Within the urban stratum, two stages of sampling were used. In the first stage, households were selected systematically with probability proportional to size. The size measure was constructed in terms of the number of adults in a household, using a maximum cap at four for the base sample and at three for supplementary samples. During the second stage, a simple random sample algorithm was used by the CAPI application to select an individual from the demographic roster of eligible household adults. Three stages were used to select the sample in the rural stratum. In the first stage, primary sampling units (PSUs) were selected with probability proportional to population size as measured by the total number of adults for each sample’s survey population in the 2001 Census. The second and third stages for the rural stratum repeated the same methodology employed in the two-stage selection for the urban stratum.
Each province had a base sample that covered the general population. Additionally, provincial ministries and other organisations sponsored supplementary samples to increase the base or to target specific subpopulations. Table C2 shows the expected number of respondents in each sample: the base, youth (ages 16 to 24 in Quebec and 16 to 29 in British Columbia), adults aged 25 to 64 in Quebec, linguistic minorities (English in Quebec and French elsewhere), recent and established immigrants, urban aboriginals, and residents (specifically Inuit and non-Inuit for Nunavut) of the territories.
Table C2
| Jurisdiction | Base sample |
Youth1 | Adult2 | Language | Immigrant | Aboriginal populations |
Non- Aboriginal populations3 |
Total |
|---|---|---|---|---|---|---|---|---|
| Newfoundland and Labrador | 1,350 | … | … | … | … | … | … | 1,350 |
| Prince Edward Island | 650 | … | … | … | … | … | … | 650 |
| Nova Scotia | 1,350 | … | … | … | … | … | … | 1,350 |
| New Brunswick | 650 | … | 760 | … | … | … | 1,410 | |
| Quebec | 1,110 | 815 | 1,885 | 570 | 270 | … | … | 4,650 |
| Ontario | 2,690 | … | … | 3,000 | 1,060 | … | … | 5,750 |
| Manitoba | 1,350 | … | … | 450 | … | 700 | … | 2,500 |
| Saskatchewan | 605 | … | … | … | … | 700 | … | 1,350 |
| Alberta | 1,350 | … | … | … | 70 | … | … | 1,420 |
| British Columbia | 1,350 | 490 | … | … | 280 | … | … | 2,120 |
| Yukon | … | … | … | … | … | 700 | 700 | 1,400 |
| Northwest Territories | … | … | … | … | … | 450 | 450 | 900 |
| Nunavut | … | … | … | … | … | 700 | 180 | 880 |
| Canada | 11,500 | 1,305 | 1,885 | 4,780 | 1,680 | 3,240 | 1,340 | 25,730 |
1. Youth = 16 to 24 in Quebec, 16 to 29 in British Columbia.
2. Adults are defined as being 25 to 64.
3. Non-Aboriginal population in Nunavut is defined as anyone who is Non-Inuit.
… Not applicable.
Source: International Adult Literacy and Skills Survey, 2003.
After adjusting for non-response and the anticipated mobility of the target sub-populations, an overall sample size of over 40,000 was achieved. The samples were selected sequentially, one after another, starting with the base sample. After the selection of each sample, chosen households were removed from the frame before the next selections, thereby making the samples dependent. The sequential selection of multiple samples in a province can be viewed as multiple phase sampling.