Home

Main Microdata User Guide

Contents

1. was selected in the survey did not have an equal probability of being selected To correct for this unequal probability or chance of being selected we created the survey weight variable In short using the survey weight variable permits the user to make generalizations to the population from which the sample was drawn Re basing the survey weights In some instances users may want to maintain the sample size rather than the population estimate and ensure that adjustments for sampling methods are retained For this reason users need to re base the survey weights Re basing the survey weight can be done as follows MAIN _WT gt MAIN _WT Relative weight sample size 6 7 Suppression of Confidential Information It should be noted that the Public Use Microdata Files PUMF may differ from the survey master files held by the Centre for Behavioural Research and Program Evaluation University of Waterloo These differences usually are the result of actions taken to protect the anonymity of individual survey respondents The most common actions are the suppression of file variables grouping values into wider categories and coding specific values into the not stated category Specifically the following variables have been removed from the PUMF e school board identifier school identifier class identifier stratum identifier postal code age responses from the parent interviews 2006 07 YSS Main Microdata User G
2. 27 Variable SLAST7B1 SLST30A1 SLST30B1 SSHAREA1 SBRNDUA1 SBRNDYC1 to SBRNDYL1 SGETCGA1 SEVRQTA1 SSURQTA1 SHRULSC1 DSUSCEPT Question How old were you when you first smoked every day for at least 7 days in a row On how many of the last 30 days did you smoke one or more cigarettes Thinking back over the last 30 days on the days that you smoked how many cigarettes did you usually smoke each day When you smoke how often do you share a cigarette with others What brand of cigarettes do you usually smoke Why do you smoke the brand of cigarettes that you do Where do you usually get your cigarettes Have you ever tried to quit smoking cigarettes Do you think you would be able to quit smoking cigarettes if you wanted to Do you ever smoke inside your home Susceptible to smoking See derived variables for items contributing to variable Valid Condition s if Respondent Had smoked every day for at least 7 days Had smoked a whole cigarette Had smoked a whole cigarette Had tried smoking Had tried smoking Had a usual brand Had tried smoking Had tried smoking Had smoked in the last 30 days Had tried smoking Had not tried smoking Skip Condition Variable coded 96 or 996 If SLAST7A1 2 NO or 96 Valid skip Have you ever smoked every day for at least 7 days ina row If SWHOLEA1 2 NO or 96 Valid Skip Have y
3. Mal Smoking Survey Main Microdata User Guide www yss uwaterloo ca Table of Contents 1 0 2 0 3 0 4 0 5 0 6 0 7 0 8 0 Introduction rer ienne A etched a AA ietaceeen 1 Backers E aaa A a AE ER EE i 2 Concepts and Definitions viii e a bev sh a a a SS a aaee 4 Survey Method OlO BY iorra arai a eE EEEE E a CE a a EEE TE EAR a EES 5 4 1 Population COVEra tc tt ete Baan 5 4 2 Sample Desi aaa 5 4 3 Sample Selec irte rindi on jocks dt de tdci sede ae 7 Data Collect AA ae 9 51 Questionnaire Desi de E 9 5 2 A Testing arne r ide da etna besten Se eae EAE a E EAEAN EIEN 10 5 3 Recruitment Of Sehol Sisina eien eaaa daa aai 11 5 4 Recruitment of Students einean d i i aaa ii 11 5 57 Dat Collection Protocols iu aici a whieh ia rd 12 Bi6 ASAMPIGSIZe ze NA ce ots icc A OO OT 13 Data POESIA en eke aie ae eee 15 671 Data Capture e a heeled A A eta acia 15 6 2 Editing and Imputation ccoconcccononononnnnonoononcnnnnnnnnononnnnnnnnnnnnn nn nnnnnnnnnnnnn on nrnnnnnnnnnnanones 16 6 3 Creation of Derived Variables eee ceeeceeeeeeeesceceececeeeeeceeeeeaaeeeeaaeceeaeeceaeeeneaaeseeaeeee 19 6 4 Skip Patterns a AA eae aA A eee 27 60 WIS ALINE nennen aa A Boles Ga sees 33 6 6 Use of Survey Weights errena aire i a E a a a i E as 36 6 7 Suppression of Confidential Information cconoccoconnnncnnnononannnnnnnonananononcnncnnnnnnnnonos 37 Data Q ality sica A eae 38 Fede Response RAS ii ta TA E EE Ta 38 72
4. Al aE A EE AEA a E A A EAA E A a ON 39 Guidelines for Tabulation Analysis and Release cccsscccccecscesesseceeeeeeessessaeeeaeeeseeeeesees 39 8 1 Ro nding GUI eae vied Ge ee et 39 8 2 Sample Weighting Guidelines for Tabulation oocccccinononoonnnnnnnnananrncncnnonnnnnnnnnos 40 8 3 Definitions of Types of Estimates Categorical and Quantitative ccccnnnnnnnnns 40 Funding for this project was provided by Health Canada 8 4 Guidelines for Statistical Analysis cocoococononccnonononannnononnnnnnannnnnnnncnnnno nn nnnnnnnnnnnnnnonos 42 8 5 Coefficient of Variation Release Guideline eee eeeeesseceseeeeeseeceeeeeesaeeeeaaeeeneeees 43 Appendix A Variables Common to Modules A B1 B2 in 2006 07 YSS ccccccccccecssssssteeeeeeseees 45 Appendix B Youth Smoking Survey Questions by Survey Y al cccccccccesssssssseeeessesssssaeeeeeeeeens 48 Appendix C Differences in Derived Variables between 2004 05 YSS and 2006 07 YSS 0 54 Funding for this project was provided by Health Canada 1 0 Introduction The Youth Smoking Survey YSS is undertaken with the cooperation support and funding of the Tobacco Control Program Health Canada Dr Steve Manske of the Centre for Behavioural Research and Program Evaluation CBRPE at the University of Waterloo served as Principal Investigator to implement the 2006 07 YSS Drs Steve Brown and Mary Thompson from the Statistics and Actuarial Science Dep
5. Canada 198 160 38 80 8 2006 07 YSS Main Microdata User Guide April 2008 13 Table 5 School Recruitment Outcomes by Province 2006 07 YSS Province NL NS PEI NB QC ON MB SK AB BC Canada School Recruitment Outcome Approached 28 33 29 203 64 86 30 29 42 88 632 Agreed Refused Response rate 183 Table 6 Participating Students by Province and Grade 2006 07 YSS Number of Students Participating by Grade Province Grade Grade Grade Grade Grade Grade Grade Grade Total 5 6 7 8 9 10 11 12 NL 532 515 275 192 191 545 528 487 3265 NS 400 483 337 202 476 919 887 672 4376 PE 470 524 400 436 450 874 877 831 4862 NB 823 1863 1676 1691 3721 3393 3356 2882 19405 Qc 898 1016 2815 2938 1815 1808 1673 0 12963 ON 773 559 658 626 2180 2061 1969 2036 10862 MB 354 451 492 456 794 862 638 494 4541 SK 374 463 393 410 249 224 187 168 2468 AB 498 523 462 404 258 255 246 200 2846 BC 508 623 790 814 429 815 808 628 5415 Canada 5630 7020 8298 8169 10563 11756 11169 8398 71003 2006 07 YSS Main Microdata User Guide April 2008 14 6 0 Data Processing The main output of the Youth Smoking Survey YSS is a microdata file This chapter presents a brief summary of the processing steps involved in producing this file 6 1 Data Capture Student questionnaires were machine scanned using Optical Mark Read OMR technology Procedures detailed several quality control measures to ensure the accuracy of th
6. Has smoked at least 100 cigarettes in his her lifetime and has smoked at least one cigarette during the 30 days preceding the survey but has not smoked every day Formerly smoked Has smoked 100 or more cigarettes in his her lifetime but has not smoked at all during the 30 days preceding the survey Formerly smoked daily Has smoked 100 or more cigarettes in his her lifetime but has not smoked at all during the 30 days preceding the survey and has at some time smoked every day for seven days in a row Formerly smoked occasionally Has smoked 100 or more cigarettes in his her lifetime but has not smoked at all during the 30 days preceding the survey and has never smoked every day for seven days in a row Non Smoker Has smoked fewer than 100 cigarettes in his her lifetime Experimental smoker beginner Has smoked between 1 and 99 cigarettes in his her lifetime and has smoked in the 30 days preceding the survey Past experimenter Has smoked between 1 and 99 cigarettes in his her lifetime but has not smoked in the 30 days preceding the survey Puffer Has smoked less than one whole cigarette in his her lifetime but has tried smoking Never tried Has never tried smoking not even just a puff 2006 07 YSS Main Microdata User Guide April 2008 4 4 0 Survey Methodology The 2006 07 Youth Smoking Survey YSS was administered to collect data from sampled public and private schools in Canada for children in grades 5 to 1
7. Have you ever used or tried heroin If AUCOCNA1 2 NO or 99 Not Stated Have you ever used or tried cocaine If AUSTERA1 2 NO or 99 Not Stated Have you ever used or tried steroids If AUSOLVA1 2 NO or 99 Not Stated Have you ever used or tried this sniffed glue gasoline or other products solvents to get high 2006 07 YSS Main Microdata User Guide April 2008 30 AUMEDSB1 AUPAINB1 AUNATRB1 How old were you when you first used or tried medication like Ritalin NOT for medical purposes How old were you when you first used or tried painkillers to get high and NOT for medical purposes How old were you when you first used or tried any other medications or natural health products to get high and NOT for medical purposes Valid Condition if Respondent Had tried medication like Ritalin NOT for medical purposes Had tried painkillers to get high Had tried other medications or natural health products to get high Skip Patterns for Variables in Module B1 only VARIABLES LISTED AS MODULES B1 ONLY SLAST7A2 to SLAST7H2 DVCIGWK1 DVNDSMK1 DAVCIGD1 All variables appearing only in Module B1 Think back over the last 7 days Fill in the number of times you smoked cigarettes on each of the last 7 days Total number of times cigarettes were smoked in the past 7 days prior to the survey Number of days on which respondent smoked at least one time in
8. 100 cigarettes in his her lifetime SWHOLEA1 Have you ever smoked a whole cigarette 2006 07 YSS Main Microdata User Guide April 2008 21 Derived Variable Response Options for DSUSCEPT Basis for Susceptibility Scale Valid response 1 Yes AND SHUNDOA1 Have you ever smoked 100 or more whole cigarettes in your life Valid response 2 No AND SLST30A1 On how many of the last 30 days did you smoke one or more cigarettes Valid response 1 none Puffer Definition A puffer is a person who has tried smoking but has never smoked a whole cigarette Calculation SPUFFOA1 Have you ever tried cigarette smoking even just a few puffs Valid response 1 Yes AND SWHOLEA1 Have you ever smoked a whole cigarette Valid response 2 No Never Tried Definition A person classified as never tried has never tried a cigarette not even just a few puffs Calculation SPUFFOA1 Have you ever tried cigarette smoking even just a few puffs Valid response 2 No DSUSCEPT 1 No 2 Yes 96 Valid Skip 99 Not Stated SSUSMTA1 Do you think in the 1 Definitely yes future you might try 2 Probably yes smoking cigarettes 3 Probably not 4 Definitely not 96 Valid Skip 99 Not Stated SSUSFOA1 If one of your best 1 Definitely yes friends was to offer 2 Probably yes you a cigarette would 3 Probably not you smoke it 4 Definitely not 99 Not Stated SSUSNYA1 At any time during the 1 Definitely yes nex
9. 24 High 109 8 Low 22 12 QC 54 High 25 5 Low 21 23 ON 54 High 27 15 Low 11 1 MB 24 High 16 2 Low 8 3 SK 24 High 16 2 Low 11 3 AB 36 High 19 9 Low 8 16 BC 36 High 28 36 Canada 324 467 165 Please note that the target number of schools for New Brunswick was 24 but the combined number of participating and not participating schools was much greater than this target The target of 24 schools reported here relates to YSS sample only The number of participating schools and not participating schools for New Brunswick includes both the YSS and the Healthy New Brunswick en sant schools described on pages 2 3 of this report Stratum 2 School Type The second set of strata was created to differentiate between elementary schools and high schools While this may sound simple in reality a variety of grade distributions occur in schools Therefore we established the following procedures If the total enrolment of grades 5 to 8 students was greater than or equal to the total enrolment of students in grades 9 to 12 the school was assigned to the elementary school stratum Similarly 1f the total enrolment of students in grades 9 to 12 was greater than the total enrolment of students in grades 5 to 8 then the school was assigned to the secondary school stratum Table 2 reflects the distribution of schools by school stratum and province 2006 07 YSS Main Microdata User Guide April 2008 6 Table 2 Number of Participating and Non Participat
10. Accessible at http www statcan ca english sdds document 4401_D2_T9_V2_E pdf 2006 07 YSS Main Microdata User Guide April 2008 39 1 Estimates in the main body of a statistical table are to be rounded to the nearest hundred units using the normal rounding technique 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 100 if the last two digits are between 00 and 49 they are changed to 00 and the preceding digit the hundreds digit is left unchanged If the last digits are between 50 and 99 they are changed to 00 and the preceding digit is incremented by 1 2 Marginal sub totals and totals in statistical tables are to be derived from their corresponding un rounded components and then are to be rounded themselves to the nearest 100 units using normal rounding 3 Averages proportions rates and percentages are to be computed from un rounded components 1 e numerators and or denominators and then are to be rounded to one decimal using normal rounding In normal rounding to a single digit if the final 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 increased by 1 4 Sums and differences of aggregates or
