Canadian Community Health Survey A new program for collecting health information Interuniversity...
-
date post
19-Dec-2015 -
Category
Documents
-
view
213 -
download
0
Transcript of Canadian Community Health Survey A new program for collecting health information Interuniversity...
Canadian Community Health SurveyCanadian Community Health SurveyA new program for collecting health informationA new program for collecting health information
Interuniversity Research Data SeminarInteruniversity Research Data SeminarUniversity of British ColumbiaUniversity of British Columbia
Béland YvesBéland Yves
Household Survey Methods DivisionHousehold Survey Methods DivisionStatistics CanadaStatistics CanadaFebruary 19, 2002February 19, 2002
Presentation OutlinePresentation OutlineHealth Information RoadmapHealth Information Roadmap
–Origin of the CCHSOrigin of the CCHS
–Objectives / ContentObjectives / Content
–CCHS two-year planCCHS two-year plan
CCHS Cycle 1.1 - Sample DesignCCHS Cycle 1.1 - Sample Design–Allocation, frameAllocation, frame
–Selection - OversamplingSelection - Oversampling
–Data CollectionData Collection
–ImputationImputation
–Weighting, sampling errorWeighting, sampling error
–Bootstrap Variance EstimationBootstrap Variance Estimation
–Data QualityData Quality
–Data DisseminationData Dissemination
CCHS Cycle 1.2 - OverviewCCHS Cycle 1.2 - OverviewFuture Cycles of CCHSFuture Cycles of CCHS
Health Information RoadmapHealth Information Roadmap
Four-year action plan to strengthen Canada’s health information Four-year action plan to strengthen Canada’s health information systemsystemEarmarks funds for specific priorities/activities based on Earmarks funds for specific priorities/activities based on national vision and provincial/regional consultationsnational vision and provincial/regional consultationsPartners: Health Canada, Canadian Institute on Health Partners: Health Canada, Canadian Institute on Health Information (CIHI) and Statistics CanadaInformation (CIHI) and Statistics Canada
Key elements:Key elements:–fill critical data gaps in health services and address population health fill critical data gaps in health services and address population health data gaps at a sub-provincial leveldata gaps at a sub-provincial level
–foster common data and technical standardsfoster common data and technical standards
–develop indicators and conduct special studiesdevelop indicators and conduct special studies
Canadian Community Health Survey Canadian Community Health Survey Results of the Consultation Process Results of the Consultation Process
Assess health measure variations at many levels of geographyAssess health measure variations at many levels of geographyCollect data on issues unique to a health region or provinceCollect data on issues unique to a health region or provinceRespond quickly to emerging issuesRespond quickly to emerging issuesExplore certain key health issues in-depthExplore certain key health issues in-depthAnalyse the effects of shocks including policy changesAnalyse the effects of shocks including policy changes
Canadian Community Health Survey Canadian Community Health Survey Two-year Plan Two-year Plan
Cycle 1.1 - Health region-level surveyCycle 1.1 - Health region-level survey–Produce reliable estimates for sub-provincial areasProduce reliable estimates for sub-provincial areas
–Continuous monthly collection : Sept. 2000 - Nov. 2001Continuous monthly collection : Sept. 2000 - Nov. 2001
–Sample size : 133,300 respondents Sample size : 133,300 respondents
–Questionnaire contentQuestionnaire content•health determinantshealth determinants
•health statushealth status
•utilization of health servicesutilization of health services
•socio-demographic / socio-economic characteristicssocio-demographic / socio-economic characteristics
Cycle 1.2 - Provincial-level survey Cycle 1.2 - Provincial-level survey –Produce reliable provincial estimates from a sample of 30,000 respondentsProduce reliable provincial estimates from a sample of 30,000 respondents
–Monthly collection : May 2002 - Dec. 2002Monthly collection : May 2002 - Dec. 2002
