Another Perspective of the Miller Forensic Assessment of Symptoms Test – Part II: A Quantitative Review

Abstract

Reference [1] presented pooled data for the specificity of the M-FAST cut-off, but ignored or excluded data based on poor justifications and used questionable analytic methods. The analyses here corrected the problems associated with [1]. No moderator substantively influenced sensitivity values. Therefore, sensitivity values were pooled across all studies (k = 25) to provide an overall estimate. Overall, the average sensitivity of the M-FAST cut-off was estimated to be 0.87, 95% CI [0.80, 0.91], and 80% of true sensitivity values were estimated to range from 0.63 to 0.96. Thus, there could be methodological scenarios when the M-FAST cut-off may not operate efficiently. Average specificity values for the M-FAST cut-off were moderated by one variable: the comparison group. On average, specificity values for clinical comparison (k = 15) groups (i.e., 0.80, 95% CI [0.73, 0.85]) were lower than specificity values for non-clinical comparison (k = 11) groups (i.e., 0.96, 95% CI [0.89, 0.99]). Unlike the CIs, the estimated distributions of true specificity values for the two subgroups overlapped, which suggests there could be scenarios when these subgroups share the same true specificity value. The M-FAST was designed to be a screener to detect potential feigning of psychiatric symptoms. An examinee is never to be designating as feigning or malingering psychiatric symptoms based on only a positive M-FAST result. As a screening instrument, the results here show that the M-FAST cut-off is operating adequately overall and negate the conclusions of [1].