Quality Issues in Interview Surveys : Some Contributions

Abstract: In Paper I, I give a brief overview of the “state of the art” in methodological research related to interview surveys and I discuss some implications for survey practices. I study the literature on participation strategies, interviewer effects that can occur during the interview, methods for quality assurance and interviewer training. Methods that are used to study quality aspects of interview surveys are also described. The discussion highlights areas where more research is needed.Paper II deals with the interview process and the concept of interviewer burden. Interviewer errors have been described in the survey methodology literature. This literature, however, has not to a great extent addressed the question of why interviewer errors occur or why interviewers behave the way they do. In this paper these issues are addressed. I model the interview process, address interviewers’ cognitive processes, define the concept of interviewer burden and discuss its effects. Data from two interviewer surveys are used to illustrate aspects of interviewer burden. In Paper III I explore some components of interviewer burden further. I use data from the Swedish part of the European Social Survey (ESS) to study the effects of interviewer burden and strategies on data quality. Multilevel regression analysis is used to model effects due to respondents and to interviewers. From the data analysis I found that interviewer burden, as I define it, affects data quality. For example, interviewers with a heavy burden tend to have lower response rates, higher refusal and noncontact rates, and shorter interview time.In Paper IV we study the effects of the fieldwork on nonresponse bias in the Swedish Labour Force Survey. In the evaluation study we use external data that is available for both respondents and nonrespondents to estimate the nonresponse bias. We apply the generalised regression estimator (GREG) using strong auxiliary information in the estimation procedure. We also carry out the same analysis assuming a simple random sample was drawn and that no auxiliary information is available. Furthermore we study noncontacts and refusals to address the question whether there is a bias caused by either group of nonrespondents. Finally we estimate the cost for the current fieldwork strategy compared with less elaborate strategies.