| Sumario: | Performing longitudinal analysis of socio‐economic change in small‐area spatial units such as census tracts presents several methodological complications and requires significant data preparation. Unit boundaries are revised each census year because of changes in population and delineation methodologies. This limits cross‐year comparison since data are not representative of the same spatial units. To address these problems, we have developed an innovative procedure to reduce error when comparing tract‐level data across census years by apportioning data to the same areal units. This paper describes the methods used to create the Canadian Longitudinal Tract Database. Our procedure is a combination of map‐matching techniques, dasymetric overlays, and population‐weighted areal interpolation. The output is a set of tables with apportionment weights pertaining to pairs of unique boundary identifiers across census years, which can be linked with census data or other data with census identifiers that require longitudinal comparison. Key Messages: Neighbourhood change research is challenged by census boundaries being revised each census year.This paper describes the creation of a longitudinal spatial database of census tracts in Canada, bridging tract‐level data for the 1971–2016 quinquennial censuses to a common set of boundaries.Methodology includes map‐matching, dasymetric overlays, and population‐weighted areal interpolation in order to minimize error when boundaries change over time.
|
|---|