Item desirability matching in forced-choice test construction

The forced-choice method has been proposed as a viable strategy to prevent socially desirable responding (SDR) on self-report non-cognitive measures. ability of the eliminate SDR stems from matching items that are perceived equally into item-blocks. gold standard in quantifying similarity between terms desirability “mean difference index”, is, absolute items' mean ratings. This index relies assumption have one true value, efficiently and unbiasedly estimated by their respective means, may fail if this does not hold. To circumvent issue, we propose indexing with several robust measures agreement (i.e., inter-item indices). Using an empirical example, show relying lead suboptimal item-block assembly relatively poor respect desirability. R code for computing indices set ratings is provided, recommendations applied researchers.