StatVillage

How StatVillage was created

The Data

The data for StatVillage came from the Public Use Microdata Files. (Source: Statistics Canada / 1991 census catalogue. (STC 93-302 p. 107)

The 1991 Census Public Use Microdata Files (PUMFs) contain samples of anonymized responses to the 1991 Census questionnaire (long form, 2B). The files have been carefully scrutinized to ensure the complete confidentiality of the individual responses. Three files are available: the Individual file, the Household and Housing file, and the Family file. The PUMFs enable the development of statistical information about Canadians, the families and households to which they belong, and the dwellings in which they live.

Microdata files give users access to unaggregated data. However, to ensure the anonymity of the respondents, geographic identifiers have been restricted to the provinces/territories and large metropolitan areas.

The PUMF on Household and Housing was first scanned to select records belonging to Vancouver, BC, Canada. Then those households living in apartment building over 5 stories were eliminated (because the layout of StatVillage doesn't have any large apartment buildings).

Finally, an approximate 1/12 sample of the remaining records was selected and the appropriate fields selected for StatVillage.

The data was approximately sorted by total income and assigned to individual units from top to bottom and left to right.

The Village

The Village consists of a fill-in form written in HTML. Because of the large number of elements, a SAS program was written to generate the HTML code.

The source for the fill-in form can be viewed using the WWW-browser.

What happens when the user submits a form

The form is passed to a PERL script which extracts the block and unit numbers selected. The script then selects the appropriate records, creates an HTML page and returns the page to the WWW-browser.