A unit-error theory for register-based household statistics

The next round of census will be completely register-based in all the Nordic countries. Household is a key statistical unit in this context, which however does not exist as such in the administrative registers available, and needs to be created by the statistical agency based on the various information available in the statistical system. Errors in such register households are thus unavoidable, and will propagate to various induced household statistics. In this paper we outline a unit-error theory which provides a framework for evaluating the statistical accuracy of these register-based household statistics, and illustrate its use through an application to the Norwegian register household data.