Total Survey Error in Practice

8The Effects of a Mid‐Data Collection Change in Financial Incentives on Total Survey Error in the National Survey of Family Growth: Results from a Randomized Experiment

James Wagner,^1,2 Brady T. West,^1,2 Heidi Guyer,¹ Paul Burton,¹ Jennifer Kelley,³ Mick P. Couper,^1,2 and William D. Mosher⁴

¹ Survey Research Center, University of Michigan, Ann Arbor, MI, USA

² Joint Program in Survey Methodology, University of Maryland, College Park, MD, USA

³ Institute for Social and Economic Research, University of Essex, Colchester, UK

⁴ Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD, USA

8.1 Introduction

In the survey methodology literature, the effects of incentives have largely been investigated with respect to nonresponse rates and, although less so, nonresponse error. Less frequent are investigations of the effects of incentives on multiple sources of errors. Nevertheless, there has been research on the impact of incentives on other sources of errors, including measurement error, and perhaps indirectly on all other sources of errors through reporting the impact of incentives on survey costs.

The goal in the investigation presented in this chapter is to understand the impact of an incentive in a large, face‐to‐face survey on several sources of errors. Specifically, this chapter examines whether a change in incentives can lead to reductions of nonresponse bias, decreases in measurement error, and—through cost savings—decreases in sampling error.

This chapter ...