New scientific publication “Item Nonresponse in Web Versus Other Survey Modes: A Systematic Review and Meta-Analysis”

Gregor Čehovin, PhD, assoc. prof. Katja Lozar Manfreda, PhD (Centre for Social Informatics) and prof. Michael Bosnjak, PhD (Robert Koch Institute and University of Trier) have jointly published a scientific article entitled “Item Nonresponse in Web Versus Other Survey Modes: A Systematic Review and Meta-Analysis”. The meta-analysis is available in open access from Social Science Computer Review (SAGE Journals).

This paper is the first meta-analysis to investigate whether web surveys are at a disadvantage with respect to item nonresponse compared to other survey modes. Item nonresponse is a fundamental problem in survey research and refers to situations in which a survey unit did not respond to a certain survey question (item).

The results of the meta-analysis showed that there was no statistically significant difference in the average item nonresponse rate for web surveys compared to other survey modes. However, six moderator variables were found to have a statistically significant effect on the relationship between survey mode and item nonresponse rate: target population, number of contacts, compared mode, survey sponsor, survey age, and the baseline item nonresponse rate of the compared mode.

Previous meta-analyses (e.g., Daikeler et al., 2020) have found that web surveys are disadvantaged relative to other survey modes in terms of unit nonresponse rate, which denotes that no (usable) responses were received from a survey unit. The same situation does not apply to item nonresponse rate, where web surveys perform similarly (on average) to other survey modes, which is the main practical implication of the present paper.