People and places: Understanding geographical accuracy in administrative data from the census and healthcare systems

Administrative systems such as health care registration are of increasingimportance in providing information for statistical, research, and policypurposes. There is thus a pressing need to understand better the detailedrelationship between population characteristics as recorded in such systems andconventional censuses. This paper explores these issues using the uniqueNorthern Ireland Longitudinal Study (NILS). It takes the 2001 Census enumerationas a benchmark and analyses the social, demographic and spatial patterns ofmismatch with the health register at individual level. Descriptive comparison isfollowed by multivariate and multilevel analyses which show that approximately25% of individuals are reported to be in different addresses and that age,rurality, education, and housing type are all important factors. This level ofmismatch appears to be maintained over time, as earlier migrants who updatetheir address details are replaced by others who have not yet done so. In somecases, apparent mismatches seem likely to reflect complex multi-address livingarrangements rather than data error.