Measurement error in earnings data: Using a mixture model approach to combine survey and register data

E. Meijer, S. Rohwedder, T. J. Wansbeek

Onderzoeksoutput: ArticleAcademicpeer review

20 Citaten (Scopus)


Survey data on earnings tend to contain measurement error. Administrative data are superior in principle, but are worthless in case of a mismatch. We develop methods for prediction in mixture factor analysis models that combine both data sources to arrive at a single earnings figure. We apply the methods to a Swedish data set. Our results show that register earnings data perform poorly if there is a (small) probability of a mismatch. Survey earnings data are more reliable, despite their measurement error. Predictors that combine both and take conditional class probabilities into account outperform all other predictors. This article has supplementary material online.

Originele taal-2English
Pagina's (van-tot)191-201
Aantal pagina's11
TijdschriftJournal of Business & Economic Statistics
Nummer van het tijdschrift2
StatusPublished - apr.-2012

Citeer dit