Misclassification errors from postal code-based geocoding to assign census geography in Nova Scotia, Canada

Abstract

OBJECTIVES: Postal codes are often the only available geographic identifiers in many sources of health data in Canada. In order to conduct geographic analyses, postal codes are routinely geocoded to census geography to link to ecological data. Despite common use of this method, the extent of geographic misclassification errors is poorly understood. We estimated misclassification errors in the geocoding of postal codes to assign census geography in Nova Scotia, Canada. METHODS:We examined differences between counts and match rates for postal-code geocoded and actual locations of buildings in Nova Scotia at two census administrative area levels: dissemination areas (DAs) and census subdivisions (CSDs). Actual locations were based on the data collected by the provincial government containing actual latitude/longitude of buildings. Variation in misclassification by rurality, using Statistics Canada's classification, was also assessed. RESULTS:Outside two urban areas (Halifax Metro and Sydney) which had <10% differences in counts, many DAs had >30% differences. Match rates showed similar patterns, with the vast majority of non-urban DAs having <40% match rates. Even in major urban areas, 10% of DAs had large misclassification errors. Misclassification errors at the CSD level were still too great to estimate counts or rates without further area aggregation.CONCLUSION: Routine use of postal code geocoding should be replaced with geocoding of location information using additional identifiers such as civic addresses or latitude and longitude. If data holders did this in-house before providing data to researchers, the accuracy and capacity of geographic analysis would be enhanced while protecting confidentiality.KEY WORDS: Geocoding; postal code; data linkage; small-area analysis; population health La traduction du résumé se trouve à la fin de l'article.

Urban-Rural Differences in Cardiac Arrest Outcomes: A Retrospective Population-Based Cohort Study

“…Rural areas are classified as all areas that are outside of population centres. 23 , 24 Briefly, population-centre boundaries are delineated using the spatial unit of “dissemination areas,” and a population centre is continuous when it is adjacent to other population centres that are less than 2 kilometres away by road. 24 …”

“…The relationship between Utstein process elements (response time and defibrillation) and survival were used to assess urban-rural differences 7,21,22 Data Analysis Population Centre Definition: The use of publicly available 2016 census data co-opts the Canadian census definition for population centre of at least 1,000 and a population density of 400 persons or more per square kilometre. Rural areas are classified as all areas outside population centres 23,24 . Briefly, population centre boundaries are delineated using the spatial unit of Dissemination Areas (DA) and a population centre is continuous when adjacent to other population centres that are less than 2 kilometers away by road 24 .…”

Potential of community-based risk estimates for improving hospital performance measures and discharge planning

“…FSAs also provide a reasonable approximation to meaningful communities and neighbourhoods without reliance of geocoding postal codes to other geographical entities, such as census geography, which has been shown to result in considerable allocation error. 34 …”

“…FSAs also provide a reasonable approximation to meaningful communities and neighbourhoods without reliance of geocoding postal codes to other geographical entities, such as census geography, which has been shown to result in considerable allocation error. 34 To adjust for community variation in patient case-mix, models included fixed effects for age-sex groups, Elixhauser comorbidity index score, percentage of time spent in the community during the last year of life, indicator variables for 25 different individual health conditions (see online supplemental appendix 2) and total number of health conditions. Persons in their last year of life are at increased risk of unplanned hospitalisations, 35 and thus proximity to death was accounted for in our model.…”