Search

Based on two individual validation studies employing face-to-face interviews and a mail survey, this article investigates factors influencing the probability that respondents truthfully admit to having been convicted of a criminal offense. Overall, 63 percent of the 495 respondents stuck to the truth in the survey settings. The mail survey elicited significantly more truthful responses (67 percent) than the face-to-face survey (58 percent). Female, older, and better-educated respondents confessed their delinquent behavior less often than male, younger, and less-educated ones. Whereas the need for social approval did not show a significant effect on the probability of an honest answer when controlling for other variables, trait desirability did. Regarding the face-to-face survey, the more interviews an interviewer had successfully completed in the ongoing study, the higher the response quality of the interviewees. In the mail mode, a strong negative effect of time to response could be observed: the longer respondents waited before they sent back the questionnaire, the lower the validity of their answers. [ABSTRACT FROM PUBLISHER]

Linking paradata from a survey on labor market participation to administrative data, this article has a unique opportunity to examine nonresponse and measurement error jointly and provide estimates for bias, variance, and mean square error. We find that increased contact attempts resulted in significant reductions in nonresponse bias. Measurement error increased somewhat with increased effort, though total bias was nevertheless reduced. One of the key survey indicators revealed an interesting case of counteracting effects of nonresponse and measurement error whereby increased effort to recruit nonrespondents led to an increase in mean square error with increased level of effort despite a reduction in nonresponse bias and constant measurement error. [ABSTRACT FROM PUBLISHER]