–In-depth focus content: 90-100 minute interviews on mental health and In-depth focus content: 90-100 minute interviews on mental health and well-beingwell-being
CCHS and NPHS CCHS and NPHS A More Robust Health Survey ProgramA More Robust Health Survey Program
CCHSCCHS– cross-sectionalcross-sectional
– sample of 160,000 sample of 160,000 respondents over two yearsrespondents over two years
– national, provincial and national, provincial and regional level estimatesregional level estimates
– customized questionnaires customized questionnaires at regional levelat regional level
– built-in flexibility for buy-built-in flexibility for buy-in sample and/or content in sample and/or content
– continuous development of continuous development of in-depth health content in-depth health content
NPHS - HouseholdNPHS - Household– « goes longitudinal »« goes longitudinal » only, starting only, starting
in wave 4in wave 4
– sample of 20,000 personssample of 20,000 persons
– national and provincial level national and provincial level estimatesestimates
NPHS - Health Care InstitutionsNPHS - Health Care Institutions– longitudinal and cross-sectionallongitudinal and cross-sectional
– sample of 2,500sample of 2,500
– national level estimatesnational level estimates
CCHS - Cycle 1.1 CCHS - Cycle 1.1 Health Region-level survey Health Region-level survey
Produce timely cross-sectional estimates for Produce timely cross-sectional estimates for 136 health regions136 health regions
Target populationTarget population–individuals living in private occupied dwellings aged 12 years old or overindividuals living in private occupied dwellings aged 12 years old or over
–Exclusions:Exclusions: those living on Indian Reserves and Crown Lands, residents those living on Indian Reserves and Crown Lands, residents of institutions, full-time members of the Canadian Armed Forces and of institutions, full-time members of the Canadian Armed Forces and residents of some remote areasresidents of some remote areas
CCHS 1.1 covers ~98% of the Canadian population CCHS 1.1 covers ~98% of the Canadian population
CCHS - Questionnaire content CCHS - Questionnaire content
45-minute interview questionnaire45-minute interview questionnaire
–30 minutes of common modules common to all health regions30 minutes of common modules common to all health regions
–10 minutes of optional items selected by health regions from a predefined 10 minutes of optional items selected by health regions from a predefined list of moduleslist of modules
–5 minutes of standard socio-economic items5 minutes of standard socio-economic items
27 different versions of the questionnaire27 different versions of the questionnaire
The complete questionnaire can be found at The complete questionnaire can be found at www.statcan.ca/health_surveyswww.statcan.ca/health_surveys
CCHS - Sample Allocation to Provinces CCHS - Sample Allocation to Provinces
ProvProv PopPop # of # of 1st Step1st Step 2nd Step2nd Step TotalTotal
SizeSize HRs HRs 500/HR500/HR X-propX-prop SampleSample
NFLD 551K 6 *2,780 1,230 4,010
PEI 135K 2 1,000 1,000 2,000
NS 909K 6 3,000 2,040 5,040
NB 738K 7 3,500 1,650 5,150
QUE 7,139K 16 8,000 16,280 24,280
ONT 10,714K 37 18,500 23,760 42,260
MAN 1,114K 11 5,500 2,500 8,000
SASK 990K 11 *5,400 2,320 7,720
ALB 2,697K 17 *8,150 6,050 14,200
BC 3,725K 20 10,000 8,090 18,090
CAN 29,000K 133 65,830 64,920 130,750
* The sampling fraction in some small HRs was capped at 1 in 20 households
CCHS - Sample Allocation to Health Regions CCHS - Sample Allocation to Health Regions
Pop. Size # of Mean
Range HRs Sample Size
Small less than 75,000 41 525
Medium 75,000 - 240,000 60 900
Large 240,000 - 640,000 25 1,500
X-Large 640,000 and more 7 2,500
CCHS - Sample Allocation to Territories CCHS - Sample Allocation to Territories
Population Sample
Yukon 25,000 850
NWT 36,000 900
Nunavut 22,000 800
CCHS - Sample Frame CCHS - Sample Frame
CCHS sample selected from three frames: CCHS sample selected from three frames:
•Area frame (Labour Force Survey structure)Area frame (Labour Force Survey structure)
•RDD frame of telephone numbers (Random Digit Dialling)RDD frame of telephone numbers (Random Digit Dialling)
