weights are not used the estimates derived from the microdata files cannot be considered representative of the survey population and will not correspond to those produced by Statistics Canada Users should also note that some software packages may not allow the generation of estimates that exactly match those available from Statistics Canada because of their treatment of the weight field When using the microdata datasets one should try replicating some tables that are already included in Acrobat under the Quality Indicators on the CD ROM and use the figures as a benchmark to verify the validity of the tables generated The person weight can be used to measure the number of travellers and non travellers It can be associated with all the socio demographic variables describing the respondent Used with the person records the user can get a socio demographic profile of travellers and non travellers or calculate travel incidences The person weight
51. iables MONTH or QUARTER and then produce the required table Microdata file users first have to combine the monthly person visit files to create the file for the required time period Then by making the proper selection when defining their population on the variables MONTH or QUARTER they can obtain the required information 70 CTS Wierodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey For Beyond 20 20 users only This visit dataset contains both the visit and reallocated expenditures information combined with selected traveller and trip characteristics One dataset is provided for each level of geography On each visit file some traveller and trip characteristics are included only to be used as a selection criteria to compile visit information and not to compile trip information the trip characteristics cannot be associated with the weights provided on the visit files see table 4 to find out which weights can be used with different variables To get information on trips one should use the person trip file When compiling visit information one has to use the person visit weight _PVISWT included on the datasets One must also make the proper selection of visit records by using only the ones where the visit flag VISFLAG is equal to 1 When compiling reallocated expenditures information one has to use the reallocated expenditures weight _REXPWT included on the datasets For microdata fi
52. ion Once linked more editing is performed on the files Gross errors such as the numbers of nights away from home not matching in different questions as well as errors in question flows are reviewed and corrected The edited files are then processed through the weighting system which derives appropriate response rates for each record and computes the person household trip and person trip weights Refer to Chapter 6 for more information on weighting procedures and Chapter 7 for more information on using the different CTS weights This series of edits consists of more thorough validity checks to detect inconsistencies and outliers in the data This step occurs after the origin and destination place names have been geo coded Once again errors are reviewed and corrected The expenditures are the only data in the CTS which are imputed All other values which are found to be missing or in error are either corrected or converted to a not stated code The expenditures however must be complete so that aggregate estimates of expenditures can be produced Missing expenditure information is imputed based on the average expenditures of respondents whose expenditure information was reported These are Statistics Canada Catalogue 87M0006GPE CTS Wicradata User s Guide 41 Canadian Travel Survey the donor respondents whose expenditures will be used to compute average expenditures used to impute the missing expenditure
53. ior interviewers are in turn under the supervision of the LFS program managers located in each of the eight Statistics Canada regional offices Interviewers are instructed to make all reasonable attempts to obtain LFS interviews with members of eligible households For individuals who at first refuse to participate in the LFS a letter is sent from the Regional Office to the dwelling address stressing the importance of the survey and the household s cooperation This is followed by a second call or visit from the interviewer For cases in which the timing of the interviewer s call or visit is inconvenient an appointment is arranged to call back at a more convenient time For cases in which there is no one home numerous call backs are made Under no circumstances are sampled dwellings replaced by other dwellings for reasons of non response Each month after all attempts to obtain interviews have been made a small number of non responding households remain For households non responding to the LFS and for which LFS information was obtained in the previous month this information is brought forward and used as the current month s LFS information For a supplementary survey such as the Canadian Travel Survey if the LFS demographics section is not completed then the CTS cannot be generated 34 CTS Mierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey CTS data The Canadian Travel Survey u
54. ith respect to the survey procedures and questionnaire observation of interviewers to detect problems of questionnaire design or misunderstanding of instructions procedures to ensure that data capture errors are minimized and coding and edit quality checks to verify the processing logic A major source of non sampling errors in surveys is the effect of non response on the survey results The extent of non response varies from partial non response failure to answer just one or some questions to total non response Total non response occurs because the interviewer is either unable to contact the respondent no member of the household is able to provide the information or the respondent refuses to participate in the survey Total non response is handled by adjusting the weight of households who respond to the survey to compensate for those who do not respond refer to Chapter 6 In most cases partial non response to the survey occurs when the respondent does not understand or misinterprets a question refuses to answer a 88 CTS Wierodata User s Guide Statistics Canada Catalogue 87 M0O006GPE Canadian Travel Survey Hypothesis tests provided by statistical software packages question cannot recall the requested information or cannot provide proxy information Since it is an unavoidable fact that estimates from a sample survey are subject to sampling error sound statistical practice calls for researchers to provide
