Prioritizing low propensity sample members in a survey

Abstract

Many survey methodologists now agree that simply striving to increase the response rate is not an optimal approach for reducing nonresponse bias in the final survey estimates. Targeting sample cases that are underrepresented can help reduce nonresponse bias. However, the challenge lies in which cases to prioritize when resources are finite, and reducing the risk of nonresponse bias is the goal. We present an approach which identifies, prioritizes, and intervenes on low-propensity-to-respond cases during nonresponse follow-up. Targeted cases were assigned to in-person interviewing. Our results suggest that in-person interviewing can be an effective approach for gaining participation from low-propensity cases. We also find that targeting low-propensity cases could improve representation and therefore should be considered by survey practitioners as a tool for nonresponse bias reduction.