ABSTRACT

Response time (RT) is a potentially important indicator of data quality that can be reliably measured for all questions in a computer-administered survey using a latent timer. This chapter examines the association between RTs and question characteristics available in the observational study. It provides the list of question characteristics and hypotheses. The hypotheses are based on expectations about whether the characteristic is likely to increase the cognitive processing burden of the respondent, interviewer, or both. The hypotheses focused on question characteristics that impact the complexity of the interviewer’s task are partially supported. There is a significant negative interaction of number of interviews completed with interviewer instructions and parenthetical phrases. Overall, interviewers’ experience within the survey (i.e., number of interviews completed) is not associated with RTs. This may be due to the telephone mode, which is more monitored compared to face-to-face modes.