55. itories persons living on Indian Reserves full time members of the Canadian Armed Forces and inmates of institutions These groups together 22 CTS Mierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey represent an exclusion of approximately 2 of the population aged 15 or over LFS sam p le The LFS has undergone an extensive redesign desi culminating in the introduction of the new design at esign the end of 1994 The LFS sample is drawn from an area frame and is based on a stratified multi stage design that uses probability sampling The successive stratification and sampling stages are outlined below A detailed description of the previous LFS design can be obtained in Methodology of the Canadian Labour Force Survey Statistics Canada Catalogue No 71 526 A diagram summarizing the design stages appears at the end of this section The main advantage of a stratified sample design is that when sampling is applied separately to many diverse strata each stratum having a relatively homogeneous population the efficiency of the sample is higher than that obtained from simple random sampling without stratification Primary stratification First each province is divided into economic regions set by federal provincial agreements and employment insurance regions Economic regions ERs are geographic areas of more or less homogeneous economic structure and are relatively stable over time Emp
56. ken 1 resulting in the intermediate weight This accounts for the trip that was described by the respondent as well as other trips the respondent reported taking which were identical to the described trip To calculate the person trip weight the intermediate weight is adjusted by the following ratio total number of trips that the respondent reported divided by the number of trips that the respondent described The adjustment of trips depends on the type of trip same day or overnight For example the weight for a same day trip is adjusted by the ratio of the total number of same day trips that the respondent reported divided by the number of same day trips that the respondent described This adjustment is necessary since not all respondents provide descriptions of all of the trips that they 56 CTS Wicrodata User e Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey reported taking For instance a respondent may report having taken five trips yet after providing details for three trips may decline to provide details for the remaining two trips Finally in order to calculate the household trip weight the person trip weight is simply divided by the number of adults including the respondent who went on the trip The person trip weight is calculated in the following manner PERSON WEIGHT number of identical trips 1 number of reported trips number of described trips The household trip wei
57. le users only The visit and reallocated expenditures datasets include province Census Metropolitan Area tourism region or Census Division visit and reallocated expenditures information only that is visit location visit length money spent by travellers in that location etc Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 71 Canadian Travel Survey To use the information provided on the visit and reallocated expenditures files one has to merge the file presenting the proper geographical level of information with the appropriate person trip file same time period This will give the user the socio demographic characteristics of the travellers who visited a specific location as well as the trip characteristics When the person trip and visit files are merged one has to be careful about which variables can be used in association with the different weights If one wants to compile visit information one can use traveller and trip characteristics to select a population subgroup and should use the PTRIPWT variable on that file the trip characteristics cannot be associated with the weights provided on the visit files see table 4 to find out which weights can be used with different variables To get information on trips one should use the person trip file Trip destination and trip distance are two criterions that are essential to have when compiling visit and reallocated expenditures information Remember
58. loyment insurance economic regions EIERs are also geographic areas and are roughly the same size and number as ERs but they Statistics Canada Catalogue 87M0006GPE CTS Wicradata User s Guide 23 Canadian Travel Survey do not share the same definitions Labour force estimates are produced for the EIER regions for the use of Human Resources Development Canada The intersections of the two types of regions form the first level of stratification for the LFS These ER EIER intersections are treated as primary strata and further stratification is carried out within them Note that a third set of regions Census Metropolitan Areas CMAs is also respected by stratification in the current LFS design since each CMA is also an EIER Types of areas Each ER EIER intersection is in turn divided into rural urban and remote areas Urban and rural areas are loosely based on the Census definitions with some exceptions to allow for the formation of strata in some areas Urban areas include the largest CMAs down to the smallest villages categorized by the 1991 Census as urban 1 000 people or more while rural areas are made up of areas not designated as urban or remote All urban areas are then further subdivided into two types that is those using an apartment list frame as well as an area frame and those using only an area frame Approximately 1 of the LFS population is found in remote areas of provinces which are less accessibl