11. Module A questionnaire and grades 7 to 12 received either a B1 or B2 Module questionnaire The variables listed as Modules B1 and B2 were only intended for respondents in grades 7 to 12 Skip Patterns for Variables in Modules A B1 and B2 Variable Question Valid Skip Condition Condition s Variable coded 96 or _if Respondent 996 SPUFFOB1 How old were you when Had tried smoking If SPUFFOA1 2 NO you first tried smoking Have you ever tried cigarettes even just a cigarette smoking even just few puffs a few puffs SSUSMTA1 Do you think in the future Had not tried If SPUFFOA1 1 YES you might try smoking smoking Have you ever tried cigarettes cigarette smoking even just a few puffs SWHOLEA1 Have you ever smokeda Had tried smoking If SPUFFOA1 2 NO whole cigarette Have you ever tried cigarette smoking even just a few puffs SWHOLEB1 How old were you when Had smoked a If SWHOLEA1 2 NO or you smoked your first whole cigarette 96 Valid Skip whole cigarette Have you ever smoked a whole cigarette SHUNDOA1 Have you ever smoked Had smoked a If SWHOLEA1 2 NO or 100 or more whole whole cigarette 96 Valid Skip cigarettes in your life Have you ever smoked a whole cigarette SLAST7A1 Have you ever smoked Had tried smoking If SPUFFOA1 2 NO every day for at least 7 days in a row Have you ever tried cigarette smoking even just a few puffs 2006 07 YSS Main Microdata User Guide April 2008
12. The final number of records is 71 003 Qu bec grades Secondaire I IL MI IV and V were converted to grades 7 8 9 10 and 11 respectively The following items required specific editing and or imputation Grade During the processes of determining permission form return rates and consent rates we noted that several students indicated a grade on the survey that was inconsistent with the grades represented in the school If a student indicated a grade that did not match the relevant grades in the school the variable was recoded to the median grade of the class to which the student belonged if the class was known If grade was missing uncodeable or improper for the province then the students grade was found from another source For those students with active permission the primary source was the student permission form This form which included a grade field was completed by the parent or the student and then signed by the parent The secondary source used to determine student grade was the student s class identification number If multiple grades were listed in these fields then the first grade listed was used If neither of the above methods was possible and the student s age was provided then age was used to impute the grade Gender As with a missing grade if the students gender was either missing or uncodeable then gender was found from the student consent form for students in active consent schools The secondary source was
13. cigarette 2006 07 YSS Main Microdata User Guide April 2008 32 6 5 Weighting Survey weights are needed to derive population estimates from the survey sample In a simple random sample every unit in the population has the same probability of being drawn The fraction of the population that is sampled is the sample size divided by population size To calculate the weight of each sampled member one should multiply each member by 1 fraction If the sample size was 100 and the population was 100 000 then the weight of each sampled member would be 1 000 This means that any sampled member s response is taken to represent 1 000 identical responses in the population This is not the case for complex survey designs such as the method used with YSS In complex survey designs sample data must be multiplied by the appropriate weights This survey weight appears on the microdata file and must be used to derive meaningful population estimates from the survey Please refer to the section on using survey weights The development of the survey weights was accomplished in two stages In the first stage a weight W1 was created to account for the school selection within health region and school strata A second weight W2 was calculated to adjust for student non response Finally the weights were calibrated to the provincial gender and grade distribution so that the total of the survey weights by gender grade and province would equal the actual enr
14. cigarettes from a friend or someone else 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 Have you ever smoked a whole cigarette Yes No R Q Where do you usually get your cigarettes R I buy them myself at a store I buy them from a friend or someone else I ask someone to buy them for me etc 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 isan 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 The only example of a quantitative estimate in the 2006 07 YSS is the number of times cigarettes were smoked or the number of whole cigarettes smoked on each of the last seven days The respondents of Module B1 were asked for the number of times cigarettes were smoked and the respondents of Module B2 were asked for the number of whole cigarettes smoked If users want to estimate the average number of whole cigarettes smoked on the days the respondent smoked then the numerator is the total number of whole cigarettes smoked in the last seven days and the denominator
15. if you wanted to Do any of your brothers or sisters smoke cigarettes Have your parents step parents or guardians ever talked to you about not smoking What are the rules about smoking in your home During the past 7 days on how many days did you ride in a car with someone who was smoking cigarettes How many people in your grade from your school do you think smoke cigarettes In the last 12 months how often did you drink alcohol In the last 12 months how often did you have 5 drinks of alcohol or more on one occasion Why do you think people your age start to drink alcohol Mark all that apply In the last 12 months how often did you use marijuana or cannabis Do you think in the future you might try marijuana or cannabis Do you think it would be difficult or easy for you to get marijuana or cannabis if you wanted to use it Why do you think people your age start to use marijuana or cannabis Mark all that apply Which do you think is more harmful to your health smoking cigarettes or marijuana cannabis feel close to people at my school feel am part of my school I am happy to be at my school feel the teachers at my school treat me fairly feel safe in my school Should smoking be allowed around kids at home Should smoking be allowed around kids in cars SSMKERA1 SPUFFOB1 SSUSFOA1 SSURQTA1 SSIBLIA1 SGRDANB1 SHRULSA1 SINCARA1 SESTIMA1 AOFTETA1 A5DRNKC1 A
16. known as the SUPPLEMENTAL dataset that includes all the variables Users of the MAIN dataset will need to use MAIN_WT to perform all analyses Anyone using the SUPPLEMENTAL dataset MUST read the additional documents that have been provided with the second dataset before using the two sets of survey weights see 2006 07 Youth Smoking Survey Guide for Use of Supplemental Data Set Why should survey weights be used There are two reasons why a survey weight variable should be used when performing analyses 1 Total population versus sample size Users may want results based on population figures instead of estimates based on the sample of individuals included in the study For example the YSS survey weight when used will produce results based on a population estimate of 3 264 160 which represents all the students in Canada grades 5 12 instead of 71 003 which is the total number of students who actually completed the survey The latter is known as the sample size of the YSS 2 Adjusting for sampling method The second use of survey weights is to adjust for sampling methods If every member of a population has an equal probability of being selected in a sample each case would carry the same survey weight and the survey weight for all individuals would be 1 But in reality YSS sampling was done in a more complex manner as explained earlier and each individual who 2006 07 YSS Main Microdata User Guide April 2008 36
17. module Total number of times cigarettes were smoked in the past 7 days prior to the survey Total number of whole cigarettes smoked in the past 7 days prior to the survey 2004 05 YSS Derived Variables DVCIGWK Total number of whole cigarettes smoked in the past 7 days prior to the survey 2006 07 YSS Main Microdata User Guide April 2008 56 2006 07 YSS Main Microdata User Guide April 2008
18. ratios are to be derived from their corresponding un rounded components and then are to be rounded themselves to the nearest 100 units or the nearest one decimal using normal rounding 5 Under no circumstances are un rounded estimates to be published or otherwise released by users Un rounded estimates imply greater precision than actually exists 8 2 Sample Weighting Guidelines for Tabulation The sample design used for the Youth Smoking Survey YSS was not self weighting When producing simple estimates including the production of ordinary statistical tables users must apply the proper sampling weight If proper weights are not used the estimates derived from the microdata files cannot be considered to be representative of the survey population and will not correspond to estimates produced by Health Canada 8 3 Definitions of Types of Estimates Categorical and Quantitative Before discussing how the YSS data can be tabulated and analyzed it is useful to describe the two main types of point estimates of population characteristics which can be generated from the microdata file for the YSS 2006 07 YSS Main Microdata User Guide April 2008 40 Categorical Estimates Categorical estimates are estimates of the number or percentage of the surveyed population possessing certain characteristics or falling into some defined category The number of students who ever smoked a whole cigarette or the proportion of smokers who usually buy
19. schools In addition schools were asked to provide a copy of their written smoking policy Participating schools received a customized school smoking policy feedback report Finally the 2006 07 YSS collaborated with a School Smoking Policy survey funded by the Canadian Tobacco Control Research Initiative CTCRI and headed by Dr Chris Lovato University of British Columbia In this survey the YSS sample overlapped completely with the School Smoking Policy sample In addition to the usual YSS procedures school administrators were asked to complete an online survey of their school smoking policy Participating schools also received a customized school smoking policy feedback report 2006 07 YSS Main Microdata User Guide April 2008 3 3 0 Concepts and Definitions Definitions of 1 currently smokes 2 formerly smoked and 3 non smoker are derived based on smoking questions contained in the student questionnaire See section 6 3 Creation of Derived Variables for more detailed information about the derived variables reflecting these definitions Definitions are consistent with those used in the 2004 05 YSS Currently smokes Has smoked at least 100 cigarettes in his her lifetime and has smoked in the 30 days preceding the survey Currently smokes daily Has smoked at least 100 cigarettes in his her lifetime and has smoked at least one cigarette per day for each of the 30 days preceding the survey Currently smokes occasionally
20. the student s name If the name was unclear for gender then gender was left missing Remaining missing data for gender were left as found for the user to decide how to treat these data Age related Variables If age related variables were reported to be greater than the actual age variable then they were given a value of 99 Not Stated If the actual age variable was 99 Not Stated then the age related questions were given a value of 99 Not Stated 2006 07 YSS Main Microdata User Guide April 2008 16 The variable GCANADA 1 How many years have you lived in Canada has several options including 11 or more years Approximately one hundred nine and ten year olds chose this response option We decided to leave these answers as they are since different users may have different ideas of how they will want to treat these variables Question 29 B1 module and Question 29 B2 module These questions ask how many times cigarettes were smoked B1 module or how many whole cigarettes were smoked B2 module on each of the last 7 days The range that was allowed for each day was 0 36 All responses between 37 and 90 have been set to 99 Not Stated Valid Skips Not Asked and Not Stated responses were set to 96 9996 and 99 as in other variables Module The variable MODULE was created to denote the appropriate module The following lists the various modules and code assigned to each module Questionnaire Module Code Questio
21. would be the number of days whole cigarettes were smoked in the last seven days The average number of times cigarettes were smoked on the days the respondent smoked can be obtained in a similar manner Tabulation of Categorical Estimates Estimates of the number of people with a certain characteristic can be obtained from the microdata file by summing the final weights of all records possessing the characteristic s of A A interest Proportions and ratios of the form X Y are obtained by a summing the final weights of records having the characteristic of interest for the numerator X 2006 07 YSS Main Microdata User Guide April 2008 41 b summing the final weights of records having the characteristic of interest for the denominator Y then c dividing estimate a by estimate b X Y Tabulation of Quantitative Estimates Estimates of totals can be obtained from the microdata file 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 For example to obtain an estimate of the total number of whole cigarettes smoked in the past seven days prior to the survey by students in grade 9 Secondaire III in Qu bec multiply the value reported in the derived variable DVCIGWK2 number of whole cigarettes smoked in the past seven days prior to the survey by the final weight for the record then sum this value over all records with DVCIGWK