•List frame of telephone numbersList frame of telephone numbers
Three frames are needed for CCHS for the following reasons:Three frames are needed for CCHS for the following reasons:
1. To yield the desired sample sizes in all health regions1. To yield the desired sample sizes in all health regions
2. Have a telephone data collection structure in place to quickly address 2. Have a telephone data collection structure in place to quickly address provincial/regional requests for buy-in sample and/or content at any point in provincial/regional requests for buy-in sample and/or content at any point in timetime
3. Optimize collection costs3. Optimize collection costs
Area frame - Sampling of householdsArea frame - Sampling of households
83% of CCHS sampled households83% of CCHS sampled households Stratified multistage sample designStratified multistage sample design
Stratum #1
Stratum #2
#1: Each health region is divided into strata
#2: Clusters selected within strata (PPS sampling) (1st stage)
#3: Dwellings selected within clusters (2nd stage)
RDD frame of telephone numbers RDD frame of telephone numbers Sampling of households Sampling of households
Elimination of non-working banks methodElimination of non-working banks method– 7% of CCHS sampled households7% of CCHS sampled households
– Telephone bank: area code + first 5 digits of a 7-digit phone #Telephone bank: area code + first 5 digits of a 7-digit phone #
1- Keep the banks with at least one valid phone #1- Keep the banks with at least one valid phone #
2- Group the banks to encompass as closely as possible the health region areas - RDD strata2- Group the banks to encompass as closely as possible the health region areas - RDD strata
3- Within each RDD stratum, first select one bank at random and then generate at random one number between 00 and 993- Within each RDD stratum, first select one bank at random and then generate at random one number between 00 and 99
4- Repeat the process until the required number of telephone numbers within the RDD stratum is reached4- Repeat the process until the required number of telephone numbers within the RDD stratum is reached
List frame of telephone numbers List frame of telephone numbers Sampling of households Sampling of households
Simple random sample of telephone numbersSimple random sample of telephone numbers– 10% of CCHS sampled households10% of CCHS sampled households
– Telephone companies’ billing address files and Telephone Infobase (repository of phone directories)Telephone companies’ billing address files and Telephone Infobase (repository of phone directories)
1- Create a list of phone numbers1- Create a list of phone numbers
2- Stratify the phone numbers by health region using the residential postal codes 2- Stratify the phone numbers by health region using the residential postal codes
3- Select phone numbers at random within a health region3- Select phone numbers at random within a health region
4- Repeat the process until the required number of telephone numbers is reached4- Repeat the process until the required number of telephone numbers is reached
CCHS - Sampling of persons CCHS - Sampling of persons
Area frameArea frame SRS of one person aged 12 years of age or older (82% of households)SRS of one person aged 12 years of age or older (82% of households) SRS of two persons aged 12 years of age or older (18%) SRS of two persons aged 12 years of age or older (18%)
RDD / List framesRDD / List frames SRS of one person aged 12 years of age or older SRS of one person aged 12 years of age or older
CCHS - Sampling of persons CCHS - Sampling of persons
Age 1996 LFS * CCHSgroup Census sample simulated
(all persons) sample ( only 1 person)
12-19 13.2 13.7 8.5
20-29 16.4 14.4 14.3
30-44 30.8 28.7 29.1
45-64 25.8 28.0 27.9
65 + 13.8 15.2 20.2
* averaged distribution over 100 repetitions using the May 99 LFS sample* averaged distribution over 100 repetitions using the May 99 LFS sample
CCHS - Representativity of sub-populations CCHS - Representativity of sub-populations
To address users’ needs, two sub-population groups needed larger effective sample sizes:
Youths (12-19 years old) –Decision > Oversample youths by selecting a second person (12-19) in some households based on their composition
Elderlies (65 years old and +)–Decision > Do not oversample - let the general sample selection process address the issue by itself
Sampling strategy based on household compositionSampling strategy based on household composition
Number of persons aged 20 or overNumber of persons aged 20 or over
NumberNumber 00 1 1 2 2 3 3 4 4 5+ 5+of 12-19of 12-19
00 - A A A A B
11 A A C C C B
22 A C C C C C
3+3+ A C C C C C
A:A: SRS of one person aged 12+ SRS of one person aged 12+
B: B: SRS of two persons aged 12+SRS of two persons aged 12+
C:C: SRS of one person in the age group 12-19 SRS of one person in the age group 12-19 andand SRS of one person 20+ SRS of one person 20+
CCHS - Sample Distribution after OversamplingCCHS - Sample Distribution after Oversampling
Age 1996 * CCHS * CCHSgroup Census simulated simulated
sample sample( only 1 person) ( some 2 persons)
12-19 13.2 8.5 14.920-29 16.4 14.3 13.130-44 30.8 29.1 28.145-64 25.8 27.9 26.365 + 13.8 20.2 17.6
* averaged distribution over 100 repetitions using the May 99 LFS sample* averaged distribution over 100 repetitions using the May 99 LFS sample
CCHS - Initial data collection planCCHS - Initial data collection plan
12 monthly samples12 monthly samples 12 collection months + 112 collection months + 1
Area frameArea frame
CAPI CAPI STC field interviewersSTC field interviewers targeted response rate: 90%targeted response rate: 90% anticipated vacancy rate: 13%anticipated vacancy rate: 13%
(09 / 2000 - 08 / 2001) + 09 / 2001(09 / 2000 - 08 / 2001) + 09 / 2001
RDD / List framesRDD / List frames
CATI CATI STC call centresSTC call centres targeted response rate: 85%targeted response rate: 85% telephone hit rate: 15-60%telephone hit rate: 15-60%
CCHS data collection - Observed situationCCHS data collection - Observed situation
Field interviewersField interviewers– workload exceeded field staff capacityworkload exceeded field staff capacity
Call centresCall centres– new collection infrastructurenew collection infrastructure
– unequal allocation of work among call centresunequal allocation of work among call centres
CCHS - Final response ratesCCHS - Final response rates
FieldField Call centresCall centres TotalTotalNFLDNFLD 86.686.6 89.389.3 86.886.8
PEIPEI 87.787.7 82.682.6 84.784.7
NSNS 88.888.8 89.389.3 88.888.8
NBNB 88.488.4 92.492.4 88.588.5
QUEQUE 85.785.7 84.884.8 85.685.6
ONTONT 82.882.8 79.579.5 82.082.0
MANMAN 90.090.0 85.085.0 89.589.5
SASKSASK 87.087.0 85.485.4 86.886.8
ALBALB 85.285.2 84.984.9 85.185.1
BCBC 83.983.9 86.786.7 84.784.7
YUKYUK 79.379.3 95.695.6 82.782.7
NWTNWT 89.689.6 85.485.4 89.289.2
NUNNUN ** 66.366.3 34.634.6 62.562.5
CANCAN 85.185.1 83.183.1 84.784.7
CCHS - Proxy interviewsCCHS - Proxy interviews
Higher number of proxy interviews than expectedHigher number of proxy interviews than expected– ~ 6% instead of 2-3%~ 6% instead of 2-3%
Major consequence: one third of the questionnaire is Major consequence: one third of the questionnaire is missing which could be missing which could be
proble-proble- matic for small health matic for small health regionsregions
Solution : ImputationSolution : Imputation
CCHS - ImputationCCHS - Imputation
3-step strategy3-step strategy– common modules / mental health related optional common modules / mental health related optional
modules / other optional modulesmodules / other optional modules
more than 2,000 imputation classes (region, age, more than 2,000 imputation classes (region, age, sex, questionnaire type, skip patterns, etc…)sex, questionnaire type, skip patterns, etc…)
hot-deck imputation using nearest neighbour hot-deck imputation using nearest neighbour approach according to 12-16 key characteristicsapproach according to 12-16 key characteristics
CCHS - Weighting and EstimationCCHS - Weighting and EstimationThree separate weighting systems:
–Area frame design
–RDD frame design
–List frame design
Several adjustments– non-response (household and person)
– seasonal factor
– etc...
