Reconciling reports: modelling employment earnings and measurement errors using linked survey and administrative data

Jenkins, Stephen P. ORCID: 0000-0002-8305-9774 and Rios-Avila, Fernando (2023) Reconciling reports: modelling employment earnings and measurement errors using linked survey and administrative data. Journal of the Royal Statistical Society. Series A: Statistics in Society, 186 (1). pp. 110-136. ISSN 0964-1998

Text (Reconciling reports: modelling employment earnings and measurement errors using linked survey and administrative data) - Published Version Available under License Creative Commons Attribution. Download (830kB)

• Author

Abstract

We develop and apply new statistical models for linked survey and administrative data on employment earnings that generalize those of Kapteyn and Ypma (Journal of Labor Economics, 2007). Our models incorporate four types of measurement error: mean-reverting measurement error in the survey data; ‘reference period’ error (mismatch between survey and administrative data definitions); error in the linking of survey and administrative data; and mean-reverting measurement error in the administrative data. In addition, we allow error distributions to differ with individual characteristics, which improves model fit and allows us to investigate substantive hypotheses about factors associated with error bias and variance. Using individual-level data from the 2011/12 Family Resources Survey linked with administrative data based on Pay As You Earn records (P14 data) for the same individuals, we contribute the first UK evidence to a field dominated by findings about the USA. We show that measurement errors are pervasive, but the four types are quite different in nature. We also document substantial heterogeneity in each of the error distributions.

Item Type:	Article
Official URL:	https://academic.oup.com/jrsssa
Additional Information:	© 2022 The Author(s).
Divisions:	Social Policy
Subjects:	H Social Sciences > HA Statistics
Date Deposited:	31 Oct 2022 11:48
Last Modified:	18 Nov 2024 08:21
URI:	http://eprints.lse.ac.uk/id/eprint/117213

Actions (login required)

View Item