Skip to main navigation Skip to main content
The University of Southampton
Southampton Statistical Sciences Research Institute

Evaluating the measurement error of interviewer observed paradata Seminar

Date:
11 November 2011
Venue:
Building 39 Room 3013

For more information regarding this seminar, please email Mrs Jane Revell at j.revell@southampton.ac.uk .

Event details

Methodology seminar

Abstract
As survey researchers have begun exploiting paradata for the correction of nonresponse bias, the quality of these data has come into question. Inaccurate information is likely to affect the resulting statistics and conclusions drawn from the application of such data. However, there is a shortage of literature documenting the quality of paradata. Therefore, this paper focuses on one prominent type of paradata used in nonresponse bias correction, interviewer observations, and assesses the quality of these observations by examining their measurement error properties. The analysis uses a unique dataset, the UK Census Nonresponse Link Study, which collected interviewer observations of housing unit and neighborhood characteristics for six major UK surveys and linked this with Census data, along with additional paradata. This dataset allows the evaluation of the observations recorded by the interviewer by comparing these with information from the Census (assumed to be a gold standard) on both respondents and nonrespondents to the surveys. A multilevel modeling approach is used to explore under which conditions the observations match, accounting for the clustering of sample members within interviewers and areas. Covariates tested in the models include characteristics of the household, interviewer and area. Particular attention is paid to the role of the interviewer in the collection of the observations to understand to what extent the measurement error is a function of interviewer characteristics. The results are expected to contribute to future decisions about which observations are most useful to collect as well as what might be done in order to improve accuracy.

Speaker information

Jenifer Sinibaldi , IAB Institute for Employment Research. Germany

Privacy Settings