59. nding file The reallocated expenditures are recorded at the level of geography represented on the file For example that same person who takes a trip to Edmonton and spends 200 in Calgary and 100 in Edmonton would show reallocated expenditures of 200 total reallocated visit expenditures shown in RREPCOST in Statistics Canada Catalogue 87M0006GPE CTS WUcerodata User s Guide 69 Canadian Travel Survey Calgary and 100 in Edmonton on the CMA visit file On the province visit file this person would show 300 total reallocated visit expenditures shown in RREPCOST in Alberta The reallocation of expenditures is performed based on expenditures reported by respondents using the model of expenditures reallocation developed with the CTS Working Group refer to Chapter 5 on Data Processing Historically the reallocation of expenditures was done at the provincial level however in 1996 because of the new visit information available the process of expenditures reallocation was expanded at the sub provincial level It is now possible to know how much money travellers spent in the Regina CMA or in the tourism region of Charlevoix As for the person trip and household trip information the person visit information provided on each monthly visit file is additive Itis possible to obtain monthly quarterly or annual information from each variable from these files For Beyond 20 20 users only make the proper preselection on the var
60. nformation collected from and about a sample of individuals Somewhat different estimates might have been obtained if a complete census had been taken using the same questionnaire interviewers supervisors processing methods etc as those actually used in the survey The difference between the estimates obtained from the sample and those resulting from a complete count taken under similar conditions is called the sampling error of the estimate Errors which are not related to sampling may occur at almost every phase of a survey operation Interviewers may misunderstand instructions respondents may make errors in answering questions the answers may be incorrectly entered on the computer and errors may be introduced in the processing and tabulation of the data These are all examples of non sampling errors Over a large number of observations randomly occurring errors will have little effect on estimates derived from the survey However errors occurring Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 87 Canadian Travel Survey systematically will contribute to biases in the survey estimates Considerable time and effort are made to reduce non sampling errors in the survey Quality assurance measures are implemented at each step of the data collection and processing cycle to monitor the quality of the data These measures include the use of highly skilled interviewers extensive training of interviewers w
61. non travellers a traveller being a person who takes at least one trip during the reference month or the reference year and a non traveller being someone who does not take a trip 58 CTS Wierodata User Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey Each respondent to the CTS has one record on the person file whether or not that person went on a trip during the reference month or the reference year The sum of all travellers and non travellers adds up to the non institutional Canadian population aged 15 and over on each monthly file and on the annual file December supplementary section see below The person microdata file includes socio demographic information on both travellers and non travellers It is useful to produce socio demographic profiles and to calculate travel incidences For example what is the age sex or educational attainment of travellers versus non travellers What percentage of the population 55 years of age and over travelled The person microdata file does not provide information on the volume of trips or person trips taken but rather on the volume of travellers and non travellers If a person travelled more than once during the reference period that person will be counted only once as a traveller When using the person file and compiling travellers information alone or linked with the TRIP file only the person weight can be used From the annual dataset provided
62. ntages should be rounded to one decimal point Note that all calculations are to be derived from their unrounded components and then rounded using the normal rounding technique Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 79 Canadian Travel Survey In normal rounding if the first or only digit to be dropped is 0 to 4 the last digit to be retained is not changed If the first or only digit to be dropped is 5 to 9 the last digit to be retained is raised by one For example in normal rounding to the nearest 1000 the estimate 49 448 would be rounded down to 49 000 and an estimate of 49 552 would be rounded up to 50 000 The figure 1 78 would be rounded to 1 8 In instances where due to technical or other limitations a rounding technique other than normal rounding is used resulting in estimates to be published or otherwise released which differ from corresponding estimates published by Statistics Canada users are urged to note the reason for such differences in the publication or released document s Type s of Before discussing how the Canadian Travel Survey data can be tabulated it is useful to describe the estimates two main types of point estimates of population characteristics which can be generated from the files for the Canadian Travel Survey that is categorical or quantitative estimates Categorical Estimates Categorical estimates are estimates of the number or percentage of the
63. ourneys and those who take them Specific survey objectives are to provide estimates of the volume of travel by Canadians to Canada by origin and destination mode of transportation used and trip purpose Statistics Canada Catalogue 87M0006GPE CTS Wieradata User s Guide 5 Canadian Travel Survey CTS products provide estimates of the volume of visits by Canadians to Canada by origin and location visited length of stay and types of accommodation used provide a picture of the socio demographic characteristics of travellers and non travellers provide estimates of the expenditures on travel by category of expenditure e g transportation accommodation food clothing etc provide estimates of the contribution of domestic demand for touristic goods and services on the national and provincial economies The results of the survey are published in Touriscope Domestic Travel Catalogue 87 504 which is prepared by the Tourism Statistics Program of Statistics Canada The publication contains a selection of statistics on travel by Canadians within Canada It is a valuable reference document for various players in the tourism industry because it contains the most current statistics on domestic tourism indicates provincial differences in terms of trips and expenditures by tourists identifies market segments gives an idea of potential uses of the CTS database 6 CTS Microdata User s Guide Statistics
