Survey Reweighting for Tax Microsimulation Modelling

This paper describes a range of ‘minimum distance' methods used to compute new weights for large cross-sectional surveys used in microsimulation modelling. Extraneous information about a range of population variables is used for calibration purposes. An iterative solution procedure is described and numerical examples are given, involving comparisons among alternative distance functions. An application to the New Zealand Household Economic Survey (HES) is reported.