Selection Bias in Web Surveys and the Use of Propensity Scores

Abstract

Web surveys are a popular survey mode, but the subpopulation with Internet access may not represent the population of interest. The authors investigate whether adjusting using weights or matching on a small set of variables makes the distributions of target variables representative of the population. This application has a rich sampling design; the Internet sample is part of an existing probability sample, the Health and Retirement Study, that is representative of the U.S. population aged 50 and older. For the dichotomous variables investigated, the adjustment helps. On average, the sample means in the Internet access sample differ by 6.5 percent before and 3.7 percent after adjustment. Still, a large number of adjusted estimates remain significantly different from their target estimates based on the complete sample. This casts doubt on the common procedure to use only a few variables to correct for the selectivity of convenience samples.