Dependent interviewing: a remedy or a curse for measurement error in surveys?

Longitudinal surveys often rely on dependent interviewing (DI) to lower thelevels of random measurement error in survey data and reduce the incidenceof spurious change. DI refers to a data collection technique that incorporatesinformation from prior interview rounds into subsequent waves. While thismethod is considered an eective remedy for random measurement error,it can also introduce more systematic errors, in particular when respondentsare rst reminded of their previously provided answer and then askedabout their current status. The aim of this paper is to assess the impactof DI on measurement error in employment mobility. We take advantageof a unique experimental situation that was created by the roll-out of dependentinterviewing in the Dutch Labour Force Survey (LFS). We applyHidden Markov Modeling (HMM) to linked LFS and Employment Register(ER) data that cover a period before and after dependent interviewing wasabolished, which in turn enables the modeling of systematic errors in theLFS data. Our results indicate that DI lowered the probability of obtainingrandom measurement error but had no signi cant eect on the systematiccomponent of the error. The lack of a signi cant eect might be partiallydue to the fact that the probability of repeating the same error was extremelyhigh at baseline (i.e when using standard, independent interviewing);therefore the use of DI could not increase this probability any further.