On the Bias in Gross Labour Flow Estimates Due to Nonresponse and Misclassification

Abstract: I evaluate and compare the bias due to nonresponse and misclassification in the sample gross labour flow estimates from the Norwegian Labour Force Survey (LFS). These help also to explain the level and net change estimates from the same survey. The main conclusions are the following: (a) the overall labour market stability, i.e., the proportion of people without change in status, should be boosted after adjusting for both nonresponse and misclassification, (b) neither nonresponse nor misclassification affects the net change estimates, and (c) misclassification has very little effect on the level estimation of the characteristics “employed”, “unemployed” and “not in the labour force”