64. ow hey ce tevin A a Legs 73 Person Weight iia wie copes otic ite aha ice aba aes ERAT RC Cosa LG O O lahat Mn omen ast Sa 74 Person trip weight ir ate Fa REE hee ee Be ep ri 75 Household trip weight sn ee a oe ee tide oS 75 Person visit weight for Beyond 20 20 users only 00 c eee cee ee eee 76 Reallocated expenditures weight for Beyond 20 20 users only 717 Using the data dictionary abia ca ENT Ge ees 77 8 GUIDELINES FOR ANALYSIS AND PRESENTATION 79 Rounding guidelines reiini ieat E ia O VR 4 CE 0 TE RVE ene ene n een eens 79 Types of estimates s gt oaan A A a Seen 80 Tabulation of categorical estimates cccccccccc ecce ecce 82 Tabulation of quantitative estimates 0 eect eee tenes 84 CTS Wicrodata User s Guide Statistes Canada Catalogue 87M0006GPE Table of contents continued Page 9 GUIDELINES FOR RELEASE DATA QUALITY cece ee 86 INTFOUCLON 227520 esata er ia A R EE RE Aik BA eng RR he Bede RR T ROA AS R R 86 S 111 845342 n ro O P P Ar E eek cece De T bie ble palas Ros 87 Hypothesis tests provided by statistical software packages 4 5 89 Minimum sizes of estimates for release nor 91 Using the coefficient of variation CV 0 cece ene e eens 91 Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide Canadian Travel Survey OVERV
65. pends on the type of accommodation used As a basic rule travellers staying in commercial accommodation tend to spend more on food bought in restaurants or bars than travellers staying in cottages camping or staying with friends or relatives table 3 The reallocation process for these two categories is the same as the one used for accommodation expenditures Example of expenditure reallocation for food or beverages bought in restaurants or bars A traveller reports having spent 200 for food or beverages bought in restaurants or bars He spent two nights in a hotel in Ottawa and three nights camping in Mont Tremblant Considering that on average travellers spend 34 night on food or beverages in restaurants or bars when staying in a hotel and 8 50 night when camping the money spent in accommodation can be redistributed as Average spending per day in hotel 34 x 2 nights 68 Average spending per day camping 8 50 x 3 nights 25 50 Total average amount spent 93 50 Actual amount spent 200 Amount spent in hotel 68 93 50 200 145 45 Amount spent camping 25 50 93 50 200 54 55 46 CTS Wierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey Using this approach the Ottawa region would have 145 45 allocated for food or beverages bought in restaurants or bars and the Mont Tremblant region would have 54 55 Using the 1994 approach the Ottawa region would have
66. r data by modem to the nearest Statistics Canada regional office For security reasons the data are encrypted during transmission In all dwellings information about all household members is obtained from a knowledgeable household member usually the person at home when the interviewer calls Such proxy reporting which accounts for approximately 55 of the information collected is used to avoid the high cost and extended time requirements that would be involved in repeat visits or calls necessary to obtain information directly from each respondent At the conclusion of the LFS monthly interviews interviewers introduce the supplementary survey if any to be administered to some or all household members that month If during the course of the six months that a dwelling normally remains in the sample an entire household moves out and is replaced by a new household information is obtained about the new household for the remainder of the six month period LFS All LFS interviewers are under the supervision of a Z z staff of senior interviewers who are responsible for Interviewers ensuring that interviewers are familiar with the concepts and procedures of the LFS and its many supplementary surveys and also for periodically monitoring their interviewers and reviewing their Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 33 Canadian Travel Survey Non response to the LFS completed documents The sen
67. rmation It cannot be associated with socio demographic characteristics of the respondents The household trip weight is used to measure the number of household trips taken refer to Chapter 7 Person trip dataset Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 75 Canadian Travel Survey Person visit weight for Beyond 20 20 users only For Beyond 20 20 users only The household trip weight is to be used when compiling information on the number of household trips taken and reported expenditures refer to Chapter 7 Person trip dataset For microdata file users only The household trip weight is to be used when compiling information on the number of household trips taken and both reported expenditures provided on the person trip file and reallocated expenditures provided on the person visit and reallocated expenditures files refer to Chapter 7 Person trip dataset This weight is to be used when compiling person visit information from the visit files Itis used to measure the number of person visits It can be associated with all the socio demographic and visit variables refer to table 4 For example one would apply the person visit weight to get the number of person visits who went to the tourism region of Regina or to get a socio demographic profile of those people who visited the Toronto CMA 76 CTS Wierodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel
68. rmation only origin destination and number of nights spent in each province were available With the introduction of the visit concept it is possible to keep track of every location visited on a particular trip This means that the expenditure data can be reallocated at different geographic levels Before 4 CTS Wierodata User Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey 1996 the money reported as having been spent during the trip could only be redistributed at the provincial level Because we now have information on each geographic area visited the expenditures can be reallocated at the sub provincial level These changes came about after the Tourism Research Working Group TRWG made recommendations This group has been formed so that the Canadian Tourism Commission CTC as well as the provinces could participate in recommending changes to the survey The Canadian Travel Survey is a federal provincial project Until 1990 Tourism Canada now the Canadian Tourism Commission assumed the cost of the basic survey and the provinces shared the cost of increasing the sample size Since 1992 the cost of the basic survey has been shared by the CTC and the provincial governments Objecti ves The Canadian Travel Survey s general objective is to provide measures of the volumes and characteristics of Canadian travellers and the domestic trips they take Its purpose is to gather information on these j
