Evaluation of Key Performance Indicators for Interviewer Falsification Suspicion from Paradata and Interview Data
Conference
64th ISI World Statistics Congress - Ottawa, Canada
Format: IPS Abstract
Session: IPS 312 - Innovative statistical methods for large-scale surveys
Wednesday 19 July 2 p.m. - 3:40 p.m. (Canada/Eastern)
Abstract
In-person surveys are susceptible to interviewer falsification and validation is usually conducted as a common practice to help detect interviewer falsification. One typical validation process could be conducted through phone calls to a subsample (e.g. 10 percent) of selected households to verify the results of the interviewer attempts to complete the survey. Because validation may not fully protect a survey from interviewer falsification, additional methods need to be explored. One potential approach is to use the paradata and interview responses to identify suspicious circumstances. This presentation begins by discussing 23 potential key performance indicators (KPIs) for interviewer falsification suspicion using paradata and interview data. Methodology will be discussed for deriving an overall KPI measure that combines standardized individual KPI measures into a single, interviewer-level score. This overall KPI measure is then evaluated in the U.S. Programme for the International Assessment of Adult Competencies US Cycle II Main Study. Lastly, visualization displays of the measures will be presented.