The Effects of Using Administrative Registers in Economic Short Term Statistics: The Norwegian Labour Force Survey as a Case Study

Abstract

ABSTRACT: In the case of a single survey at one point in time, it is well known that combining administrative registers with survey data often substantially improves the quality of estimation. However, in short term statistics it is as important to measure changes over time as it is to measure the overall level. Using data from the Norwegian Labour Force Surveys (LFS) and administrative registers, we demonstrate in this article that the use of registers has little or no additional effect on the accuracy of estimates of change based on the panel part of the survey data, neither in terms of the sampling variance nor in the bias introduced by nonresponse. The main reason is that the administrative register available is not sufficiently up-to-date at the time of production. Indirectly, however, the use of registers can improve the estimator of change through the rotation design of the surveys, since it allows us to deploy a higher overlap proportion in the sample without seriously reducing the accuracy of the level estimates. We believe that these findings are relevant to short term statistics in general, especially when the registers suffer from delays.

KEYWORDS: Poststratification; estimation of level and change; survey design.