The impact of administration mode on response effects in survey measurement

Abstract

Abstract The major differences between face‐to‐face and telephone interviews as well as self‐administered questionnaires are reviewed and are related to the cognitive and communicative processes assumed to underlie the process of question answering. Based on these considerations the impact of administration mode on the emergence of well‐known response effects in survey measurement is discussed, and relevant experimental evidence is reported. It is concluded that administration mode affects the emergence of question order and context effects; the emergence of response order effects; the validity of retrospective reports; and the degree of socially desirable responding. The emergence of question wording and question form effects, on the other hand, appears to be relatively independent of administration mode.