69. s items such as souvenirs shoes belts jewellery handbags and household items registration fees for courses or conferences customs duties postcards and stamps insurance fees medication books craft supplies film and developing costs for child care telephone charges etc Statistics Canada Catalogue 87M0006GPE CTS Wicradata User s Guide 21 Canadian Travel Survey LFS population coverage SAMPLE The Canadian Travel Survey is administered to one or more sub samples of households in the Labour Force Survey LFS sample and therefore its sample design is closely tied to that of the LFS Except for differences in sample size the design features of the LFS sample are maintained in the CTS sample Non response to the LFS also carries over to CTS except in those cases where the LFS interviews could not be conducted in the current reference month because of temporary circumstances and when in an earlier month the LFS data was collected The LFS has response rates of 95 or higher The LFS design is briefly described in this chapter The last part of the chapter describes how the Canadian Travel Survey departed from the basic LFS design in 1996 The LFS is a monthly household survey whose sample of individuals is representative of the civilian non institutionalised population 15 years of age or older in Canada s ten provinces Specifically excluded from the survey s coverage are residents of the Yukon and Northwest Terr
70. s will be collapsed to include trips with any reason for the trip and so on Once a set of donor averages has been computed for all levels of trips characteristics the trips requiring imputation are then matched to the averages for trips with the same characteristics and the missing expenditures are calculated An additional step in the imputation process is the distribution of package deal expenditures to specific expenditure categories This is accomplished in the same fashion as expenditure imputation donor averages are used to impute the expected value of the expenditure items included in the package deal these imputed amounts are then ratio adjusted to arrive at the total amount reported for the package deal Imputed expenditures are then reedited to ensure that no outlier values have been created by the expenditure imputation process Reallocation of allocation of expenditures is the process by r which the respondent s reported expenditures are expenditures redistributed to specific geographic regions where money was spent The CTS uses an expenditure reallocation model by which money included in each expenditure category is redistributed to a geographic region according to specific rules Generally money is allocated at the destination location in the case of same day trips and redistributed according to the number of nights Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 43 Canadian Travel Sur
71. ses computer assisted E interviewing CAD 1 e the questionnaire 1s collection designed for a laptop computer and the interviewer keys in reported information during the interview Some of the benefits of CAI come from on line editing of information as it is received refer to Chapter 5 on data processing This collection method also helps in avoiding errors associated with the electronic transcription of data written on the paper questionnaire The survey is administered to one randomly selected individual per household Only old respondents to the LFS who were already interviewed at least one month before can be selected as respondents to the CTS The CTS program automatically selects the respondent from the LFS demographics component It prefills the respondents first and last names Because of the possibility of duplicate names within the household and because some names are gender neutral it also indicates the age and sex of the respondent Upon completion of the Labour Force Survey interview the interviewer asks to speak to the selected person for the Canadian Travel Survey If the selected person is not available the interviewer arranges for a convenient time to phone back Proxy response is not allowed hence the collection period is extended by one week to allow the interviewers time to contact the selected individuals Statistics Canada Catalogue 87M0006GPE CTS Wicradata User s Guide 35 Canadian Travel Survey
72. sitters newspaper carriers with employees Self employed unincorporated without employees self employed with an unincorporated business 1 e a business farm or professional practice that 1s not incorporated or without a business e g baby sitters newspaper carriers without employees Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 11 Canadian Travel Survey Unpaid family worker person working without pay on a farm or in a business or professional practice owned and operated by a related member of the same household Industry General nature of the business carried out by the employer for whom the respondent works If the respondent did not have a job during the reference week the information is collected for the last job held providing the respondent worked within the previous twelve months This variable is not available on the Beyond 20 20 files or on the microdata files but can be used in special requests Occupation Kind of work the respondent was doing during the LFS reference week as determined by the kind of work reported and the description of the respondent s most important duties If the respondent did not have a job during the reference week the information is collected for the last job held providing the respondent worked within the previous twelve months This variable is not available on the Beyond 20 20 files or on the microdata files but can be used in special requ
