Back

Pseudo-neighbourhoods: Approximating the Social Characteristics of Saskatoon's Locally-Defined Neighbourhoods using Statistics Canada's Census Profiles

Marouzi, A.; Plante, C.; Neudorf, C.

2023-08-23 public and global health
10.1101/2023.08.18.23294274 medRxiv
Show abstract

There is a growing desire to use social data to support local evidence-based health planning and decision-making. However, the geographic boundaries which social data are disseminated for do not usually align exactly with boundaries used by local health organizations. In this paper, we propose a method we call "pseudo-geography" to estimate counts for locally-defined geographic boundaries using data on smaller spatial units. We compared six different pseudo-geography methods, using data in Saskatoon, and identified the most accurate one, which incorporates the area-weighted spatial join technique. We further found that the pseudo-geography method can be refined by eliminating the areas with few or no residents before carrying out any spatial joins. We expect this method to be more accurate in larger cities and when the ratio of the locally-defined area to the smaller spatial units gets larger.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.