Weighting Adjustment Techniques

Abstract

The weighting techniques can attempt to reduce the bias due to self-selection. The principles of weighting adjustment are closely related to the concept of representativity. This chapter describes several weighting techniques. It starts with the simplest and most commonly used one: post-stratification. Next, generalized regression estimation is described, which is more general than post-stratification. This technique can be applied in situations where the auxiliary information is inadequate for post-stratification. Furthermore, raking ratio estimation is discussed as an alternative for generalized regression estimation. Also, an introduction into calibration is provided. This can be seen as an even more general theoretical framework for adjustment weighting that includes generalized regression estimation and raking ratio estimation as special cases. Post-stratification, linear weighting, and multiplicative weighting are special cases for theoretical framework for adjustment weighting.

Authors 2

1. Silvia Biffignandi

   University of Bergamo

   Affiliation as printed

   University of Bergamo, Italy

2. Jelke G. Bethlehem Aachen Faculty of Social and Behavioral Sciences Institute of Political Science

   Leiden University

   Affiliation as printed

   Faculty of Social and Behavioral Sciences, Institute of Political Science, Leiden University, The Netherlands