Consideration Set Sampling to Analyze Undecided Respondents

TL;DR

This paper introduces consideration set sampling to analyze undecided respondents in surveys, providing a new way to understand decision-making processes by modeling the options respondents consider.

Contribution

It presents a novel approach to analyze consideration sets using random set modeling, offering insights into undecided respondents in survey data.

Findings

Consideration set sampling is easy to implement.

The approach enables structural analysis of respondents' decision processes.

Modeling consideration sets as random sets facilitates regression analysis.

Abstract

Researchers in psychology characterize decision-making as a process of eliminating options. While statistical modelling typically focuses on the eventual choice, we analyze consideration sets describing, for each survey participant, all options between which the respondent is pondering. Using a German pre-election poll as a prototypical example, we give a proof of concept that consideration set sampling is easy to implement and provides the basis for an insightful structural analysis of the respondents' positions. The set-valued observations forming the consideration sets are naturally modelled as random sets, allowing to transfer regression modelling as