Rosenfeld, B., Sands, S. A., & Van Gorp, W. G. (2000). Have we forgotten the base rate problem? Methodological issues in the detection of distortion. Archives of Clinical Neuropsychology, 15(4), 349-359.

The search for valid and reliable methods of detecting malingering and distortion has become an increasingly important task for forensic psychologists and neuropsychologists. This report highlights several important methodological issues commonly observed in research on the prediction of malingering. The choice of indices for determining optimal cutoff scores on the utility of existing measures, the impact of base rates of malingering on the accuracy of prediction models, the incremental accuracy of combining multiple measures, and the relationship of test validity to the interpretation of data are described with regard to the prediction of malingering on neuropsychological tests. These methodological concerns are discussed in reference to several recent publications assessing the utility of various methods for the detection of malingering. The article defines the terms sensitivity, specificity, positive predictive accuracy, negative predictive accuracy, false negative, false positive, hit rate, and base rate.

Author's email address

A one page definition of the 2x2 table's accuracy terms can be found at:

2x2 table.pdf