Using GPS and Other Data to Assess Errors in Level-of-Effort Data in Field Surveys

• Activity Number: 496
• Type: Contributed
• Date/Time: Wednesday, August 7, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Survey Research Methods Section
• Author(s): James Wagner*+ and Kristen Olson and Minako Edgar
• Companies: University of Michigan and University of Nebraska and University of Michigan
• Keywords: Paradata ; Nonresponse adjustment ; Measurement error

Abstract

Level-of-effort data are paradata generated by the process of collecting data in surveys. Level-of-effort data are developed from call record data and include proxy measures for contactibility and cooperation. For example, the number of calls required to complete an interview is a proxy for contactability. Many surveys use these data as predictors in nonresponse adjustment models. However, recent research has found that these data may include measurement errors which may reduce their effectiveness for adjustment purposes (Biemer, Chen, and Wang, 2013).

We focus on methods for assessing whether errors occur in level of effort data. We have been collecting GPS data generated by smartphones carried by interviewers in the National Survey of Family Growth since September 2011. We compare these GPS data with the interviewer-reported call records to identify potential errors in the call records. We also examine other indicators of errors in the call records (e.g., changed date, time, address, rounded times). Identifying and measuring errors in the level-of-effort data is a first step towards accounting for these errors when developing nonresponse adjustments.