Online Program Home
My Program

Abstract Details

Activity Number: 237 - SPEED: Missing Survey Data: Analysis, Imputation, Design, and Prevention
Type: Contributed
Date/Time: Monday, July 30, 2018 : 2:00 PM to 3:50 PM
Sponsor: Survey Research Methods Section
Abstract #328719
Title: Effect of the Survey Name on Response Rates and Survey Estimates
Author(s): David McGrath*
Companies: Department of Defense Office of People Analytics
Keywords: Survey; Nonresponse; Vote; Election; Military

The Department of Defense Office of People Analytics (OPA) has observed that surveys of the active duty military on voting participation have lower response rates (about five percentage points) than other survey topics. OPA hypothesized that a survey name containing the word voting may be of little interest to a mostly young military, and therefore generate low response rates, and also appeal to members interested in politics and voting. If true, the voting name could cause nonresponse bias and lead OPA to overestimate military voting rates. OPA conducted an experiment by manipulating the Voting Survey Name to a Generic Survey Name for a random 15 percent of the sample to determine the effects on response rates and survey estimates. The generic name produced response rates more than 50 percent higher than the voting name (16% vs. 9%). In addition, the generic name produced lower registration and voting rates than the voting name, and weighting could not eliminate the differences in estimates between the two groups. The effects of this experiment were very large, and further research is required to determine if military surveys on different topics exhibit this effect.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program