TY - JOUR
T1 - Measuring temporary employment. Do survey or register data tell the truth?
AU - Pavlopoulos, D.
AU - Vermunt, J.K.
PY - 2015
Y1 - 2015
N2 - One of the main variables in the Dutch Labour Force Survey is the variable measuring whether a respondent has a permanent or a temporary job. The aim of our study is to determine the measurement error in this variable by matching the information obtained by the longitudinal part of this survey with unique register data from the Dutch Institute for Employee Insurance. Contrary to previous approaches confrontingsuch datasets, we take into account that also register data are not error-freeand that measurement error in these data is likely to be correlated over time. Morespecifically, we propose the estimation of the measurement error in these two sourcesusing an extended hidden Markov model with two observed indicators for the typeof contract. Our results indicate that none of the two sources should be consideredas error-free. For both indicators, we find that workers in temporary contracts areoften misclassified as having a permanent contract. Particularly for the register data,we find that measurement errors are strongly autocorrelated, as, if made, they tendto repeat themselves. In contrast, when the register is correct, the probability of anerror at the next time period is almost zero. Finally, we find that temporary contractsare more widespread than the Labour Force Survey suggests, while transitionrates between temporary to permanent contracts are much less common than bothdatasets suggest.
AB - One of the main variables in the Dutch Labour Force Survey is the variable measuring whether a respondent has a permanent or a temporary job. The aim of our study is to determine the measurement error in this variable by matching the information obtained by the longitudinal part of this survey with unique register data from the Dutch Institute for Employee Insurance. Contrary to previous approaches confrontingsuch datasets, we take into account that also register data are not error-freeand that measurement error in these data is likely to be correlated over time. Morespecifically, we propose the estimation of the measurement error in these two sourcesusing an extended hidden Markov model with two observed indicators for the typeof contract. Our results indicate that none of the two sources should be consideredas error-free. For both indicators, we find that workers in temporary contracts areoften misclassified as having a permanent contract. Particularly for the register data,we find that measurement errors are strongly autocorrelated, as, if made, they tendto repeat themselves. In contrast, when the register is correct, the probability of anerror at the next time period is almost zero. Finally, we find that temporary contractsare more widespread than the Labour Force Survey suggests, while transitionrates between temporary to permanent contracts are much less common than bothdatasets suggest.
M3 - Article
SN - 0714-0045
VL - 41
SP - 197
EP - 214
JO - Survey Methodology
JF - Survey Methodology
IS - 1
ER -