73. son trip dataset contains socio demographic d t t and trip characteristics On that file there are adult atase records and child records There is only one record Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 63 Canadian Travel Survey for adults from the same household despite the number of adults who went on the trip the person trip weight for that record is adjusted accordingly If there were children from the same household accompanying the adult s there is only one record for children despite the number of children who went on the trip the person trip weight for that record is adjusted accordingly From the person trip file one can obtain person trip or household trip information A person trip is defined as a trip taken by one person If this person takes more than one trip and or travels with other members of the same household we will count as many person trips as there are trips and persons who took these trips If four persons from the same household go on a trip together it counts as four person trips If the same person takes two trips it counts as two person trips The person trip dataset takes into account the number of persons from a same household who accompanied the respondent on a specific trip and the frequency of travel The person trip concept is used to measure the total number of trips combined with the total number of people who went on the trip To make this concept more
74. surveyed population possessing certain characteristics or falling into some defined category The number of people 15 80 CTS Wierodata User s Guide Statistics Canada Catalogue 87 MO006GPE Canadian Travel Survey years of age or more who took at least one same day trip in the reference month or the proportion of trips taken which were business related are examples of such estimates An estimate of the number of persons possessing a certain characteristic may also be referred to as an estimate of an aggregate Examples of Categorical Questions Q Did you take any trips of one night or more which ended in reference month R Yes No Q What was your main reason for taking this trip R Visiting friends or relatives Pleasure Personal Business Non business convention Quantitative Estimates Quantitative estimates are estimates of totals or of means medians and other measures of central tendency of quantities based upon some or all of the members of the surveyed population They also specifically involve estimates of the form X Y where X is an estimate of surveyed population quantity total and Y is an estimate of the number of persons in the surveyed population contributing to that total quantity An example of a quantitative estimate is the average number of trips taken per person who travelled during the reference month The Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 81 Canadian Tr
75. t on meals and drinks purchased from restaurants bars cafeterias fast food take out counters and minibars located in some hotel motel rooms regardless where they were consumed Food or beverages purchased at stores during the trip Includes the total amount spent at local stores while on the trip regardless of where they were consumed For example groceries purchased to bring home or to eat during the trip are included in this category Accommodation expenditures Total expenditures for nights spent in hotels motels resorts cabins cottages campgrounds etc This primarily includes rental fees However in the case of trips to private cottages or the home of friends or relatives it could also include any money given to owners for the use of their accommodation 20 CTS Wierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey Recreation and entertainment expenditures Includes the cost of admission to theatres sports events art galleries nightclubs etc It also includes gambling expenses and sporting activity costs such as daily ski lift passes green fees rental of sports equipement entrance fees to a cultural or leisure activity boat and bus tours but excludes recreation and entertainment purchased for the season e g season ski passes Clothing expenditures Includes any clothing purchases whether they are gifts or for personal use Other expenditures Include
76. table job had been offered or they had been recalled if on temporary layoff or if the reason they could not take a job was of a temporary nature such as own illness or disability personal or family responsibilities vacation or they already had a job to start in the near future Full time students currently attending school and looking for full time work are not considered to be available for work during the reference week since they are 10 CTS Wierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey assumed to be looking for a job to start sometime in the future Class of worker Category of employer employee relationship or self employment for the respondent s job or business If the respondent did not have a job during the reference week the information is collected for the last job held providing the respondent worked within the previous twelve months Paid worker private sector employee of a private firm or business or self employed with an incorporated business Paid worker public sector employee of a local provincial or federal government a government service or agency a Crown corporation or a government owned public establishment such as a school or a hospital Self employed unincorporated with employees self employed with an unincorporated business 1 e a business farm or professional practice that 1s not incorporated or without a business e g baby
77. talogue 87M0006GPE CTS Mienodata User s Guide Canadian Travel Survey Table of contents continued Page 5 DATA PROCESSING oiia 4424 cee A A NCA AR ES ERS 38 Data Capra ER o AR Na dra e asaya cara NA r dde dle dA a beds 38 Preliminary editing seco a e EA core a ogee eats 39 Ranking to the LES potaje dent doles ih diane ttle od aan a e a e 39 Geographic codis nia A e Rl wit A te 39 Secondary ed tin eae les calls adenine Satay eee eA Oa E eee tg il otal 41 WEE 22725754 A Pa ee IG SS 41 Consistency edits seses n nenir ste A pte ead aka eee 41 Expenditure imputation iier ca imee Pia Pene E AA Ea E E A E E a 41 Reallocation of expenditures ccc ccc r errereen 43 Data TEVIEW n eset Baths anne enn dene Dir ltd healed aod E a a E a 50 6 WEIGHTING sa 25 irori E 0225604 LR DV teed E e a EE Taah A EE SE 51 Weighting procedures for the LFS 0 0000004004400000 004444444 51 Weighting procedures for the CTS 0000000000404000 0000000044 54 7 USING THE MICRODATA diia a 58 File de SCripti NT 212 a328 g 2 EA rd Os pe eR iE ks DUE ee pee NEE S oes 58 Person dataset tcc spear cele A a tele G SI A dad 58 Trip dataset available only for microdata files users 2020000220 eee 62 Person trip dataset ii r batera taa A bate be ies leg a Wee 4 54 63 Visit dataset g c s uchiha AS io te Se ta ea aes ee cha ii 67 Using the CIS weights ceni os G
