Mode effects in concurrent mixed-mode surveys

Citations Over Time

Abstract

사회환경 변화와 정보기술 발전에 따라 한 조사에 다양한 조사모드(survey mode)를 활용하는 혼합조사(mixed-mode survey)가 확대되고 있으며, 포함오차 축소, 비용절감, 응답률 향상 등의 장점을 가진다. 그러나 혼합조사는 선택효과와 측정효과가 혼재된 모드효과 발생으로 조사품질에 대한 우려가 있다. 통계개발원은 이러한 혼합조사의 모드효과를 파악하기 위하여 2014년에 병행적 혼합모드 시험조사를 수행하였다. 본 연구는 시험조사 자료에 대해 자기기입식 종이조사와 웹조사 간 모드효과를 선택효과와 측정효과로 분리하여 계량적으로 분석하였다. 선택계층의 효과를 분리하였을 때, 조사항목에 따라 과대 또는 과소 응답하는 측정효과가 존재하는 것을 확인하였다. Mixed-mode (MM) designs in which data are collected by different modes in one design have become increasingly popular. An MM data collection has several advantages such as reductions of coverage error, non-response and cost. However, MM designs may introduce mode effects that are confounded by selection effects and measurement effects, which can make MM data quality poor. In order to investigate mode effects, SRI implemented a concurrent mixed-mode experiment in 2014 where respondents could choose between a self-administrated Web survey and a self-administrated paper survey. This paper separately estimates selection effects and measurement effects. We found that measurement effects on some items are large.

Related Papers

• → Pixels or pencils? The relative effectiveness of Web-based versus paper surveys(2003)133 cited
• → Improving Survey Response Rates: The Effect of Embedded Questions in Web Survey Email Invitations(2017)11 cited
• → Pictures Instead of Survey Questions: An Experimental Investigation of the Feasibility of Using Pictures in a Housing Survey(2022)7 cited
• → Underreporting of Purchases in the US Consumer Expenditure Survey(2021)9 cited
• → Are Embedded Survey Items the Solution to Low Web Survey Response Rates? An Investigation of the Interaction Between Embedded Survey Items and Time of Survey Administration.(2017)2 cited