Linear discriminant function analysis in neuropsychological research: some uses and abuses

Abstract

The present paper addressed the continued misinterpretation and misapplication of linear discriminant function analysis in neuropsychological research. Methodological problems concerning the influence of shrinkage and stepwise selection procedures on LDFA are virtually ignored and affect both the classification and inferential application of LDFA. Throughout the paper examples of potential abuses of LDFA were cited and data from a familiar research problem was employed to demonstrate procedures which enable more accurate interpretation of LDFA results. Linear discriminant function analysis and its multivariate equivalents are powerful and flexible tools for exploring group differences provided appropriate applications and interpretations of results are made.