Absence de rigueur dans les sondages d'opinion : Les lecons d'un retour d'experience

Abstract

Absence of rigor in opinion polls, Lessons learned from experience: The authors statictically analyze data collected during a 2003 CAPI (computer-assisted personal interview) public opinion poll of 2,520 persons. Interviewer data collection is examined for number of interviews, lenght of interviews, response modality use and time between interviews. This analysis identifies a number of interviewers whose data production raises certain questions. Far from placing responsibility only on interviewers, the authors critique certain practices in polling that encourage the production of low-quality data.