Interview cooperation and procedural response quality

This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.

In the previous studies, response quality has been investigated mostly in association with the characteristics of the interviewer, the respondent, the questionnaires, or the modes of data collection, but rarely with the process of interview interaction. From the process perspective, this paper examines the relationship between interview co-operation and procedural response quality. The interview co-operation is based on the interviewer's evaluation of his or her interaction with the respondent. The procedural response quality is based on error and non-responses derived from the interviewer's field performance of a completed questionnaire.

The data collected from two subsets (Part I and Part II) of the Taiwan Social Change Survey (TSCS) of year 2000 were analysed using the Hierarchical Linear Model (HLM). The results show that the interviewer's education (Part I) or work experience (Part II) has a significant effect on the procedural response quality. The significant effect of the interview co-operation on the procedural response quality is found only in Part I. The HLM analysis also suggests an interaction effect of the interview co-operation with the interviewer's characteristics (education for Part I and work experience for Part II). In conclusion, suggestions have been made that survey contents are an important factor in differentiating the relationship between procedural response quality and interview co-operation.