Hierarchical Bayesian models for the autonomic-based concealed information test.

The concealed information test (CIT) is a psychophysiological memory detection technique for examining whether an examinee recognizes crime-relevant information. In current statistical analysis practice, the autonomic responses are usually transformed into Z scores within individuals to remove inter- and intra-individual variability. However, this conventional procedure leads to overestimation of the effect size, specifically the standardized mean difference of the autonomic responses between the crime-relevant information and the crime-irrelevant information. In this study, we attempted to resolve this problem by modeling inter- and intra-individual variability directly using hierarchical Bayesian modeling. Five models were constructed and applied to CIT data obtained from 167 participants. The validity of the CIT was confirmed using Bayesian estimates of the effect sizes, which are more accurate and interpretable than conventional effect sizes. Moreover, hierarchical Bayesian modeling provided information that is not available from the conventional statistical analysis procedure.