78. the Data Quality Report Chapter 10 Statistics Canada Catalogue 87M0006GPE CTS Wicradata User s Guide 37 Canadian Travel Survey DATA PROCESSING The main output of the Canadian Travel Survey is a set of clean microdata files This chapter presents a brief summary of the processing steps involved in producing these files Data ca ptu re Capture of survey data is accomplished as the interview is done Computer Assisted Interviewing CAI allows the interviewers to key in the data as the respondent reports it After the interview is completed the data are electronically transmitted to regional offices for further processing As the data are captured on line editing is done CAI controls the sequence or flow of questions resulting from previous question responses so that problems caused by incorrect flows are minimized Other checks are also done during the interview to reduce the number of errors resulting from typing mistakes or misunderstandings For example if the number of nights spent in different types of accommodation does not add up to the total number of nights spent away from home an edit message appears The interviewer can then correct the mistake and less editing has to be performed at head office Although some checks are done during the interview there are almost no cases where the interviewer must correct the information at worst 38 CTS Wierodata User e Guide Statistics Canada Catalogue
79. they can obtain the required information Reported expenditures information Reported expenditures are only available on the person trip file When compiling reported 66 CTS Wierodata User s Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey expenditures refer to Chapter 2 for difference between reported and reallocated expenditures information from the person trip file only the household trip weight can be used because these represent the household expenditures and not just the traveller s expenses For microdata file users only Microdata file users will notice that some records included on the person trip file contain partial information only Those are child records that is records for children from the same household as the respondent who accompanied them on the trip Those child records have blank fields or Os for the socio demographic variables the household trip weight and the expenditures information They must be included when compiling person trip information Because these records have a household trip weight equal to 0 by default they will not appear in household trip counts Remember according to Statistics Canada s definition of a trip a person must have travelled for 80 km or more from home and must have travelled to a Canadian destination Do not forget to make the proper selection on the variables DISTANC distance and DEPROV province of destination when defining the eligi
80. tion Areas EAs are used as clusters In the low density urban strata a three stage design is followed Under this design two towns within a stratum are sampled and then six or 24 clusters within each town are sampled 26 CTS Mierodata User e Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey For urban apartment strata instead of defining clusters the apartment building is the primary sampling unit Apartment buildings are sampled from the list frame with probability proportional to the number of units in each building Within each of the secondary strata in rural areas where necessary further stratification is carried out in order to reflect the differences among a number of socioeconomic characteristics within each stratum Within each rural stratum six EAs or two or three groups of EAs are sampled as clusters Dwelling selection In all three types of areas urban rural and remote areas selected clusters are visited by enumerators in the field to prepare a listing of all private dwellings in the cluster From the listing a sample of dwellings is then selected The sample yield depends on the type of stratum For example in the urban area frame sample yields are either 6 or 8 dwellings depending on the size of the city In the urban apartment frame each cluster yields 5 dwellings while in the rural areas and EA parts of cities each cluster yields 10 dwellings In all clusters dwellings are
81. true for small sample sizes 94 CTS Wicrodata User y Guide Statistics Canada Catalogue 87M0006GPE
82. ukon and Northwest Territories persons living on Indian Reserves full time members of the Canadian Armed Forces and persons living in institutions e g inmates of penal institutions and patients in hospitals or nursing homes who have resided in the institution for more than six months these groups together represent an exclusion of approximately 2 of the Canadian population aged 15 and over LFS reference week Entire calendar week Sunday to Saturday covered by the LFS each month Itis usually the week containing the 15th day of the month Statistics Canada Catalogue 87M0006GPE CTS Microdata User s Guide 9 Canadian Travel Survey Labour Force Status Status of the respondent in the labour market that is employed unemployed or not in the labour force Employed did any work at all at a job or business during reference week excluding unpaid housework and volunteer work or absent from a job for a reason other than layoff Unemployed not employed but available for work during reference week and looked for work at some time during the month OR absent from a job due to temporary layoff OR had a new job to start within four weeks of reference week Not in the labour force unwilling or unable to offer or supply labour services that is not employed or unemployed during reference week Persons are regarded as available for work if they reported that they could have worked in the reference week if a sui
