Face-to-face or sequential mixed-mode surveys among non-western minorities in the netherlands: The effect of different survey designs on the possibility of nonresponse bias

Abstract

This article compares the quality of response samples based on a single mode CAPI survey design with the quality of response samples based on a sequential mixed-mode (CAWI-CATICAPI) survey design among four non-Western minority ethnic groups in the Netherlands. The quality is assessed with respect to the representativity of the response samples and the estimated potential for nonresponse bias in survey estimates based on auxiliary variables and the response rate. This article also investigates if these designs systematically enhance response rates differently among various sociodemographic subgroups based on auxiliary variables. Also, costs and cost-related issues particular to this sequential mixed-mode design are discussed. The results show that sequential mixed mode surveys among non-Western ethnic minorities in the Netherlands lead to less representative response samples and show more potential for nonresponse bias in survey estimates. Furthermore, the designs lead to systematic differences in response rates among various sociodemographic subgroups, such as older age groups. Both designs also cause some of the same sociodemographic subgroups to be systematically underrepresented among all non-Western ethnic minority groups. Finally, the results show that in this instance the cost savings did not outweigh the reduction in quality.