Answers are grounded in this paper and cite their sources.
In analyzing data from attitude surveys, it is common to consider the “don’t know” responses as missing values. In this article, we present a statistical model commonly used for the analysis of responses/evaluations expressed on Likert scales and extended to take into account the presence of don’t know responses. The main objective is to offer an alternative to the usual custom to treat them as missing values by considering them as a source of uncertainty. The original proposal in this article is the introduction of the relevant covariates in order to discriminate subpopulations that can show different behaviors in choosing between a substantive response and the don’t know option.
No takes yet. Share an insight, caveat, or question.
Iannario et al. (2018) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: