Alternative Imputation Models For Wage Related Data Collected From Establishment Surveys

Carl Barsky, James A. Buszuwski, Lawrence R. Ernst, Michael K. Lettau, Mark A. Loewenstein, Brooks Pierce, Chester H. Ponikowski, James Smith, and Sandra A. West


This study was undertaken to determine imputation methods for data collected from the National Compensation Survey (NCS), conducted by the Bureau of Labor Statistics (BLS). In this paper alternative regression models are compared for item nonresponse of wage related data, which are collected from establishments by detailed occupation level. The surveys involved are of a longitudinal nature and two separate cases of item nonresponse are considered. The first case involves establishment nonresponse at initiation in the survey, and the second case involves an update time for the establishment. The empirical study tests various regression models on real survey data. The nonresponse patterns in our tests were simulated using observed patterns on current NCS data.