22. 027 3388 5415 63 8 Canada 148710 32431 58358 90789 61 1 Based on completed questionnaires numerator and eligible students denominator These numbers include all students who filled out the YSS surveys as well as those that completed the surveys for the Healthy New Brunswick en sant survey The full NB sample rather than just students who completed YSS modules was included in order to calculate student response rates 2006 07 YSS Main Microdata User Guide April 2008 38 7 2 Survey Errors The estimates derived from this survey are based on a sample of schools Somewhat different estimates might be obtained if a complete census had been taken using the same questionnaire data collection staff and processing methods 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 Administrators may misunderstand instructions respondents may make errors in answering questions the answers may be incorrectly entered on the questionnaire 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 erro
23. 07 YSS Main Microdata User Guide April 2008 54 2006 07 YSS Derived Variables Computation Rationale DAVCIGD1 B1 module DAVCIGD2 B2 module DVNDSMK1 B1 module DVNDSMK2 B2 module true 3 Mostly true 4 True Scores were summed and averaged across the questions that were answered resulting in an overall score for DVSELF min 0 max 12 Factor analyses showed that use of three variables rather than five captured variation in responses sufficiently Average number of times cigarettes were smoked on the days that the respondent smoked Average number of whole cigarettes smoked on the days that the respondent smoked Number of days on which respondent smoked at least one time in the week prior to the survey Number of days on which respondent smoked at least one whole cigarette in the week prior to the 2004 05 YSS Derived Variables DVAVCIGD DVNDSMK Computation 3 Mostly True 4 True Scores were summed and averaged across the questions that were answered resulting in an overall score for DVSELF min 0 max 20 Average number of whole cigarettes were smoked on the days that the respondent smoked Number of days on which respondent smoked at least one whole cigarette in the week prior to the survey 2006 07 YSS Main Microdata User Guide April 2008 55 2006 07 YSS Derived Variables DVCIGWK1 B1 module DVCIGWK2 B2
24. 1 1 Are you a girl or a boy SEX 3 3 3 Are you an Aboriginal person GABORGA1 4 4 4 What language do you speak most often at GLANGUA1 5 5 5 home How many years have you lived in Canada GCANADA1 6 6 6 On average how many hours a day do you PSCRENA2 7 7 7 watch TV or videos How often do you read for fun not for PRDAVGA1 8 8 8 school About how much money do you usually get GMONEYA1 9 10 10 each week to spend on yourself or to save Remember to include all money from allowances and jobs like babysitting delivering papers In general like the way am OHOWFLA1 11 12 12 When do something do it well OHOWFLB1 12 13 13 like the way look OHOWFLC1 13 14 14 Are you a smoker SSMKERA1 14 15 15 Have you ever tried cigarette smoking even SPUFFOA1 15 16 16 just a few puffs How old were you when you first tried SPUFFOB1 16 17 17 smoking cigarettes even just a few puffs Do you think in the future you might try SSUSMTA1 17 18 18 smoking cigarettes If one of your best friends was to offer you a SSUSFOA1 18 19 19 cigarette would you smoke it At any time during the next year do you think SSUSNYA1 19 20 20 you will smoke a cigarette Have you ever smoked a whole cigarette SWHOLEA1 21 22 21 How old were you when you smoked your first SWHOLEB1 22 23 22 whole cigarette Have you ever smoked 100 or more whole SHUNDOA1 23 24 23 cigarettes in your life Have you ever smoked every day for at least SLAST7A1 24 25 24 7 days in a row How
25. 2 Primaire 5 6 and Secondaire I to V in Qu bec 4 1 Population Coverage All 10 provinces participated in this study Sampling frames for each province began with a list of all schools in each of the provinces This information was gathered from the Ministry of Education of each respective province Each provincial sampling frame consisted of a range of information about each eligible school including the school board name alternately called school divisions and school districts city address and school enrolment numbers by grade The target population for the 2006 07 YSS consisted of all young Canadian residents attending private public and Catholic schools enrolled in grades 5 to 12 inclusively Those residing in the Yukon Nunavut and Northwest Territories and those living in institutions or on First Nations reserves were not included in the target population Young persons who were attending special schools e g schools for visually impaired and hearing impaired individuals or who were attending schools located on military bases were also excluded from the target population 4 2 Sample Design The sampling of schools for the 2006 07 YSS was based on a stratified multistage design Within each province stratification was based on two classifications 1 health region smoking rate above or below median and 2 type of school elementary or secondary Stratum 1 Health Region The school s six digit postal code was used
26. 2 lt 996 Please note that for this particular example we must use SUPP_WT for the final weight since this question only appears in Module B2 8 4 Guidelines for Statistical Analysis Use of Weights for Producing Simple Estimates The 2006 07 YSS is based upon a complex sampling design with stratification two stages of selection and unequal probabilities of selection of respondents The calculation of more precise variance estimates requires detailed knowledge of the design of the survey Such details cannot be given in this microdata file since confidentiality must be respected However variances that take account for the sample design can be calculated from the bootstrap weights which are provided as a separate data file Health Canada employed STATA for all analyses of the 2006 07 YSS All analyses were conducted using Stata 9 The surveyset commands were used to account for the complex survey design and variance estimates were derived using balanced repeated replication BRR with Fay s method This procedure creates reliable estimates of the variance for both simple estimates such as estimates of totals proportions and ratios and more complex analyses such as linear or logistic regression Another option is to use the Bootvar program available in both SAS and SPSS formats It is made up of macros that compute variances for totals differences between ratios and for linear and logistic regression The bootstrap program for SAS can be
27. 6 Valid Skip DVTY2ST 1 Current Daily Smoker 2 Current Occasional Smoker 3 Former Daily Smoker 4 Former Occasional Smoker 5 Experimental Smoker Beginner 6 Past Experimental Smoker 7 Puffer 8 Never Tried Current Daily Definition A current daily smoker is a person who reports Smoker currently smoking cigarettes every day Calculation SHUNDOA1 Have you ever smoked 100 or more whole cigarettes in your life Valid response 1 Yes AND SLST30A1 On how many of the last 30 days did you smoke one or more cigarettes Valid response 8 30 days every day Current Definition A current occasional smoker is a person who Occasional currently smokes cigarettes but not every day Smoker Calculation SHUNDOA1 Have you ever smoked 100 or more whole cigarettes in your life Valid response 1 Yes AND SLST30A1 On how many of the last 30 days did you smoke one or more cigarettes Valid responses 2 1 day 2 to 3 days 4 to 5 days 6 to 10 days 6 11 to 20 days 7 21 to 29 days Former Daily Definition A former daily smoker is a person who smoked at Smoker least 100 cigarettes in his her lifetime and smoked at least seven days ina row but did not smoke in the last 30 days Calculation SHUNDOA1 Have you ever smoked 100 or more whole cigarettes in your life Valid response 1 Yes AND 2006 07 YSS Main Microdata User Guide April 2008 20 Former Definition Occasional Smoker Calculation E
28. 7E2 SLAST7F2 Responses for SLAST7G2 and SLAST7H2 excluding days with a missing or zero response DVNDSMK1 Notes e Zero has been treated as a valid response e Ifall days have missing data then DVNDSMK1 999 2006 07 YSS Main Microdata User Guide April 2008 24 Derived Variable DAVCIGD1 Definition i Average number of times cigarettes were smoked on the days that the respondent smoked Calculation of DVCIGWK1 Responses for DVNDSMK1 DAVCIGDI Notes e If DVCIGWK1 and DVNDSMK1 were both zero responses then DAVCIGD1 0 e If either DVCIGWK1 or DVNDSMK1 were missing then DAVCIGD1 99 The following five supplemental derived variables use the following questions from the B2 module Question Variable Name Response Options Think back over the last 7 days Find yesterday on the wheel and fill in the number of whole cigarettes you smoked Then follow the wheel backwards and fill in the number of whole cigarettes you smoked on each of the last 7 days a Sunday SLAST7B3 0 0 whole cigarettes b Monday SLAST7C3 smoked c Tuesday SLAST7D3 1 36 whole cigarettes d Wednesday SLAST7E3 smoked e Thursday SLAST7F3 96 Valid Skip f Friday SLAST7G3 9996 Not Asked g Saturday SLAST7H3 99 Not Stated Coverage Respondents of the B2 module survey where SWHOLEA1 1 Whole Cigarette Derived Variable DVAMTSMK Definition The average number of whole cigarettes smoked per day in the past week as an integer value C
29. DSMk2 were both zero responses then DAVCIGD2 0 e f either DVCIGWK2 or DVNDSMk2 were missing then DAVCIGD2 99 DVSMKPTN Smoking pattern in the last 7 days Calculated based on these variables SLAST7B3 SLAST7C3 SLAST7D3 SLAST7E3 SLAST7F3 SLAST7G3 SLAST7H3 1 Smoked every day 2 Smoked week days only 3 Smoked weekend days only 4 Did not smoke in the last 7 days 5 Other pattern 99 Not stated 2006 07 YSS Main Microdata User Guide April 2008 26 6 4 Skip Patterns The youth questionnaire was intentionally designed with no respondent use skip patterns to avoid the identification of smokers by rate of survey completion during the classroom session Thus all smoking behaviour items included a response option such as Z do not smoke However due to the logical flow of the questions a number of questions are extraneous based on the answer to a previous question In these cases a skip pattern has been imposed onto the data set If a question could have been skipped if this were allowable within the structure of the questionnaire it was coded as 96 or 996 or 9996 The following explains each question that has a 96 or a 996 code and the logical reasoning for coding the question in that way The code 9996 has only been used to identify those individuals who have not completed either module B1 or B2 variables Note that the module distribution corresponds to grade for example grades 5 to 6 received a
30. N All variables appearing only in Module B2 Think back over the last 7 days Fill in the number of whole cigarettes you smoked on each of the last 7 days The average number of whole cigarettes smoked per day in the past week Total number of whole cigarettes smoked in the past 7 days prior to the survey Number of days on which respondent smoked at least one whole cigarette in the week prior to the survey Average number of whole cigarettes smoked on the days that the respondent smoked Smoking pattern in the last 7 days Valid Condition if Respondent Completed Module B2 Had smoked a whole cigarette Had smoked a whole cigarette Had smoked a whole cigarette Had smoked a whole cigarette Had smoked a whole cigarette Had smoked a whole cigarette Skip Condition Variable coded 96 or 996 or 9996 If MODULE 1 2 3 or 4 MODULE A ENGLISH MODULE A FRENCH MODULE B1 ENGLISH or MODULE B1 FRENCH If SWHOLEA1 2 NO or 96 Valid Skip Have you ever smoked a whole cigarette If SWHOLEA1 2 NO or 96 Valid Skip Have you ever smoked a whole cigarette If SWHOLEA1 2 NO or 96 Valid Skip Have you ever smoked a whole cigarette If SWHOLEA1 2 NO or 96 Valid Skip Have you ever smoked a whole cigarette If SWHOLEA1 2 NO or 96 Valid Skip Have you ever smoked a whole cigarette If SWHOLEA1 2 NO or 96 Valid Skip Have you ever smoked a whole
31. RDAVGA1 OHOWFLA1 OHOWFLB1 OHOWFLC1 OSKLVGA1 AEVRETA1 AEVRETB1 ASDRNKA1 ASDRNKB1 AEVRMJA1 AEVRMJB1 AUAMPHA1 AUMDMAA1 AUHALUA1 AUDACSA1 The wording for this particular item was slightly different in 2006 Respondents of Module B1 were asked to give the number of times they smoked cigarettes in the last 7 days and respondents of Module B2 were asked to give the number of whole cigarettes they smoked in the last 7 days 2006 07 YSS Main Microdata User Guide April 2008 49 Question 2006 07 Variable name E Heroin smack junk crank AUHEROA1 F Cocaine crack blow snow AUCOCNA1 G Steroids testosterone growth hormones Dianbol juice roids AUSTERA1 17 Mark the circle if you have ever used or tried any of the following Then mark your age when you first used or tried it A Sniffed glue gasoline or other products solvents to get high AUSOLVA1 B Used or tried medication like Ritalin NOT for medical purposes AUMEDSA1 C Used or tried painkillers Talwin Oxycontin to get high and NOT AUPAINA1 for medical purposes D Used or tried any other medications or natural health products to AUNATRA1 get high and NOT for medical purposes 18 Do people have to smoke for many years before it will hurt their health SOPINOA1 19 Is there any danger to your health from an occasional cigarette SOPINOB1 20 Can smoking help people when they are bored SOPINOC1 21 Does smoking help people rela
