Use of Response Propensities

Abstract

Web survey-based estimates may be biased due to under-coverage, self-selection, or nonresponse. This chapter is about response propensities. It describes what they are, how they can be computed, and what can be done with them. The method of propensity score matching is applied to web surveys. The chapter discusses various problems and ways to use response propensities to improve estimators in web surveys. A definition of response propensity is given, and models for response propensities are described. The chapter presents methods for correcting bias using response propensities. Particularly response propensity weighting and stratification are proposed as correction techniques. The chapter also describes an application comparing methods for correcting bias.

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