Survey modes: Design and estimation
Mixed-mode surveys are almost inevitable today, especially for academic research and official statistics. Mixing modes has many advantages, but there are also some potential drawbacks. In this lecture we give an overview of issues in design and analysis and provide tools for designing, implementing and evaluating mixed-mode surveys. We will discuss the most common designs for mixing modes. In analysing mixed-mode data it is important to distinguish between selection effects (who responds to which mode) and measurement effects (effect of mode on answer). We will discuss the implications of mixing modes for questionnaire design, total survey error, logistics and data analysis.
- De Leeuw, E.D. (2018). Mixed-Mode: Past, Present, and Future. Survey Research Methods, 12, 2, 75-89. https://ojs.ub.uni-konstanz.de/srm/article/view/7402/6582
- Toepoel, de Leeuw & Hox (2019). Single- and mixed-mode survey data collection. Sage Research Methods foundations (on blackboard)
- Kolenikov, S., & Kennedy, C. (2014). Evaluating Three Approaches to Statistically Adjust for Mode Effects. Journal of Survey Statistics and Methodology, 2(2).
Take home exercise