TOWARD UNDERSTANDING THE CONTENTS OF THE BLACK BOX FOR PREDICTING COMPLEX DECISIONMAKING OUTCOMES
Overview
Identity
Additional Document Info
Other
View All
Overview
abstract
The purpose of this research is to show the usefulness of three relatively simple nonlinear classification techniques for policycapturing research where linear models have typically been used. This study uses 480 cases to assess the decisionmaking process used by 24 experienced national bank examiners in classifying commercial loans as acceptable or questionable. The results from multiple discriminant analysis (a linear technique) are compared to those of chisquared automatic interaction detector analysis (a search technique), loglinear analysis, and logit analysis. Results show that while the four techniques are equally accurate in predicting loan classification, chisquared automatic interaction detector analysis (CHAID) and loglinear analysis enable the researcher to analyze the decisionmaking structure and examine the human variable within the decisionmaking process. Consequently, if the sole purpose of research is to predict the decision maker's decisions, then any one of the four techniques turns out to be equally useful. If, however, the purpose is to analyze the decisionmaking process as well as to predict decisions, then CHAID or loglinear techniques are more useful than linear model techniques. Copyright 1983, Wiley Blackwell. All rights reserved