Mixed-Mode Designs bei Erhebungen mit sensitiven Fragen

Abstract

"Mixed-Mode Designs are becoming more common in social surveys. This is due to lower costs as well as higher data quality. This paper compares a mixed mode telephone and online interview to a single mode telephone interview with regard to (1) response rate, (2) unit nonresponse error, and measurement error due to social desirability bias. Within a health survey, randomized experiment was conducted based on a random sample from a German Registration Office (Einwohnermeldeamt). Individuals were randomly assigned to a single mode telephone and a mixed mode telephone and online survey. In the mixed mode group the response rate was significantly higher, and unit nonresponse error was smaller, especially with regard to sex and age composition of the sample. An additional propensity score matching indicates that social desirability bias was reduced, too." (Author's abstract, IAB-Doku) ((en))

Cite article

Krug, G., Kriwy, P. & Carstensen, J. (2014): Mixed-Mode Designs bei Erhebungen mit sensitiven Fragen. Einfluss auf das Teilnahme- und Antwortverhalten. (LASER discussion papers 84), Erlangen, 36 p.