Integration of the two weighting systems based on DeffsCalibration using a one-dimensional poststratification adjustment of ten age/sex poststrata within each health region
Variance estimation : bootstrap re-sampling approach–set of 500 bootstrap weights for each individual
CCHS Weighting StrategyCCHS Weighting Strategy
Area frame Telephone frame
Initial weight (dwelling level) Initial weight (dwelling level)| |
Remove out-of-scope units Remove out-of-scope units| |
Household nonresponse Household nonresponse| |
# of people in hhld (person wgt) No phone lines| |
Person level nonresponse # of people in hhld (person wgt)| |
F inal Area weight Person level nonresponse|
Multiple phone lines|
Final Telephone weight
Weighting & EstimationWeighting & Estimation
Final Area weight Final Telephone weight
Integration|
Seasonal effect|
Post Stratification
(by health region, 10 age-sex groups)|
F inal CCHS master weight
CCHS - Special WeightsCCHS - Special Weights
For various reasons, many other weights are produced
– Quarter 4 special weight
– PEI special weight
– Share weights (master, Q4 and PEI special)
– Link weights (master, Q4 and PEI special)
Sampling ErrorSampling Error
Difference in estimates obtained from a sample as Difference in estimates obtained from a sample as compared to a censuscompared to a census
The extent of this error depends on four factors:The extent of this error depends on four factors:– sample sizesample size
– variability of the characteristic of interestvariability of the characteristic of interest
– sample designsample design
– estimation method estimation method
Generally, the sampling error decreases as the size of the Generally, the sampling error decreases as the size of the sample increasessample increases
Sampling ErrorSampling Error
Measure of precision, reliability of the estimatesMeasure of precision, reliability of the estimates
– Variance (standard deviation)Variance (standard deviation)
– Coefficient of variationCoefficient of variation
• Standard deviation of estimate x 100% / estimate itself Standard deviation of estimate x 100% / estimate itself
• CV allows comparison of precision of estimates with CV allows comparison of precision of estimates with different scalesdifferent scales
– Example:Example:
• 24% of population are daily smokers, std dev. = 0.00324% of population are daily smokers, std dev. = 0.003
• CV=0.003/0.24 x 100%=1.25%CV=0.003/0.24 x 100%=1.25%
Sampling Variability GuidelinesSampling Variability Guidelines
Type of estimateType of estimate CVCV GuidelinesGuidelines
AcceptableAcceptable 0.0-16.5 0.0-16.5 General unrestricted releaseGeneral unrestricted release
MarginalMarginal 16.6-33.3 16.6-33.3 General unrestricted release but withGeneral unrestricted release but with warning warningcautioning users of the highcautioning users of the high sampling variablitity. sampling variablitity. Should Should
be identified by letter M.be identified by letter M.
UnacceptableUnacceptable > 33.3> 33.3 No release.No release.
Should be flagged with letter U.Should be flagged with letter U.
Sampling ErrorSampling Error
Measuring sampling error for complex sample designs:Measuring sampling error for complex sample designs:
– Simple formulas not availableSimple formulas not available
– Most software packages do not incorporate design Most software packages do not incorporate design effect (and weights adjustments) appropriately for effect (and weights adjustments) appropriately for calculationscalculations
– Solution for CCHS: the Bootstrap methodSolution for CCHS: the Bootstrap method
Bootstrap methodBootstrap method
Principle:Principle:
– You want to estimate how precise is your estimation of the You want to estimate how precise is your estimation of the number of smokers in Canadanumber of smokers in Canada
– You could draw 500 totally new CCHS samples, and compare You could draw 500 totally new CCHS samples, and compare the 500 estimations you would get from these samples. The the 500 estimations you would get from these samples. The variance of these 500 estimations would indicate the variance of these 500 estimations would indicate the precision.precision.
– Problem: drawing 500 new samples is $$$Problem: drawing 500 new samples is $$$
– Solution: Use your sample as a population, and take many Solution: Use your sample as a population, and take many smaller subsamples from it.smaller subsamples from it.
Starting point: Full data file (example presented for a given stratum)ID Wgt ClusterA 10 1B 10 1C 10 1D 10 2E 10 2F 10 2G 10 3H 10 3I 10 4J 10 4
Select n-1 clusters among n within each stratum (with replacement)ID Wgt Cluster B1 = # of times the cluster is selectedA 10 1 1B 10 1 1C 10 1 1D 10 2 1E 10 2 1F 10 2 1G 10 3 0H 10 3 0I 10 4 1J 10 4 1
Repeat the process 500 times (*BOOTSTRAP REPLICATES*)ID Wgt Cluster B1 B2 . . . . . . . . . . . . B500A 10 1 1 0 3B 10 1 1 0 3C 10 1 1 0 3D 10 2 1 1 0E 10 2 1 1 0F 10 2 1 1 0G 10 3 0 0 0H 10 3 0 0 0I 10 4 1 2 0J 10 4 1 2 0
Apply the survey weight (Wgt) (*BOOTSTRAP WEIGHTS*)ID Wgt Cluster B1 B2 . . . . . . . . . . . . B500A 10 1 10 0 30B 10 1 10 0 30C 10 1 10 0 30D 10 2 10 10 0E 10 2 10 10 0F 10 2 10 10 0G 10 3 0 0 0H 10 3 0 0 0I 10 4 10 20 0J 10 4 10 20 0
Adjust for the fact that we picked n-1 among n (factor = n / n-1 = 1.33)ID Wgt Cluster B1 B2 . . . . . . . . . . . . B500A 10 1 13 0 40B 10 1 13 0 40C 10 1 13 0 40D 10 2 13 13 0E 10 2 13 13 0F 10 2 13 13 0G 10 3 0 0 0H 10 3 0 0 0I 10 4 13 27 0J 10 4 13 27 0
USING THE BOOTSTRAP WGTS: Estimate the number of smokersID Wgt Cluster Smoke B1 B2 . . . . . . . . . . . . B500A 10 1 X 13 0 40B 10 1 X 13 0 40C 10 1 13 0 40D 10 2 13 13 0E 10 2 13 13 0F 10 2 13 13 0G 10 3 X 0 0 0H 10 3 0 0 0I 10 4 13 26 0J 10 4 X 13 27 0
40 39 27 . . . . . . . . . . . . 80
Bootstrap methodBootstrap method
T = 40Var = (Bi - B)2 / 499
How CCHS Bootstrap weights are createdHow CCHS Bootstrap weights are created(the secret is now revealed!!!)(the secret is now revealed!!!)