32. Telephone 519 885 1211 Ext 36632 Telephone 613 957 0697 Fax 519 746 2510 Fax 613 954 2292 E mail r4ahmed uwaterloo ca E mail Judy_SniderOhcOhc sc gc ca 2006 07 YSS Main Microdata User Guide April 2008 1 PLEASE BECOME FAMILIAR WITH THE CONTENTS OF THIS DOCUMENT BEFORE PUBLISHING OR OTHERWISE RELEASING ANY ESTIMATES DERIVED FROM THE MICRODATA FILE OF THE 2006 07 YOUTH SMOKING SURVEY ESPECIALLY WHEN USING THE SURVEY WEIGHTS 2 0 Background The Youth Smoking Survey YSS is a classroom based survey of a representative sample of schools in the ten Canadian provinces When first administered in 1994 it was the largest and most comprehensive survey on youth smoking behaviour since 1979 The YSS was repeated in 2002 and 2004 in order to track changes in the attitudes and behaviour of Canadian children and adolescents with respect to tobacco Previously YSS was only administered to students in grades 5 through 9 In the 2006 07 YSS the survey was extended to include all secondary students in a province 1 e grades 5 to 12 in most provinces and in Quebec Primaire 5 6 and Secondaire I to V The 2006 07 YSS was coordinated by Centre for Behavioural Research and Program Evaluation CBRPE and the SHAPES team School Health Action Planning and Evaluation System at the University of Waterloo Data were collected during the fall winter and spring of the 2006 07 school year The main objective of the YSS is to prov
33. YALSTA1 to AYALSTN1 AOFTMJA1 AMIGHTA1 AHWHRDA1 AYMJSTA1 to AYMJSTL1 AMRHRMA1 OCONCTA1 OCONCTB1 OCONCTC1 OCONCTD1 OCONCTE1 SOPINOL1 SOPINOM1 2006 07 YSS Main Microdata User Guide April 2008 51 Table B4 Questions in the 2006 07 Survey 44 Items Question 1 Inthe last 12 months how often did you smoke 2 When you smoke how often do you share a cigarette with others 3 Ina typical week how often do you see cigarettes advertised or promoted in stores near your school 4 How many of the stores that you visit near your school sell cigarettes 5 Do any of your parents step parents or guardians smoke cigarettes 6 Inthe last 12 months have you taken part in any other anti smoking activities or events either at school or in the community Mark all that apply 7 Inthe last 30 days where did you buy little cigars cigarillos plain or flavoured Mark all that apply 8 How many students at this school smoke where they are not allowed to 9 You can be fined for smoking on school property 10 often see students smoking near this school 11 This school has a clear set of rules about smoking for students to follow 12 If students are caught breaking the smoking rules at this school they get into trouble 13 How many years have you lived in Canada 14 Including graduated licenses do you currently have a valid driver s license 15 In a typical week how often do you visit retail
34. a User Guide April 2008 23 Supplemental Data Set Derived Variables The following three supplemental derived variables use the following questions from the B1 module Question Variable Name Response Options Think back over the last 7 days Find yesterday on the wheel and fill in the number of times you smoked cigarettes Then follow the wheel backwards and fill in the number of times you smoked cigarettes on each of the last 7 days a Sunday SLAST7B2 0 0 times cigarettes were b Monday SLAST7C2 smoked c Tuesday SLAST7D2 1 36 times cigarettes were d Wednesday SLAST7E2 smoked e Thursday SLAST7F2 96 Valid Skip f Friday SLAST7G2 9996 Not Asked g Saturday SLAST7H2 99 Not Stated Coverage Respondents of the B1 module survey where SPUFFOA1 1 Puffer Derived Variable DVCIGWK1 Definition Total number of times cigarettes were smoked in the 7 days prior to the survey Calculation of SLAST7B2 SLAST7C2 SLAST7D2 SLAST7E2 SLAST7F2 Responses for SLAST7G2 SLAST7H2 DVCIGWK1 Notes e Not necessary for all component variables to have valid responses for derived variable to have valid response e Zero value on a component variable has been treated as a valid response e Ifall days have missing data then DVCIGWK1 999 Derived Variable DVNDSMK1 Definition Number of days on which respondent smoked at least 1 time in the week prior to the survey Calculation of A count of SLAST7B2 SLAST7C2 SLAST7D2 SLAST
35. alculation of SLAST7B3 SLAST7C3 SLAST7D3 SLAST7E3 SLAST7F3 SLAST7G3 SLAST7H3 Responses for 7 DVAMTSMK Notes e All responses had to have valid responses for valid data e If all responses have 99 or if any of the days are missing then DVAMTSMK 99 2006 07 YSS Main Microdata User Guide April 2008 25 Derived Variable _ Definition Calculation of Responses for DVCIGWK2 Notes Derived Variable Definition Calculation of Responses for DVNDSMK2 Notes Derived Variable _ Definition Calculation of Responses for DAVCIGD2 Notes Derived Variable _ Definition Calculation of Responses for DVSMKPTN DVCIGWK2 Total number of whole cigarettes smoked in the 7 days prior to the survey SLAST7B3 SLAST7C3 SLAST7D3 SLAST7E3 SLAST7F3 SLAST7G3 SLAST7H3 e Not necessary for all to have valid responses e Zero value has been treated as a valid response e If all days have missing data then DVCIGWK2 999 DVNDSMK2 Number of days on which respondent smoked at least 1 whole cigarette in the week prior to the survey A count of SLAST7B3 SLAST7C3 SLAST7D3 SLAST7E3 SLAST7F3 SLAST7G3 and SLAST7H3 excluding days with a missing or zero response e Zero has been treated as a zero response e Ifall days have missing data then DVNDSMk2 99 DAVCIGD2 Average number of whole cigarettes smoked on the days that the respondent smoked DVCIGWK2 DVNDSMK2 e IfDVCIGWK2 and DVN
36. artment at the University of Waterloo acted as co principal investigators Two groups at the University of Waterloo coordinated the 2006 07 YSS the Centre for Behavioural Research and Program Evaluation CBRPE and the SHAPES team School Health Action Planning and Evaluation System The investigators and staff were assisted by a consortium of university and non governmental organizations across the country Dr Shirley Solberg Memorial University on sabbatical Dr Alice Gaudine Memorial University Ms Meg McCallum Canadian Cancer Society Nova Scotia Division Ms Donna Murnaghan University of Prince Edward Island Dr William Morrison University of New Brunswick Dr Jennifer O Loughlin Universit de Montr al Ms Louise Guyon Institut national de sant publique du Qu bec Dr Jane Griffith Cancer Care Manitoba Ms June Blau Saskatchewan Coalition for Tobacco Reduction Dr Cameron Wild University of Alberta Dr Chris Lovato University of British Columbia This manual has been produced to facilitate the manipulation of the Public Use Microdata File of the survey results Please direct any questions about the data set or its use to University of Waterloo Health Canada Rashid Ahmed Judy Snider Senior Data Analyst Office of Research Surveillance and Evaluation University of Waterloo Tobacco Control Programme 200 University Ave W Rm LHN 2707 123 Slater Street Waterloo Ontario N2L 3G1 Ottawa Ontario K1A OK9
37. bles appearing only in Modules A and B2 In the last 12 months how often did you smoke How often do you smoke tobacco in each of the following places How often do you smoke tobacco at the following times How often do you smoke tobacco with the following people Completed Module Aor B1 Valid Condition if Respondent Completed Module A or B2 Had tried smoking Had tried smoking Had tried smoking Had tried smoking B2 ENGLISH MODULE B2 FRENCH Skip Condition Variable coded 96 or 996 or 9996 If MODULE 3 or 4 MODULE B1 ENGLISH MODULE B1 FRENCH If SPUFFOA1 2 NO Have you ever tried cigarette smoking even just a few puffs If SPUFFOA1 2 NO Have you ever tried cigarette smoking even just a few puffs If SPUFFOA1 2 NO Have you ever tried cigarette smoking even just a few puffs If SPUFFOA1 2 NO Have you ever tried cigarette smoking even just a few puffs Skip Patterns for Variables in Modules B1 and B2 VARIABLES LISTED AS MODULES B1 AND B2 AEVRETB1 AOFTETA1 A5DRNKA1 All variables appearing only in Modules B1 and B2 How old were you when you first had a drink of alcohol that is more than a sip In the last 12 months how often did you drink alcohol Have you ever had 5 drinks or more of alcohol on one occasion Valid Condition if Respondent Completed Module B1 or B2 Had tried alcohol Had tried alcohol Had tried alcohol Skip C
38. e scan data First staff visually scanned all questionnaires and darkened marks that were too light or incomplete e g check marks instead of filled in circles to ensure that they would be recognized by the scanner At the same time they separated the perforated questionnaire booklets and oriented them in preparation for the OMR scan Second staff inserted standard surveys to ensure that the calibration of the scanner remained constant Visual scanning aspects of survey processing ensure that the data on the surveys are correctly recorded by the electronic scanner In the course of visually scanning a survey a human scanner could correct a survey in a variety of ways including darkening marks that needed to be read by the electronic scanner but might have originally been drawn too lightly erasing marks from answers where the respondents changed their mind but did not sufficiently erase the original response erasing accidental wayward marks that were not meant to indicate answers e g graffiti or doodles erasing marks made in any places reserved for office use only and correcting answers on two part questions where two different responses were given for the same question i e for the number of times cigarettes were smoked number of whole cigarettes smoked in the past 7 days All bundles of questionnaires were scanned twice and discrepancies were investigated Staff were trained to make decisions according to strict crit
39. eased However those of Marginal or Unacceptable quality level must be accompanied by a statement of warning to caution subsequent users 2006 07 YSS Main Microdata User Guide April 2008 43 Table 9 Quality Level Guidelines Quality Level of Estimate Acceptable Marginal Unacceptable Guidelines Estimates have a sample size of 30 or more and low coefficients of variation in the range of 0 0 to 16 5 No warning is required Estimates have a sample size of 30 or more and high coefficients of variation in the range of 16 6 to 33 3 Estimates should be flagged with the letter M or some similar identifier They should be accompanied by a warning to caution subsequent users about the high levels of error associated with the estimates Estimates have a sample size of less than 30 or very high coefficients of variation in excess of 33 3 It is not recommended to release estimates of unacceptable quality Such estimates should be replaced with the letter U or some similar identifier and the following statement Unreleasable due to low sample size 2006 07 YSS Main Microdata User Guide April 2008 44 Appendix A Variables Common to Modules A B1 B2 in 2006 07 YSS Table A1 Questions and Variable Names Common to Modules A B1 and B2 MAIN Weight to be Applied when Estimating Population Totals 2006 07 YSS MAIN Questions Variable Name Question A B1 B2 What grade are you in GRADE 1
40. eria For example they had to distinguish between true uncodeable responses not to be corrected e g where the respondent chose two answers and those which were machine errors that were to be corrected e g where the respondent erased one mark and chose another answer but the scanner picked up the erased mark as well On average between 10 and 15 of all surveys had one or more responses altered due to the visual scanning process Due to these screening procedures all invalid responses were corrected prior to data capture by the scanner Logbooks and a quality control record were kept to track the number of corrections made and to monitor the progress of merging files to create a school level file 2006 07 YSS Main Microdata User Guide April 2008 15 6 2 Editing and Imputation The following standard codes were used in the microdata file Valid skip 96 and 996 Not stated 99 and 999 Not asked 9996 Prior to data cleaning the 2006 07 YSS student dataset contained 71 034 records Questionnaires were scanned twice and duplicate files were removed Two surveys that indicated students were not in grades 5 12 were removed from the data set resulting in 71 032 eligible records Twenty grade 6 students were removed from the dataset because they were listed as having passive consent An additional 9 students were removed from the dataset where the student was the only participating individual from a certain grade in a certain school
41. ets Six thousand 6 000 such bootstrap samples were computed The average of sets of twelve bootstrap weights were used to create a set of 500 averaged bootstrap weights The formula for the weight adjustment is obtained as follows Let w be the smoothed calibrated main weight for student j in school i gt Rao J N K amp Wu C F J 1988 Resampling inference with complex survey data Journal of the American Statistical Association 83 231 241 2006 07 YSS Main Microdata User Guide April 2008 35 1 where N is the number of schools in a given stratum and n i Let A n l1 is the number of schools actually selected in that stratum The bootstrap weight w would then be given by w l 4 number of times school i has been resampled 6 6 Use of Survey Weights Cautions The survey weight w just described above is considered the MAIN_WT and is relevant to those variables that appeared in all three survey modules A B1 and B2 For those variables that appeared only in certain survey modules B1 or B2 a second survey weight SUPP_WT variable was created Due to this distinction between the two survey weights the dataset was divided in two parts The first set of data is known as the MAIN dataset and includes only those variables that have been asked in all three modules A B1 and B2 The second set of data contains two sets of weights MAIN_WT and SUPP_WT and is
42. found at http data library ubc ca datalib survey statscan nphs synthetic cycle 1 bootstrap B TDOCENG pdf and bootstrap program for SPSS can be found at http prod library utoronto ca 8090 datalib codebooks cstdli nphs 2005_dummy bootstrap SPSS Pgm 5 StataCorp 2005 Stata Statistical Software Release 9 College Station TX StataCorp LP Judkins D 1990 Fay s Method for Variance Estimation Journal of Official Statistics 6 3 223 239 2006 07 YSS Main Microdata User Guide April 2008 42 along with the documents explaining how to modify and use the program to meet users needs When producing simple estimates including the production of ordinary statistical tables users must apply the proper sampling weight There is a method that makes using standard packages of analysis techniques such as linear regression logistic regression and analysis of variance more reasonable This is done by rescaling the weights on the records so that the average weight is one As a result of using this weight the results produced by standard packages will take into account the unequal probabilities of selection and thus be more meaningful even if they do not take into account the stratification and clustering of the design of the sample A rescaled weight can be calculated by dividing the original weight by the average of the original weights for the sampled units contributing to the estimator that one is interested in The method de
43. his instrument contained 66 questions that were deemed relevant to students in these grade levels Module A did not include drug and alcohol questions e Module B1 was administered to students in grades 7 through 12 This instrument contained 76 questions including some new questions some questions from Module A and drug and alcohol questions e Module B2 was administered to students in grades 7 through 12 This instrument contained 84 questions including some new questions some questions from Module A and drug and alcohol questions 2006 07 YSS Main Microdata User Guide April 2008 9 Procedures were common in all provinces except New Brunswick see NB specific procedures below All grades 5 and 6 students completed Module A Grades 7 12 students in Qu bec Secondaire I V completed either the B1 or B2 module not both Within a class 50 of students were randomly selected to receive B1 and the other 50 received B2 Surveys were collated i e alternating B1 and B2 modules in advance and shipped to each provincial site In New Brunswick YSS collaborated with the Health and Education Research Group Dr Bill Morrison and the Departments of Wellness Culture and Sport and of Education on a survey supporting the Healthy New Brunswick en sant project This initiative collected data on smoking YSS healthy eating HE physical activity PA and mental fitness MF Thus in New Brunswick grades 5 and 6 students completed one of th
44. ide benchmark data on national prevalence rates for students in grades 5 through 12 In addition it provides a unique opportunity to advance our knowledge of the psychosocial correlates of smoking behaviour including initiation and cessation Further it can assist in exposing individual differences in the influence of tobacco marketing purchasing controls and other policy initiatives YSS offers a detailed snapshot of purchasing behaviour knowledge and awareness of warning labels and information about the effect of continued tobacco marketing This information is critical to assessing the need for increased legislative controls on tobacco and bolstering public support for these policy options Without this type of monitoring the effectiveness of our prevention efforts cannot be gauged Schools that participated in the YSS received a school specific feedback report and executive summary within 8 to 10 weeks of data collection This report provided valuable customized information to the schools including the school smoking rate plus other behavioural and environmental information Throughout the feedback report we compared 2006 07 school results to provincial and national estimates based on the 2004 05 YSS Another unique aspect of the 2006 07 YSS was its collaboration with three other surveys the Healthy New Brunswick en sant project Project Impact and the Canadian School Smoking Policy Survey 2006 07 YSS Main Microdata User Guide A
45. ility the basis of the questionnaire was the 2002 and 2004 05 YSS with most items unchanged to allow for comparisons with the 2004 05 2002 and 1994 data e Responsiveness to meet the needs of users of the data provincial collaborators and those responsible for federal and provincial tobacco strategies were given an opportunity to contribute topics items for consideration by a content team e Relevancy to ensure value added for participating schools items were added significance to schools in order to enhance school level feedback reports and e Feasibility to meet the criterion of being able to complete the survey in one class period there was a key consideration to restrict length The 2006 07 YSS student questionnaires were adapted from the 2002 and 2004 05 YSS surveys A Content Committee had participation from Research Surveillance and Evaluation in the Tobacco Control Programme of Health Canada interested provincial collaborators and persons with responsibility for evaluation of provincial tobacco control strategies The questionnaire was finalized through a series of reviews and meetings Appendix B provides information about questions that have been asked in all the survey years 1994 2002 2004 2006 and those that have been asked in only certain survey years e g 2004 and 2006 In the 2006 07 YSS the student survey data were collected using three instruments e Module A was administered to students in grades 5 and 6 T
46. ing Schools by School Stratum and Province 2006 07 YSS Provi Target School of Participating of Schools Not rovince ete A Schools Stratum Schools Participating Elementary 18 1 ME e Secondary 8 1 Elementary 13 6 NS Secondary 8 6 Elementary 18 3 PEI Secondary 7 1 Elementary 125 13 NB1 24 Secondary 58 7 Elementary 36 11 QC 24 Secondary 11 6 Elementary 32 24 OM Secondary 16 14 Elementary 19 1 MB Secondary 8 2 Elementary 16 3 ak Secondary 8 2 Elementary 18 7 AB 36 Secondary 12 5 Elementary 29 31 po Secondary 7 21 Canada 324 467 165 The target of 24 schools reported here relates to YSS sample only The number of participating schools and refused schools for New Brunswick includes both the YSS and the Healthy New Brunswick en sant schools 4 3 Sample Selection Thus within each provincial sampling frame four school strata were created by crossing the health region strata low and high and the two grade level strata elementary and secondary Within each stratum in each province schools were randomly selected with probabilities proportional to the total enrolment in their boards In an effort to reach our targets we over sampled schools in each province based on the provincial school recruitment rate from the 2004 05 YSS to accommodate school refusals in 2006 07 Based on the 2004 05 recruitment rate in British Columbia BC we raised our target by an additional 32 schools however BC c
47. itment package and phone calls An invitation letter a project summary sample questionnaires sample consent letters and forms and a template feedback report were included in the standard recruitment package for both boards and schools In addition many boards and schools had formal application forms and procedures Educators also had access to materials through the web www yss uwaterloo ca 5 4 Recruitment of Students Active Permission Schools with elementary grades e g grades 5 6 and in some cases high schools based on school or board request obtained signed parental permission for students to participate in the survey i e active parental permission For active permission an information letter and permission form were sent home with students Parent information letters provided details about the project contact information for project staff and referral to the website for further details including copies of the questionnaires Parents were given a minimum of two weeks to return permission forms To improve permission form return rates some schools chose to resend permission materials conduct phone follow up to parents and or provide verbal or written reminders to students Only those students whose parents indicated yes to participation on the student permission form were able to participate in the survey Students also had the opportunity to decline participation on the day of data collection Active Information Passi
48. l property How often do you smoke tobacco at concerts dances clubs How often do you smoke tobacco at restaurants coffee shops How often do you smoke tobacco at parties How often do you smoke tobacco at your friend s house How often do you smoke tobacco in a vehicle How often do you smoke tobacco before school How often do you smoke tobacco during the school day How often do you smoke tobacco after school How often do you smoke tobacco in the evening How often do you smoke tobacco on weekends How often do you smoke tobacco by yourself How often do you smoke tobacco with your parents How often do you smoke tobacco with other family members How often do you smoke tobacco with friends How important is getting good grades to you How important is making friends to you How important is participating in school activities outside of class How important is getting to class on time to you How important is learning new things to you How important is expressing my opinion in class to you How important is getting involved in the student council or other similar groups to you Do people who smoke become more popular _Variable Name SPLACEC1 SPLACED1 SPLACEE1 SPLACEF1 SPLACEG1 SPLACEH1 SPLACEI1 STIMESA1 STIMESB1 STIMESC1 STIMESD1 STIMESE1 SPEOPLA1 SPEOPLB1 SPEOPLC1 SPEOPLD1 OIMPORA1 OIMPORB1 OIMPORC1 OIMPORD1 OIMPORE1 OIMPORF1 OIMPORG1 SOPINOI1 2006 07 YSS Main Microdata User Guide Ap
49. n 2006 07 Variable _Name SHUNDOA1 SEVRQTA1 SPUFFOA1 SLAST7A1 SLAST7B1 Survey Year Table B1 Questions in All Four Surveys 1994 2002 2004 2006 29 Items Question 1 Have you ever smoked 100 or more whole cigarettes in your life 2 Have you ever tried to quit smoking cigarettes 3 Have you ever tried cigarette smoking even just a few puffs 4 Have you ever smoked every day for at least 7 days in a row 5 How old were you when you first smoked every day for at least 7 days in SSUSNYA1 SSUSMTA1 SBRNDYC1 to SBRNDYL1 SBRNDUA1 SHWHRDA1 SGETCGA1 SLST30C1 SLST30E1 SSRULSA1 SSRULSC1 SSRULSB1 SHRULSB1 SHRULSC1 S5FRNDA1 SSTRTYA1 to SSTRTYM1 SHELTHA1 to SHELTHE1 SLECSMA1 SEVTRYA1 to SEVTRYJ1 SEX GLANGUA1 GABORGA1 2006 07 YSS Main Microdata User Guide April 2008 48 Question 27 28 29 About how much money do you usually get each week to spend on yourself or to save Remember to include all money from allowances and jobs like babysitting delivering papers How old are you What grade are you in 2006 07 Variable _Name GMONEYA1 AGE GRADE Table B2 Questions in the 2002 2004 and 2006 Surveys 28 ltems Question 1 2 030 ga Ss 11 12 13 15 16 In the last 30 days have you ever been asked for ID when buying cigarettes in a store In the last 30 days have you ever asked a stranger to buy you cigarettes Think back over
50. nnaire Module Code Module A English 4 Module A French 2 Module B1 English 3 Module B1 French 4 Module B2 English 5 Module B2 French 6 e Module A completed by Grades 5 6 e Modules B1 and B2 completed by Grades 7 12 or equivalent e All grades 5 and 6 students who filled out a Module B1 or a Module B2 survey were given a 9996 Not Asked for the questions that were not asked in Module A surveys These records were given the value MODULE 1 1 e Module A English or MODULE 2 e Module A French e All grades 5 and 6 students who filled out a Module B1 were given a 99 Not Stated for the questions that only appear in Modules A and B2 All grades 5 and 6 students who filled out a Module B2 were given a 99 Not Stated for the questions that only appear in Modules A and B1 e All grades 7 to 12 students who filled out a Module A were given a 99 Not Stated for all questions in both Module B1 and Module B2 but not Module A These records were given the value MODULE 3 i e Module B1 English or MODULE 4 i e Module B1 French Therefore respondents were given 9996 Not Asked for all questions in Modules A and B2 and 99 Not Stated for all questions in Module B1 Inconsistencies The YSS survey was intentionally designed with no respondent use skip patterns to avoid the identification of smokers by rate of survey completion during the classroom session However due to the logical flow of the questions a number of que
51. od On average the survey took 30 to 40 minutes to complete To protect confidentiality teachers were asked not to circulate among the students Students were also required to place their completed survey in an envelope and to seal this envelope before it was collected by the classroom teacher Individual envelopes containing the completed student questionnaire were placed in a large classroom envelope A project staff member site coordinator or data collector attended each school data collection The staff member set up a station in front of the school office or another central location The data collector was available to answer questions and receive classroom envelopes at the end of the data collection period Within a few days of data 2006 07 YSS Main Microdata User Guide April 2008 12 collection the site coordinators shipped the completed questionnaires organized by school and classroom to the SHAPES team at the University of Waterloo 5 6 Sample Size The following tables provide recruitment outcomes by school board Table 4 and school Table 5 Table 6 provides the total number of students who completed the survey Table 4 Board Recruitment Outcomes by Province 2006 07 YSS Board Recruitment Outcome Province Approached Agreed Refused Response rate NL 4 4 0 100 0 NS 7 7 0 100 0 PEI 2 2 0 100 0 NB 14 14 0 100 0 Qc 36 30 6 83 3 ON 34 28 6 82 4 MB 13 12 1 92 3 SK 17 16 1 94 1 AB 30 22 8 73 3 BC 41 25 16 61 0
