joint canada/u.s. health survey catherine simile, national center for health statistics patrice...
TRANSCRIPT
![Page 1: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/1.jpg)
Joint Canada/U.S. Health Survey
Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada
Ed Rama, Statistics Canada
NCHS 2002 Data Users ConferenceJuly 15-17, 2002Washington, DC
![Page 2: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/2.jpg)
Sample Parameters
Target Population: Household residents aged 18 and older in Canada and in United States
Produce reliable estimates at the national level for 6 domains :
– 3 age groups (18-44, 45-64, 65 and older)– by gender (F, M)
![Page 3: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/3.jpg)
Sample Design
Sample size: – about 5,000 respondents in the U.S.– about 3,500 respondents in Canada
Random digit dialing (RDD) method used: Telephone numbers are randomly selected 1 respondent per household (18 and older) is then selected
![Page 4: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/4.jpg)
Why use the RDD method?
The most similar method existing in both countries
Simple method Less expensive
Limitations with RDD: Some households don’t have telephone
– 4% - 5% in the U.S. , less than 2% in Canada
The age and sex of the household members are unknown beforehand
Sample Design
![Page 5: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/5.jpg)
Sample Design
Selection process:
List all the household members
When 65 and older are presentrandomly select the respondent among the 65 and older only
When no 65 and older randomly select the respondent among all the members
![Page 6: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/6.jpg)
Why increasing the probabilities of selection for the 65 and older ?
The group “65 and older” is less common in the population (in about 13% of the households)
Not enough “65 and older” in the sample
Sample Design
![Page 7: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/7.jpg)
Sample Design
Sample Composition - Canada (similar in the U.S.)
Domain Population(%)
Sample (%)
18-44 yrs MaleFemale
25.8%25.6%
25.1%25.1%
45-64 yrs MaleFemale
14.7%15.2%
14.3%14.7%
65 and older MaleFemale
7.3%11.4%
9.3%12.1%
![Page 8: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/8.jpg)
Data Collection
• Computer Assisted Telephone Interviewing (CATI)
• All interviews conducted from Statistics Canada regional offices (Toronto, Vancouver, Edmonton and Montreal)
• Interviews in 3 languages (Eng., Spanish, French)
• 20 minutes interviews
• Collection period: November 2002 to March 2003
• Targeted response rate: 75%
• No proxy interviews
![Page 9: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/9.jpg)
Public Use File to be released in the fall of 2003. (No Master file, for confidentiality reasons)
A users manual and initial publication outlining major findings of the survey will be released
Information about the survey and the data will be made available on the NCHS and STC websites.
Data Release
![Page 10: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/10.jpg)
Weighting & Estimation Estimation relates sample back to
population Must use weights in calculation of estimates
to correctly draw conclusions about pop’n of interest
Sampling weight is related to the probability of selecting a unit in the sample
Respondents selected with unequal probabilities therefore have varying weights
![Page 11: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/11.jpg)
Weighting & Estimation
Same method for both countries, but applied separately for each
Basic weight: inverse of the probability of selecting the telephone line
Some weight adjustments:• households with more than one phone line• non-response (household and respondent levels)• etc…
Post-stratify to 2002 population estimates based on last Census counts
![Page 12: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/12.jpg)
Effect of Weighting
Comparison of males and females who reported being in excellent or very good health:
Weighted difference: 65.3–61.6 = 3.7%Unweighted difference: 62.6–60.8 = 1.8%
Source: National Population Health Survey, Statistics Canada
![Page 13: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/13.jpg)
Sampling Error
Measure of precision, reliability of the estimates Variance (standard deviation) Coefficient of variation
Standard deviation of estimate x 100% / estimate itself
Example: 24% of population are daily smokers, std dev. =
0.003 CV=0.003/0.24 x 100%=1.25%
![Page 14: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/14.jpg)
Sampling Variability Guidelines
Type of estimate CV Guidelines
Acceptable 0.0-16.5 General unrestricted release
Marginal 16.6-33.3 General unrestricted release but withwarning cautioning users of the highsampling variablitity.
Unacceptable > 33.3 No release.
![Page 15: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/15.jpg)
CV Look-up Tables—Example National Population Health Survey ‑ 1996/1997
Approximate Sampling Variability Tables for Ontario Health Area:OTTAWA CARLETON ‑ Selected members
NUMERATOR OF ESTIMATED PERCENTAGE PERCENTAGE ('000) 0.1% 1.0% 2.0% 5.0% 10.0% 15.0% 20.0% 25.0% 30.0% 35.0% 40.0% 50.0% 70.0% 90.0%
1 ******** 48.6 48.4 47.6 46.4 45.0 43.7 42.3 40.9 39.4 37.8 34.5 26.8 15.5 2 ******** 34.4 34.2 33.7 32.8 31.9 30.9 29.9 28.9 27.9 26.8 24.4 18.9 10.9 3 ******** 28.1 27.9 27.5 26.8 26.0 25.2 24.4 23.6 22.7 21.9 19.9 15.5 8.9 4 ******** 24.3 24.2 23.8 23.2 22.5 21.9 21.2 20.4 19.7 18.9 17.3 13.4 7.7 5 ******** 21.7 21.6 21.3 20.7 20.1 19.5 18.9 18.3 17.6 16.9 15.5 12.0 6.9 6 ******** 19.8 19.7 19.4 18.9 18.4 17.8 17.3 16.7 16.1 15.5 14.1 10.9 6.3 7 ******** 18.4 18.3 18.0 17.5 17.0 16.5 16.0 15.5 14.9 14.3 13.1 10.1 5.8 8 **************** 17.1 16.8 16.4 15.9 15.5 15.0 14.5 13.9 13.4 12.2 9.5 5.5 9 **************** 16.1 15.9 15.5 15.0 14.6 14.1 13.6 13.1 12.6 11.5 8.9 5.2 10 **************** 15.3 15.1 14.7 14.2 13.8 13.4 12.9 12.5 12.0 10.9 8.5 4.9 ... ... 300 **************************************************************************************** 2.0 1.5 0.9 350 **************************************************************************************** 1.8 1.4 0.8 400 ************************************************************************************************ 1.3 0.8 450 ************************************************************************************************ 1.3 0.7 500 ************************************************************************************************ 1.2 0.7
NOTE: FOR CORRECT USAGE OF THESE TABLES PLEASE REFER TO MICRODATA DOCUMENTATION
![Page 16: Joint Canada/U.S. Health Survey Catherine Simile, National Center for Health Statistics Patrice Mathieu, Statistics Canada Ed Rama, Statistics Canada NCHS](https://reader036.vdocument.in/reader036/viewer/2022082517/56649dc05503460f94ab4cb7/html5/thumbnails/16.jpg)
CV Look-up Tables
Appoximate
Can only use for categorical variables, and for estimations of totals and proportions
Provided with PUF
Easy to use
The CVs in the table take into account the design effect and the weights adjustments