83. understandable let us take a family of two adults with two children If they all go to a zoo using the person trip concept they will each have to go through the turnstile We would count them as four person trips This concept can be associated 64 CTS Wierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey with both the socio demographic variables and the trip characteristics variables If a user wants to know how many person trips were made by plane in April how many adults and children took a trip in April and used the plane as their mode of transportation or how many person trips were made to the Calgary CMA as a final destination in November how many adults and children took a trip to the Calgary CMA in November one has to use the person trip concept from the person trip dataset When compiling person trip information one has to use the person trip weight available on the files called _PTRIPWT on the Beyond 20 20 files and PTRIPWT on the microdata files A household trip is defined as a trip involving one or more persons from the same household leaving and returning together If four persons from the same household go on a trip together that is they leave and return together it counts as one household trip If the same household takes two trips it counts as two household trips The household trip concept is used to measure the total number of trips In our same example of a
84. vey spent in each geographic region in the case of overnight trips However this rule may vary according to the expenditure item for more details refer to tables 1 and 2 on pages 48 and 49 Once redistributed the expenditures are referred to as reallocated expenditures In 1996 data providing more detailed information have been collected and allowed the redistribution of the reported expenditures at a sub provincial level By using the additional information available at the locational level namely number of nights spent at a location types of accommodation used and number of nights spent by type of accommodation it was possible to refine the expenditure reallocation model for the following categories of expenditures accommodation food or beverages purchased at restaurants or bars and food or beverages purchased in stores during the trip Accommodation In cases where the traveller used one or multiple accommodation types in one location reported expenditures are allocated at the location the same as in 1994 In cases where the traveller used one accommodation type in multiple locations reported expenditures are redistributed according to the number of nights spent in each location the same as in 1994 44 CTS Wierodata User s Guide Statistics Canada Catalogue 87 M0006GPE Canadian Travel Survey In cases where the traveller went to different locations and used different types of accommodation the realloc
85. vince of origin This is the same as was done in 1994 2 In cases of one accommodation type and multi locations money is allocated according to the number of nights spent in each location In cases of mixed accommodation types and multi locations the amount of money redistributed would vary depending on the type of accommodation and the number of nights spent in each location Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 49 Canadian Travel Survey TABLE 3 Average expenditures per type of accommodation travellers who used only one type of accommodation overnight travel 1996 Accom Food or Food or modation bev bev bought bought in in stores restau during rants or the trip bars per per day day Resort and Lodge 71 52 29 33 11 02 Motel 48 81 26 08 6 79 45 52 Private Cottage 42 29 11 50 10 03 13 03 Home of friends or relatives 11 47 12 84 4 50 Other 35 87 26 51 5 56 24 36 1716 3194 Source Canadian Travel Survey 1994 Data review The final weighted and imputed files are then subject to an analytical review to detect problems at the aggregate level Any anomalies are corrected and the final files are then made available to the end users 50 CTS Wierodata User e Guide Statistics Canada Catalogue 87M0006GPE Canadian Travel Survey a El Weighting procedures for the LFS WEIGHTING Since the Canadian Travel Survey used a sub sample of the
86. with the Beyond 20 20 software and on the microdata file supplementary information included on the December person dataset it is possible to get annual socio demographic information on travellers Statistics Canada Catalogue 87M0006GPE CTS Wierodata User s Guide 59 Canadian Travel Survey and non travellers from this file That information is derived from an additional question included in the December questionnaire The question is as follows DURING THE ELEVEN MONTH PERIOD FROM JANUARY 1 TO NOVEMBER 30 survey year DID YOU TAKE ANY NON BUSINESS TRIPS OF ONE NIGHT OR MORE TO A DESTINATION 1 WITHIN THE PROVINCE 2 TO SOME OTHER PROVINCE 3 TO THE UNITED STATES 4 TO A FOREIGN COUNTRY OTHER THAN THE UNITED STATES This question for which results appear in the variables YRSAMEPR the person took at least one intraprovincial trip YRCANADA interprovincial trip YRUSA trip to the United States and YROTHER trip to a foreign country other than the United States gives users the information determining if a respondent has travelled to specific destinations within the reference year Microdata users have to combine the results from this question with the information collected for the month of December to know about trips taken in December to determine if a respondent travelled during the complete reference year Results for the complete reference year are already combined under these same variables for Beyond 2
87. y can vary greatly from relatively high population density areas to low population density areas resulting in Statistics Canada Catalogue 87M0006GPE CTS Wicradata User s Guide 25 Canadian Travel Survey the formation of strata that reflect these variations The different stratification strategies for rural areas were based not only on concentration of population but also on cost efficiency and interviewer constraints In each province remote settlements are sampled proportional to the number of dwellings in the settlement with no further stratification taking place Dwellings are selected using systematic sampling in each of the places sampled Cluster delineation and selection Households in final strata are not selected directly Instead each stratum is divided into clusters and then a sample of clusters is selected within the stratum Dwellings are then sampled from selected clusters Different methods are used to define the clusters depending on the type of stratum Within each urban stratum in the urban area frame a number of geographically contiguous groups of dwellings or clusters are formed based upon 1991 Census counts These clusters are generally a set of one or more city blocks or block faces The selection of a sample of clusters always 6 or a multiple of 6 clusters from each of these secondary strata represents the first stage of sampling in most urban areas In some other urban areas Census Enumera

Canadian Travel Survey Microdata User's Guide

Contents

Download Pdf Manuals

Related Search

Related Contents