52. oker DVTY1ST 3 Never Smoker Derivation of Current Definition A current smoker is a person who reports having Responses for smoker smoked 100 cigarettes and has smoked in the past DVTY1ST 30 days Calculation SHUNDOA1 Have you ever smoked 100 or more whole cigarettes in your life Valid response 1 Yes AND SLST30A1 On how many of the last 30 days did you smoke one or more cigarettes Valid responses 2 1 day 3 2 to 3 days 4 4 to 5 days 5 6 to 10 days 6 11 to 20 days 7 21 to 29 days 8 30 days every day Former Definition A former smoker is a person who reports having Smoker smoked 100 or more cigarettes but did not smoke in the last 30 days Calculation SHUNDOA1 Have you ever smoked 100 or more whole cigarettes in your life Valid response 1 Yes AND SLST30A1 On how many of the last 30 days did you smoke one or more cigarettes Valid response 1 None Never Definition A never smoker is a person who reports that he or Smoker she has not smoked 100 or more whole cigarettes in his or her life time but might have smoked a whole cigarette Calculation SHUNDOA1 Have you ever smoked 100 or more whole cigarettes in your life Valid response 2 No 2006 07 YSS Main Microdata User Guide April 2008 19 Derived Variable Derived Variable Response Options for DVTY2ST Derivation of Responses for DVTY2ST DVTY1ST l l SWHOLEA1 Have you ever smoked a whole cigarette Valid responses 2 No 9
53. old were you when you first smoked SLAST7B1 25 26 25 every day for at least 7 days in a row On how many of the last 30 days did you SLST30A1 27 27 27 smoke one or more cigarettes Thinking back over the last 30 days on the SLST30B1 28 28 28 days that you smoked how many cigarettes did you usually smoke each day 2006 07 YSS Main Microdata User Guide April 2008 45 MAIN Questions Variable Name Question A B1 B2 When you smoke how often do you share a SSHAREA1 29 30 30 cigarette with others What brand of cigarettes do you usually SBRNDUA1 30 31 31 smoke Why do you smoke the brand of cigarettes that you do My friends smoke the same brand SBRNDYC1 31 32 32 My parents smoke the same brand SBRNDYD1 31 32 32 like the packaging SBRNDYE1 31 32 32 This brand costs less than other brands SBRNDYF1 31 32 32 like the image of this brand SBRNDYG1 31 32 32 like the taste SBRNDYH1 31 32 32 They are the only ones can get SBRNDYI1 31 32 32 They have less tar SBRNDYJ1 31 32 32 For the nicotine buzz SBRNDYK1 31 32 32 Other SBRNDYL1 31 32 32 Where do you usually get your cigarettes SGETCGA1 32 33 33 In the last 30 days have you ever been asked SLST30C1 33 34 34 your age when buying cigarettes in a store In the last 30 days have you ever been asked SLST30D1 34 35 35 for ID when buying cigarettes in a store In the last 30 days has anyone in a store SLST30E1 35 36 36 refused to sell you cigarettes In the last 30 days have you e
54. ollaborators requested that we add another 24 schools resulting in a total of 56 additional schools sampled in this province Table 3 shows by province the target number of schools the number of additional schools over sampled based on the 2004 05 recruitment rate and the final number of 2006 07 YSS Main Microdata User Guide April 2008 7 schools in the sample at the outset of the project Note that some schools were eliminated even before recruitment began Explanation of exclusions and or inclusions is provided in the notes below Table 3 Table 3 Total Number of Schools Sampled by Province 2006 07 YSS Province Target School Over sampled of Schools Sample at schools recruitment 06 07 added by project 06 07 rate 04 05 request outset NL 24 100 4 0 0 28 NS 24 77 8 30 0 32 PE 24 96 3 0 0 27 NB 24 71 8 30 171 203 QC 54 60 28 40 0 82 ON 54 39 32 60 0 854 MB 24 88 8 20 0 32 SK 24 69 8 35 0 32 AB 36 50 20 55 0 54 BC 36 27 32 85 24 92 Canada 324 55 151 54 195 667 Although NL had 100 response rate in 04 05 we provided 4 additional schools 1 from each stratum to their sample list to accommodate refusals in 06 07 PEI was originally not over sampled However we decided to add an additional 3 schools 1 from each stratum note there were no schools to select from for the 4 stratum low smoking rate secondary school stratum to the sample list to accommoda
55. olments in those groups Finally bootstrap weights see Stage 5 page 34 were generated to attach to the data file Stage 1 Calculation of w For all the provinces all the schools in a given province were divided into four strata based on their grade levels and health region adult smoking rates as described earlier Within each stratum in each province schools were randomly selected with probability proportional to the total enrolment in their boards For school j w has been computed as Wi 1 Tt where Tt y is the probability of inclusion for school j at stage 1 and where L T l Mj 2M in this expression Mj total enrolment for the board of school j Number of selected schools in the given stratum and L Total number of schools in the stratum 2006 07 YSS Main Microdata User Guide April 2008 33 Table 7 below summarizes the number of schools participating per stratum Table 7 Number of Schools Participating by Province and Stratum 2006 07 YSS Stratum Province 1 2 Total Elementary Secondary NL 18 8 26 NS 13 8 21 PEI 18 7 25 NB 125 58 283 QC 36 11 47 ON 32 16 48 MB 19 8 27 SK 16 8 24 AB 18 12 30 BC 29 7 36 Canada 324 143 467 Stage 2 Calculation of w Within each selected school we computed the response rate for the students by grade n g 2 N 8 where n g is the number of students who completed a survey in grade g in school j N g is the total number of student
56. on of New Brunswick translation of all materials was conducted by Services D Edition Guy Connolly and certain documents were reviewed by Qu bec project staff Note that the HE and PA surveys contained YSS smoking behaviour questions and mental fitness questions A collaborative decision was made to exclude all data from the PA and HE modules from the YSS datasets including the smoking variables 2006 07 YSS Main Microdata User Guide April 2008 10 5 3 Recruitment of Schools The process of school recruitment started by sending project information letters to all provincial Ministries of Education and Health across the country to inform them of the planned Youth Smoking Survey in the upcoming 2006 07 school year In return several Deputy Ministers of Education and Health returned letters of support providing information on the importance of the YSS and describing how the survey fits within their mandate When available these support letters were used as a part of the recruitment package for schools and boards within the province In all provinces staff approached school boards prior to contact with schools Private schools were approached directly as there was often no school board School boards were typically contacted via a formal application if applicable or a board recruitment package and phone calls Once a school board was successfully recruited the schools within that school board were approached via a school recru
57. on preparation and implementation Site coordinators attended a two day training session participated in additional web based training sessions received a comprehensive manual and had ready access to the Student Data Collection Coordinator for advice regarding day to day issues Materials an online database and protocols were centrally developed to ensure consistency across provinces The online database permitted central coordinators to monitor progress and alignment with protocols Provincial site coordinators took responsibility for all board and school recruitment Site coordinators worked with a school contact to arrange data collection at each school School contacts were asked to provide a list of classes for the eligible grades that included teacher name course name and or the classroom number grade room number optional and the number of students enrolled Staff used this information to prepare consent materials and entered it along with other school particulars e g address data collection date etc into an online database Upon receipt of consent materials student information was entered into this database and questionnaire IDs were assigned Questionnaires were bundled by classroom and couriered to the school contact for distribution to classroom teachers 1 to 2 days prior to the data collection date On the data collection date teachers administered the survey according to detailed instructions during a designated class peri
58. ondition Variable coded 96 or 996 or 9996 If MODULE 1 or 2 MODULE A ENGLISH MODULE A FRENCH If AEVRETA1 2 NO or 99 Not Stated Have you ever had a drink of alcohol that is more than a sip If AEVRETA1 2 NO or 99 Not Stated Have you ever had a drink of alcohol that is more than a sip If AEVRETA1 2 NO or 99 Not Stated Have you ever had a drink of alcohol that is more than a sip 2006 07 YSS Main Microdata User Guide April 2008 29 A5DRNKB1 ASDRNKC1 AEVRMJB1 AOFTMJA1 AMIGHTA1 AUAMPHB1 AUMDMAB1 AUHALUB1 AUDACSB1 AUHEROB1 AUCOCNB1 AUSTERB1 AUSOLVB1 How old were you when you first had 5 drinks or more of alcohol on one occasion In the last 12 months how often did you have 5 drinks of alcohol or more on one occasion How old were you when you first used marijuana or cannabis In the last 12 months how often did you use marijuana or cannabis Do you think in the future you might try marijuana or cannabis How old were you when you first used or tried amphetamines How old were you when you first used or tried MDMA How old were you when you first used or tried hallucinogens How old were you when you first used or tried DACS How old were you when you first used or tried heroin How old were you when you first used or tried cocaine How old were you when you first used or tried steroids How old were you when
59. ou ever smoked a whole cigarette If SWHOLEA1 2 NO or 96 Valid Skip Have you ever smoked a whole cigarette If SPUFFOA1 2 NO Have you ever tried cigarette smoking even just a few puffs If SPUFFOA1 2 NO Have you ever tried cigarette smoking even just a few puffs If SBRNDUA1 1 I do not smoke 2 I do not have a regular brand 96 Valid Skip or 99 Not Stated What brand of cigarettes do you usually smoke If SPUFFOA1 2 NO Have you ever tried cigarette smoking even just a few puffs If SPUFFOA1 2 NO Have you ever tried cigarette smoking even just a few puffs If SLST30A1 1 None or 96 Valid Skip On how many of the last 30 days did you smoke one or more cigarettes If SPUFFOA1 2 NO Have you ever tried cigarette smoking even just a few puffs If SPUFFOA1 1 YES Have you ever tried cigarette smoking even just a few puffs 2006 07 YSS Main Microdata User Guide April 2008 28 Skip Patterns for Variables in Modules A and B1 Variable VARIABLES Questions Valid Condition if Respondent Skip Condition Variable coded 9996 If MODULE 5 or 6 MODULE LISTED AS MODULES A AND B1 Skip Patterns for Variables in Modules A and B2 Variable VARIABLES LISTED AS MODULES A AND B2 SLST12A1 SPLACEA1 to SPLACEI1 STIMESA1 to STIMESE1 SPEOPLA1 to SPEOPLD1 All variables appearing only in Modules A and B1 Questions All varia
60. ou think you will smoke a cigarette Do you think in the future you might try smoking cigarettes Why do you smoke the brand of cigarettes that you do Mark all that apply What brand of cigarettes do you usually smoke Do you think it would be difficult or easy for you to get cigarettes if you wanted to try smoking Where do you usually get your cigarettes In the last 30 days have you ever been asked your age when buying cigarettes in a store In the last 30 days has anyone in a store refused to sell you cigarettes At your school what are the rules about smoking tobacco How do the rules about smoking tobacco at your school affect you Do most students who smoke cigarettes obey the rules about smoking at your school Excluding yourself how many people smoke inside your home every day or almost every day Do not count those who smoke outside Do you ever smoke inside your home Your closest friends are the friends you like to spend the most time with How many of your closest friends smoke cigarettes Why do you think people your age start to smoke Mark all that apply What health problems can people get if they smoke for many years Mark all that apply In the last 12 months how many classes did you have that talked about the effects of smoking Have you ever tried any of the following Mark all that apply Are you a Girl Boy What language do you speak most often at home Are you an aboriginal perso
