Robustness of taxometric analysis with skewed indicators: I. A Monte Carlo study of the MAMBAC procedure

Abstract

A small Monte Carlo study was conducted to determine whether Meehl and Yonce's (1994) MAMBAC procedure--a taxometric method for testing between discrete and continuous models of latent variables--is robust when the latent variable and its manifest indicators are skewed. Analysis of constructed data sets containing three levels of skew indicated that the MAMBAC procedure is highly unlikely to yield spurious findings of discreteness ("taxonicity") even when skewness is considerable. MAMBAC appears to be a robust and promising addition to the family of taxometric procedures.