Bootstrap MethodBootstrap Method
How Bootstrap replicates are built (cont’d)How Bootstrap replicates are built (cont’d) The “real” recipeThe “real” recipe
1- Subsampling of clusters (SRS) within strata1- Subsampling of clusters (SRS) within strata
2- Apply (initial design) weight2- Apply (initial design) weight
3- Adjust weight for selection of n-1 among n3- Adjust weight for selection of n-1 among n
4- Apply all standard weight adjustments (nonresponse, 4- Apply all standard weight adjustments (nonresponse, share, etc.)share, etc.)
5- Post-stratification to population counts5- Post-stratification to population counts The bootstrap method intends to mimic the same approach The bootstrap method intends to mimic the same approach
used for the sampling and weighting processesused for the sampling and weighting processes
Bootstrap MethodBootstrap Method
Sampling weight vs. Bootstrap weightsSampling weight vs. Bootstrap weights
– Sampling weight used to compute the Sampling weight used to compute the estimationestimation of a of a
parameter (e.g.: number of smokers)parameter (e.g.: number of smokers)
– Bootstrap weights used to compute the Bootstrap weights used to compute the precisionprecision of the of the
estimation (e.g.: the CV of the number of smokers estimation (e.g.: the CV of the number of smokers
estimation)estimation)
CCHS - Data Dissemination StrategyCCHS - Data Dissemination Strategy
Wide range of users and capacity–136 health regions
–13 provincial/territorial Ministries of Health
–Health Canada and CIHI
–Internal STC analysts
–Academics
–Others
Data products–Microdata
–Analytical products (Health Reports, How Healthy are Canadians, etc…)
–Tabular statistics (ePubs, Cansim II, community profiles, etc…)
–Client support (head and regional offices, CCHS website, workshops, etc…)
CCHS - Access to microdataCCHS - Access to microdata
Master file–all records, all variables
•Statistics Canada
•university research data centres
•remote access
Share / Link files–respondents who agreed to share / link
•provincial/territorial Ministries of Health
•health regions (through the STC third-party share agreement)
Public Use Microdata File (PUMF)–all records, subset of variables with collapsed response categories
•free for 136 health regions
•cost recovery for others
CCHS - Overview of Cycle 1.2CCHS - Overview of Cycle 1.2
Produce provincial cross-sectional estimates from a sample of 30,000 respondents
Area frame sample only / one person per household
CAPI only
90-100 minute in-depth interviews on mental health and well-being based on WMH2000 questionnaire
Scheduled to begin collection in May 2002
CCHS - Future PlansCCHS - Future Plans
Same two-year cycle approach:–health region level survey starting in January 2003
–provincial level survey starting in January 2004
New consultation process with provincial and regional authorities
Flexible sample designs (adaptable to regional needs)
Development of an in-depth nutrition focus content (Cycle 2.2)
CCHS Web siteCCHS Web site
www.statcan.ca/health_surveyswww.statcan.ca/health_surveys
www.statcan.ca/enquetes_santéwww.statcan.ca/enquetes_santé
Contacts in MethodologyContacts in Methodology
Yves Béland:Yves Béland:[email protected]@statcan.ca
François Brisebois: François Brisebois: [email protected]@statcan.ca