61. pril 2008 2 YSS and Healthy New Brunswick en sant collaborated on data collection in that province Healthy New Brunswick en sant sampled all students in grades 6 through 12 grade 5 students only in YSS sampled schools in the province Administration of this survey was sponsored by the New Brunswick Department of Wellness Culture and Sport as part of the implementation of the NB Wellness Strategy The 2006 07 YSS sample design included a total of 32 schools with a target of obtaining 24 schools in NB The Healthy New Brunswick en sant Survey sampled an additional 171 elementary middle and secondary schools in New Brunswick In all schools students in eligible classes were randomly assigned to complete one of three separate modules 1 Youth Smoking Survey 2 Healthy Eating or 3 Physical Activity Staff at the Universities of Waterloo and of New Brunswick adapted YSS protocols project materials and the online database Online Survey Implementation System OSIS to accommodate seamless data collection in this province alongside the YSS All YSS module data collected were incorporated to create a richer more comprehensive YSS dataset for this province Likewise the 2006 07 YSS collaborated with the CIHR funded Project Impact headed by Dr Chris Lovato University of British Columbia Project Impact collected data in five provinces Nine schools were sampled in common between the two projects YSS procedures were followed in all these
62. ree modules A PA HE Grades 7 12 students completed one of four modules B1 B2 PA HE Within each class in grades 5 and 6 and using the method described above 50 of students completed Module A 25 of students completed Module PA and the rest of the students 25 completed Module HE Similarly within each class in grades 7 12 25 of students completed Module B1 25 of students completed Module B2 25 of students completed Module PA and 25 of students completed Module HE 5 2 Pilot Testing In August 2006 SHAPES staff implemented a pilot test of the student questionnaire and the protocols for data collection As part of the pilot students were asked to complete the questionnaire according to normal protocols as well as provide feedback on any questionnaire items they found difficult to answer or did not understand Three focus groups were held with a small group of students in order to explore reactions to the survey in more depth The school contact and teachers also provided feedback As a result of the pilot test refinements were made to six questions e g rewording additional response options added and to the explanatory text e g definitions added assurances of confidentiality repeated All project materials including questionnaires were translated into French for the 2006 07 YSS French documents including French surveys were used in four provinces New Brunswick Ontario Qu bec and Alberta With the excepti
63. ril 2008 53 Appendix C Differences in Derived Variables between 2004 05 YSS and 2006 07 YSS Table C1 Differences in Derived Variables between 2006 07 YSS and 2004 05 YSS 2006 07 YSS Derived Variables _2004 05 YSS Derived Variables DSUSCEPT D_SUSCEPTIBLE Response 1 No Response 1 No options 2 Yes options 2 Yes 96 Valid Skip 99 Not Stated 99 Not Stated Valid Skips were Valid Skip 96 if not assigned SPUFFOA1 1 Yes Have you ever tried cigarettes smoking even just a few puffs Rationale This variable is not applicable to those who have already tried smoking DVSELF Derived from Choose the Derived from Choose the answer three of the answer that best five that best describes five 2004 05 describes how questions how you feel questions you feel a In general like a In general the way am like the way b Overall have a am lot to be proud of b When Ido c A lot of things something about me are do it well good c like the way d When Ido look something do it well e Ilike the way look Response 1 True Response 1 False options for 2 Mostly true options for 2 Mostly false each item 3 Sometimes each item 3 Sometimes false true Sometimes sometimes true false 4 Mostly true 4 Mostly false 5 True 5 False Recoded 0 False Recoded 0 False 1 Mostly false 2 Sometimes false sometimes 1 Mostly false 2 Sometimes false Sometimes true 2006
64. rs occurring systematically will contribute to biases in the survey estimates Considerable time and effort were taken to reduce non sampling errors in the survey Quality assurance measures were implemented at each step of the data collection and processing cycle to monitor the quality of the data These measures included 1 the use of protocols that have been validated in previous studies of school based data collection around youth smoking 2 detailed instructions for teachers 3 extensive training of project staff with respect to the survey procedures 4 procedures to ensure that data capture errors were minimized and 5 coding and edit quality checks to verify the processing logic 8 0 Guidelines for Tabulation Analysis and Release Please note that this section is adapted from the 2002 Youth Smoking Survey User Guide written by Statistics Canada It details guidelines for users when tabulating analyzing publishing or otherwise releasing any data derived from the survey microdata files With the aid of these guidelines users of microdata should be able to produce the same figures as those produced by any statistician and at the same time will be able to develop currently unpublished figures in a manner consistent with these established guidelines 8 1 Rounding Guide Users are urged to adhere to the following guidelines regarding the rounding of such estimates Stats Canada 2002 Microdata User Guide Youth Smoking Survey 2002
65. s in grade g in school j Hence wa 1 Tt2 2006 07 YSS Main Microdata User Guide April 2008 34 Stage 3 Un calibrated Final Weight The final un calibrated weight is based on w MAIN _WT w w Stage 4 Calibration of Survey Weights The weights described above were then calibrated using school administrative datasets that include the total student enrolment by gender and grade grades 5 through 12 for each province Province grade and gender calibration were used to adjust the sampling weights so that estimated numbers of students in these domains reproduce known population numbers exactly Final weight variables were designated as MAIN_WT Stage 5 Construction of Bootstrap Weights Statisticians use bootstrap methods to estimate sampling error The bootstrap weights for each province were constructed separately as follows 1 Within each stratum health region smoking rate stratum crossed with grade level stratum the same number of schools was selected from the sample by simple random sampling SRS with replacement as was selected in the original sample design 2 Then within each re sampled school all eligible students who had consent to participate were selected 3 The weights for re selected units were recalculated and adjusted for the re sampling inference based on the method of Rao and Wu 1988 4 Finally the new weights were recalibrated to the provincial enrolment figures using the administrative datas
66. scribed in the above paragraph produces reliable estimates of the coefficients under consideration in the analysis however the stratification and clustering of the sample s design are still not taken into account Consequently the variance estimates calculated in this way are likely to be under estimated 8 5 Coefficient of Variation Release Guidelines Before releasing and or publishing any estimate from the 2006 07 YSS users should first determine the quality level of the estimate The quality levels are Acceptable Marginal and Unacceptable Data quality is affected by both sampling and non sampling errors as discussed in Section 7 However for this purpose the quality level of an estimate will be determined only on the basis of sampling error as reflected by the coefficient of variation i e standard deviation divided by the mean multiplied by 100 as shown in the table below Nonetheless users should be sure to read Section 7 to be more fully aware of the quality characteristics of these data First determine the number of respondents who contributed to the calculation of the estimate If this number is less than 30 consider the weighted estimate to be of Unacceptable quality For weighted estimates based on sample sizes of 30 or more users should determine the coefficient of variation of the estimate and follow the guidelines in Table 9 Apply these quality level guidelines to weighted rounded estimates All estimates may be rel
67. sest friends smoke cigarettes In the last 12 months how many classes did SLECSMA1 65 59 67 you have that talked about the effects of smoking In the last 12 months have you taken part in any other anti smoking activities or events either at school or in the community School assembly or class with guest SANTISA1 66 60 68 speaker School health fair SANTISB1 66 60 68 Media production poster commercial SANTISC1 66 60 68 etc Community event outside of school SANTISD1 66 60 68 Quit smoking contest SANTISE1 66 60 68 Smoking cessation counselling or SANTISF1 66 60 68 program have not taken part in any of these SANTISG1 66 60 68 activities or events in the last 12 months Susceptible to smoking DSUSCEPT D D D General score to measure the child s overall DVSELF D D D self esteem Smoking Status DVTY1ST D D D Smoking Detailed Classifications DVTY2ST D D D Language of the Survey LANGUAGE D D D Module the respondent filled out MODULE D D D Project which the respondent s school was PROJECT D D D recruited for Province ID Number provID D D D Student survey identification number scanID D D D D refers to derived variable as described in Section 6 3 of this Guide 2006 07 YSS Main Microdata User Guide April 2008 47 Appendix B Youth Smoking Survey Questions by D 11 12 13 14 15 16 18 19 20 21 22 23 24 25 26 a row At any time during the next year do y
68. stions were extraneous based on the answer to a previous question In these cases a skip pattern was imposed onto the data set There are other instances where inconsistencies in student response were present In order to be consistent with the 2002 YSS dataset released by Statistics Canada the responses as recorded by the student have been provided Note however that in certain cases responses to one question may contradict a response to a previous 2006 07 YSS Main Microdata User Guide April 2008 17 question In conducting analyses of these variables it is recommended that the observations with inconsistent responses be taken into consideration For example a student may have responded in one question having smoked in the last seven days and in another question the same student responded I have not smoked in the last 30 days These types of inconsistencies were left in the data set for the user to decide how best to handle the case 2006 07 YSS Main Microdata User Guide April 2008 6 3 Creation of Derived Variables A number of variables in the microdata file were derived by combining items on the questionnaire in order to facilitate data analysis Examples of derived variables include the average number of whole cigarettes smoked daily and the number of whole cigarettes the respondent had smoked Main Data Set Derived Variables Derived Variable DVTY1ST _ Response 1 Current smoker Options for 2 Former sm
69. stores e g convenience stores supermarkets grocery stores gas stations near your school 16 In the last 12 months did you engage in any of the following activities outside of school requirements and without being paid A Supporting a cause e g food bank environmental group B Fund raising e g charity school trips C Helping in my community e g hospital volunteering work in a community organization D Helping neighbours or relatives e g cutting grass babysitting shoveling snow E Doing other organized volunteer activity 17 In the last 4 weeks how many days of school did you miss because of your health 18 In the last 4 weeks how many classes did you skip when you weren t supposed to 19 How often do you smoke tobacco at home 20 How often do you smoke tobacco walking to and or from school _Variable Name SLST12A1 SSHAREA1 SSTRSPA1 SSTRSCA1 SGRDANA1 SANTISA1 to SANTISG1 SWRBYCA1 to SWRBYCE1 SNTSPDA1 SFINEDA1 SNEAROA1 SCLEARA1 SBREAKA1 GCANADA1 GLICNSA1 SSTRSVA1 OVOLUNA1 OVOLUNB1 OVOLUNC1 OVOLUND1 OVOLUNE1 OMISSHA1 OSKIPOA1 SPLACEA1 SPLACEB1 2006 07 YSS Main Microdata User Guide April 2008 52 Question 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 How often do you smoke tobacco at school but off school property How often do you smoke tobacco at school on schoo
70. t year do you think you will smoke a cigarette 2 Probably yes 3 Probably not 4 Definitely not 99 Not Stated 2006 07 YSS Main Microdata User Guide April 2008 22 Derivation of Responses for DSUSCEPT Derived Variable Objective Questions Notes 1 No 2 Yes 96 Valid Skip 99 Not Stated DVSELF Calculation Calculation Calculation Calculation To measure the student s overall self esteem For the next 3 questions choose the answer that describes how you feel about the statement OHOWFLA1 In general like the way am OHOWFLB1 When I do something do it well OHOWFLC1 like the way look Scale recoded as If SSUSMTA1 4 and SSUSFOA1 4 and SSUSNYA1 4 If SSUSMTA1 1 2 3 or 99 or SSUSFOA1 1 2 3 or 99 or SSUSNYA1 1 2 3 or 99 If SPUFFOA1 1 If SSUSMTA1 99 and SSUSFOA1 99 and SSUSNYA1 99 Only those students who had all three questions missing were given DSUSCEPT 99 1 True 2 Mostly true 3 Sometimes true Sometimes false 4 Mostly false 5 False 0 False 1 Mostly false 2 Sometimes false Sometimes true 3 Mostly true 4 True e Following the re coding of the scale the scores were added up across the questions that were answered by the student giving an overall score for variable DVSELF e Only those records who had all three questions missing were given DVSELF 99 2006 07 YSS Main Microdat
