A New Model for Acquiescence at the Interface of Psychometrics and Cognitive Psychology

Abstract

When measuring psychological traits, one has to consider that respondents often show content-unrelated response behavior in answering questionnaires. To disentangle the target trait and two such response styles, extreme responding and midpoint responding, Böckenholt ( 2012a ) developed an item response model based on a latent processing tree structure. We propose a theoretically motivated extension of this model to also measure acquiescence, the tendency to agree with both regular and reversed items. Substantively, our approach builds on multinomial processing tree (MPT) models that are used in cognitive psychology to disentangle qualitatively distinct processes. Accordingly, the new model for response styles assumes a mixture distribution of affirmative responses, which are either determined by the underlying target trait or by acquiescence. In order to estimate the model parameters, we rely on Bayesian hierarchical estimation of MPT models. In simulations, we show that the model provides unbiased estimates of response styles and the target trait, and we compare the new model and Böckenholt's model in a recovery study. An empirical example from personality psychology is used for illustrative purposes.

Individual, situational, and cultural correlates of acquiescent responding: Towards a unified conceptual framework

“…First, our acquiescence index – despite being based on 29 heterogeneous items – might still contain content variance. Ideally, studies should test whether our findings generalize to a latent acquiescence trait defined over several balanced‐keyed scales using confirmatory factor analysis models or, preferably, models from the item response theory family (e.g., Plieninger & Heck, ). A latent acquiescence factor thus conceived would have higher reliability and validity than our current one.…”

A Novel Partial Credit Extension Using Varying Thresholds to Account for Response Tendencies

“…Second, across all categories, threshold shifts do not add or subtract to the linear parameter combination. Therefore, the location of the respondent on the latent continuum is set by the construct level and is not shifted by response tendencies (see also Plieninger & Heck, 2018, for a discussion). Third, as varying thresholds sum to zero within respondents, the constraint implicitly incorporates dependencies between varying thresholds that are often found in empirical data.…”

“…The scale matrix mirrors the strong negative correlations between the outer and between the inner thresholds, respectively, reflecting ERS and MRS (with 90% of correlations in the interval for ERS and for MRS; due to the difference in variance), but small correlations between constructs, and constructs and varying thresholds (90% of correlations in the interval [ − .25, .25]). The outer and the inner thresholds had an expected level of negative correlations (with 90% of correlations in the interval [ − .66, .04]; see also Plieninger & Heck, 2018).…”

Seeing the Forest and the Trees: Comparison of Two IRTree Models to Investigate the Impact of Full Versus Endpoint-Only Response Option Labeling

“…One example is a respondent’s response style, which is the tendency for a respondent to systematically choose particular response options regardless of the content of the items and survey (Leventhal & Stone, 2018; Park & Wu, 2019; Paulhus, 1991; Plieninger & Meiser, 2014). As noted previously, Baumgartner and Steenkamp (2001) discussed several response styles that have been identified in literature, including ERS (Cronbach, 1946) and MRS (Messick, 1968; Plieninger & Heck, 2018; Schuman & Presser, 1981).…”