Complementing Data Gaps on Wages in the Labour Force Survey Data Set: Evidence from Poland
Loading...
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Technická Univerzita v Liberci
Technical university of Liberec, Czech Republic
Technical university of Liberec, Czech Republic
Abstract
Due to the low level of quality of the Labour Force Survey (LFS) data set, studies devoted to matching the LFS data with data from alternative sources are frequent. In this paper, we propose a novel method of complementing data gaps on wages in the Labour Force Survey data set. The method is based on estimataing the parameters of the multilevel model explaining wages on the basis of the Structure of Earnings Survey (SES) data set. In such a way, we identify the impact of individual characteristics and enterprise-level features on wages. We also find evidence of random differences between the wages of workers from different professional groups. The relative importance of consecutive groups of variables is evaluated on the basis of the estimates of the parameters of the full model and reduced models. The results of the estimation of the parameters are in line with expectations. The estimates of parameters and predictions of random effects are used in order to calculate the theoretical wages of individuals who do not report wages in the Labour Force Survey. When the predicted wages are compared with the observed ones, some discrepancies are observed. Rationales for these discrepancies are provided. Therefore, the use of a correction factor is proposed. Correction factors are provided for different features of workers and different features of enterprises. The use of the microeconometric multilevel model, as well as the correction factor, leads to reasonable wage estimates of workers not reporting them in the Labour Force Survey. The proposed method may be used in order to complement data gaps on wages for other EU countries.
Description
Subject(s)
LFS, SES, microeconometrics, mixed-effects model, data gaps
Citation
ISSN
1212-3609