71. te refusals in 06 07 3 An additional 171 schools were added to the sample as part of the Healthy New Brunswick en sant initiative For a description please see the Background section of this report pages 2 3 One school was eliminated after sampling because the school was identified as an alternative school Two schools were eliminated after sampling because they were identified as schools for the learning disabled 6 The additional 24 schools were part of the sampling for selecting 92 schools for BC Selection of Private and Independent Schools Within each province lists of private schools were obtained A simple random sample of private schools was selected in each province from these lists The number of schools originally selected was roughly proportional to the number of students enrolled in private schools in that province as compared to the total in public schools Selection of Students Within each selected school all students in the survey grades 5 12 were eligible for participation Consent procedures are described in Section 5 4 2006 07 YSS Main Microdata User Guide April 2008 8 5 0 Data Collection Data collection was conducted from November 2006 to June 2007 with school board recruitment beginning in one province ON as early as August 2006 Students were surveyed in their classrooms 5 1 Questionnaire Design Several key considerations guided the design of the student questionnaire e Comparab
72. the last 7 days Find yesterday on the wheel and fill in the number of cigarettes that you smoked Then follow the wheel backwards and fill in the number of cigarettes you smoked on each of the last 7 days If you have not smoked mark one of the circles below On average how many hours a day do you watch TV or videos How often do you read for fun not for school In general like the way am When do something do it well like the way look How are you doing in school compared to other students in your class Have you ever had a drink of alcohol that is more than just a sip a beer wine cooler glass of wine or shot of liquor How old were you when you first had a drink of alcohol that is more than a sip Have you ever had 5 drinks or more of alcohol on one occasion How old were you when you first had 5 drinks or more of alcohol on one occasion Have you ever used or tried marijuana or cannabis a joint pot weed hash How old were you when you first used marijuana or cannabis This chart asks about your drug use First mark the circle if you have ever used or tried the drug Then mark your age when you first tried the drug A Amphetamines speed ice meth MDMA ecstasy E X C Hallucinogens LSD PCP acid magic mushrooms mesc DACS links U is 2006 07 Variable name SLST30D1 SLST30F1 SLAST7A2 to SLAST7H2 B1 SLAST7A3 to SLAST7H3 B2 PSCRENA2 P
73. the week prior to the survey Average number of times cigarettes were smoked on the days that the respondent smoked Valid Condition if Respondent Completed Module B1 Had tried smoking Had tried smoking Had tried smoking Had tried smoking Skip Condition Variable coded 96 or 996 or 9996 If AUMEDSA1 2 NO or 99 Not Stated Have you ever used or tried medication like Ritalin NOT for medical purposes If AUPAINA1 2 NO or 99 Not Stated Have you ever used or tried painkillers to get high and NOT for medical purposes If AUNATRA1 2 NO or 99 Not Stated Have you ever used or tried any other medications or natural health products to get high and NOT for medical urposes Skip Condition Variable coded 96 or 996 or 9996 If MODULE 1 2 5 or 6 MODULE A ENGLISH MODULE A FRENCH MODULE B2 ENGLISH or MODULE B2 FRENCH If SPUFFOA1 2 NO Have you ever tried cigarette smoking even just a few puffs If SPUFFOA1 2 NO Have you ever tried cigarette smoking even just a few puffs If SPUFFOA1 2 NO Have you ever tried cigarette smoking even just a few puffs If SPUFFOA1 2 NO Have you ever tried cigarette smoking even just a few puffs 2006 07 YSS Main Microdata User Guide April 2008 31 Skip Patterns for Variables in Module B2 only VARIABLES LISTED AS MODULES B2 ONLY SLAST7A3 to SLAST7H3 DVAMTSMK DVCIGWK2 DVNDSMK2 DAVCIGD2 DVSMKPT
74. to identify its health region From there the smoking rates for 15 19 year olds in each health region were determined based on the Canadian Community Health Survey CCHS data The CCHS sampled sufficient adults in each health region to allow for an estimate of the region s current smoking rate Within each province each school was assigned an estimate of the adult smoking rate from the CCHS for the school s public health region Next the total eligible grade enrolments were used as a weight to compute the median smoking rate for each province by using the health region s smoking rate Schools that were located in a health region with a smoking rate lower than the median smoking rate were assigned to the low smoking rate stratum Similarly schools located in a health region with For consistency the guide will refer to school boards school districts and school divisions by the term school board 2006 07 YSS Main Microdata User Guide April 2008 5 a smoking rate more than or equal to the median were assigned to the high smoking rate stratum Table 1 reflects the distribution of schools by health stratum and province Table 1 Number of Participating and Non Participating Schools by Health Stratum and Province 2006 07 YSS Province Target Health of Participating of Schools Not Schools Stratum Schools Participating l Low 9 1 NL 24 High 17 Low 10 6 NS High 11 6 Low 8 3 PE High 17 1 Low 74 12 NB
75. uide April 2008 37 7 0 Data Quality There are various factors that influence data quality This section summarizes threats to data quality and steps taken to ameliorate these 7 1 Response Rates There were various levels of non response throughout the 2006 07 YSS First some degree of non response was noted among school boards and schools Refer to Table 4 and Table 5 for a listing of response rates at the school board and school level in 2006 07 YSS The third level of response rate is based on individual student consent The response rate at the student level is derived based on the number of eligible students as provided by school contacts for participating classes Non response at the student level can be attributed to several factors Some parents guardians refused to allow their child to take part in the survey Even with parental permission some students refused to participate or were absent from class on the day of collection The final response rates at the student level are summarized in Table 8 below Table 8 Student Level Response Rates by Province 2006 07 YSS Students Students Province students Milhactivo with passive questionnaires rate CA NL 6759 2062 1203 3265 48 3 NS 7115 1761 2615 4376 61 5 PEI 7718 2446 2416 4862 63 0 NB 63631 12306 26885 39191 61 6 Qc 18632 2358 10605 12963 69 6 ON 18009 2895 7967 10862 60 3 MB 7018 1462 3079 4541 64 7 SK 4984 2468 0 2468 49 5 AB 6353 2646 200 2846 44 8 BC 8491 2
76. ve Permission For schools that contained only secondary grades e g 9 12 in ON 8 12 in BC and Secondaire I V in QC active information passive permission procedures were used In these schools school staff sent information permission letters to the student s home address This letter provided detailed information about the student survey and requested parents to call a toll free number or inform the school if they did not want their child to participate If no call email or letter was received it was assumed that parents passively 2006 07 YSS Main Microdata User Guide April 2008 11 provided permission for their child to participate All students except those whose name appeared on the no permission list received a survey on data collection day 5 5 Data Collection Protocols Ethics Review Prior to implementation the University of Waterloo Human Research Ethics Committee approved all protocols and materials Local institutional review boards affiliated with the institutions of consortium members also reviewed the project at the provincial level where applicable 1 e where collaborators were affiliated with universities All methods received ethics approval by the appropriate institutions e g in some cases from three levels the University of Waterloo provincial host institution and school board Each provincial collaborator hired a site coordinator to be responsible for school board and school recruitment data collecti
77. ver asked a SLST30F1 36 37 37 stranger to buy you cigarettes Have you ever tried to quit smoking SEVRQTA1 41 38 42 cigarettes Do you think you would be able to quit SSURQTA1 42 39 43 smoking cigarettes if you wanted to Have you ever tried any of the following Smoking pipe tobacco SEVTRYA1 43 40 44 Smoking cigars cigarillos or little cigars SEVTRYB1 43 40 44 plain or flavoured Smoking bidis tobacco product from SEVTRYC1 43 40 44 India Using chewing tobacco SEVTRYD1 43 40 44 Using nasal snuff tobacco powder SEVTRYE1 43 40 44 people sniff Using oral snuff tobacco powder people SEVTRYF1 43 40 44 hold between their lip and gum or cheek Using nicotine patches nicotine gum or SEVTRYG1 43 40 44 nicotine lozenges Using a water pipe also known as SEVTRYH1 43 40 44 hookah sheesha narg eelay hubble bubble or gouza to smoke tobacco have not tried these things SEVTRYJ1 43 40 44 Do any of your parents step parents or SGRDANA1 47 43 50 guardians smoke cigarettes Do any of your brothers or sisters smoke SSIBLIA1 48 44 51 cigarettes Do you ever smoke inside your home SHRULSC1 52 48 52 2006 07 YSS Main Microdata User Guide April 2008 46 MAIN Questions Variable Name Question A B1 B2 During the past 7 days on how many days did SINCARA1 53 49 53 you ride in a car with someone who was smoking cigarettes Your closest friends are the friends you like to S5FRNDA1 54 50 54 spend the most time with How many of your clo
78. x SOPINOD1 22 Does quitting smoking reduce health damage even after many years of SOPINOE1 smoking 23 Does smoking help people stay slim SOPINOF1 24 Can people become addicted to tobacco SOPINOG1 25 Can tobacco smoke be harmful to the health of non smokers SOPINOH1 26 Can smokers quit anytime they want SOPINOJ1 27 Do you think smoking is cool SOPINOK1 28 Is it nicer to date people who do not smoke SOPINON1 The item DACS was only included in the 2004 and 2006 surveys This item was not on the 2002 survey This question appeared in the manner above in both the 2004 and 2006 surveys In 2002 two questions were asked in place of this one They were Have you ever used or tried Ephedrine or Pseudoephedrine Sudafed Ephedra Herbal ecstasy to get high and NOT for medical purposes and Have you ever used or tried Gravol to get high and NOT for medical purposes In addition the corresponding age questions for the above two questions were asked in 2002 2006 07 YSS Main Microdata User Guide April 2008 50 Table B3 Questions in the 2004 and 2006 Surveys 24 Items _2006 07 Variable name Question 1 2 10 11 13 14 15 18 19 20 21 22 23 24 Are you a smoker How old were you when you first tried smoking cigarettes even just a few puffs If one of your best friends was to offer you a cigarette would you smoke it Do you think you would be able to quit smoking cigarettes
79. xperimental Definition Smoker Beginner Calculation Past Definition Experimental Smoker Calculation SLST30A1 On how many of the last 30 days did you smoke one or more cigarettes Valid Response 1 None AND SLAST7A1 Have you ever smoked every day for at least 7 days in row Valid Response 1 Yes A former occasional smoker is a person who smoked at least 100 cigarettes in his her life time and did not smoke for at least seven days in a row and also did not smoke in the last 30 days SHUNDOA1 Have you ever smoked 100 or more whole cigarettes in your life Valid response 1 Yes AND SLST30A1 On how many of the last 30 days did you smoke one or more cigarettes Valid response 1 None AND SLAST7A1 Have you ever smoked every day for at least 7 days in row Valid response 2 No An experimental smoker is a person who has smoked in the last 30 days but has not smoked 100 or more cigarettes SWHOLEA1 Have you ever smoked a whole cigarette Valid response 1 Yes AND SHUNDOA1 Have you ever smoked 100 or more whole cigarettes in your life Valid response 2 No AND SLST30A1 On how many of the last 30 days did you smoke one or more cigarettes Valid responses 2 1 day 3 2 to 3 days 4 4 to 5 days 5 6 to 10 days 6 11 to 20 days 7 21 to 29 days 8 30 days every day A past experimental smoker is a person who has smoked a whole cigarette but did not smoke in the last 30 days and also did not smoke
80. you first used or tried this sniffed glue gasoline or other products solvents to get high Valid Condition if Respondent Had 5 drinks or more on one occasion Had 5 drinks or more on one occasion Had tried marijuana Had tried marijuana Had not tried marijuana Had tried amphetamines Had tried MDMA Had tried hallucinogens Had tried DACS Had tried heroin Had tried cocaine Had tried steroids Had sniffed glue gasoline or other products solvents to get high Skip Condition Variable coded 96 or 996 or 9996 If ASDRNKA1 2 NO 96 Valid Skip or 99 Not Stated Have you ever had 5 drinks or more of alcohol on one occasion If ASDRNKA1 2 NO 96 Valid Skip or 99 Not Stated Have you ever had 5 drinks or more of alcohol on one occasion If AEVRMJA1 2 NO or 99 Not Stated Have you ever used or tried marijuana or cannabis If AEVRMJA1 2 NO or 99 Not Stated Have you ever used or tried marijuana or cannabis If AEVRMJA1 1 YES or 99 Not Stated Have you ever used or tried marijuana or cannabis If AUAMPHA1 2 NO or 99 Not Stated Have you ever used or tried amphetamines If AUMDMAA1 2 NO or 99 Not Stated Have you ever used or tried MDMA If AUHALUA1 2 NO or 99 Not Stated Have you ever used or tried hallucinogens If AUDACSA1 2 NO or 99 Not Stated Have you ever used or tried DACS If AUHEROA1 2 NO or 99 Not Stated

Download Pdf Manuals

Related Search

Related Contents

Loading x86 BootBIOS  BIBLIOGRAFIA Abraham, P. D. et al. 1968. Stimulation of latex flow  オパシメータ    Operating Manual: - Spechtenhauser Pumpen GmbH  Viewsonic A Series 19" Value Series Widescreen LCD  Guide d`utilisation de la Box SFR  Miele DAR 1150 Specification Sheet    [U4.43.03] Opérateur AFFE_MATERIAU  

Copyright © All rights reserved. Failed to retrieve file