The Problem of Under‐coverage

Abstract

This chapter focuses on under-coverage. Under-coverage in web surveys would not be a problem if those with Internet did not differ systematically from those without it. It is true that the diffusion of Internet both at household and individual level is a constantly increasing phenomenon and surveys have to handle with the new characteristics of the sampling frame. The more or less ideal case is considered now in which it is possible to select a random sample without replacement from the Internet population. There are several ways in which the negative effects of under-coverage can be reduced. Three approaches are discussed in this chapter. The first approach is to give Internet access to persons in the sample without it. A second approach is to conduct a mixed-mode survey. This is a survey in which different modes of data collection are used. A third approach is to apply 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