Longitudinal child data: What can be gained by linking administrative data and cohort data?

Abstract

Linked administrative data sets are an emerging tool for studying the health and well-being of the population. Previous papers have described methods for linking Canadian data, although few have specifically focused on children, nor have they described linkages between tax outcomes and a cohort of children who are particularly at risk for poor outcomes in adulthood. This paper describes a probabilistic linkage performed by Statistics Canada linking the Montreal Longitudinal Experimental Study (MLES) and the Quebec Longitudinal Study of Kindergarten Children (QLSKC) survey cohorts and administrative tax data from 1992 through 2012. The number of valid cases in the original cohort file with valid tax records was approximately 84%. Rates of false positives, false negatives, sensitivity, and specificity of the linkage were all acceptable. Using the linked file, the relationship of childhood behavioural indicators to adult outcomes including earnings, total household income, and use of social assistance can be investigated in future studies. Innovative methods for creating longitudinal datasets on children can enhance existing data by providing information on a variety of outcomes without an increase in response burden, additional costs, or additional data collection. These can increase the longevity of survey data by examining long-term outcomes associated with early childhood characteristics as well as interventions to enhance child outcomes.