Exploring the Use of Telephone Surveys and Propensity Score Adjustments to Correct Web Survey Biases
Author: Eric Chen-hua Yu, Chih-yang Tu
Abstract / Chinese PDF Download
While web surveys are observed quite frequently in our day-to-day lives, scholars rarely take their results seriously. This is mainly due to the fact that the results of web surveys are the product of non-random sampling and cannot be used to draw inferences about the target populations. This paper utilizes numerous parallel waves of telephone and web survey data, from Taiwan’s Election and Democratization Studies (TEDS), to explore whether or not the possible biases produced by web surveys can be corrected with a “reference group” dataset drawn from telephone surveys. Specifically, it uses the so-called “Webographic variables” and combines the two types of data to produce proper estimates for web surveys via the propensity score adjustment (PSA) method. Overall, this analysis examines the effectiveness of using data from telephone surveys and the PSA method when dealing with possible biases of web survey results. Additionally, this paper highlights some key pros and cons of using such methods and suggests various venues for future research.