Catscale: A Stochastic Multidimensional Scaling Methodology for the Spatial Analysis of Sorting Data and the Study of Stimulus Categorization
Computational Statistics & Data Analysis, Volume 18, Issue 1, Pages 165-184, 1994
20 Pages Posted: 6 Jun 2016
Date Written: August 1994
Abstract
Sorting tasks have provided researchers with valuable alternatives to traditional paired-comparison similarity judgments. They are particularly well-suited to studies involving large stimulus sets where exhaustive paired-comparison judgments become infeasible, especially in psychological studies investigating stimulus categorization. This paper presents a new stochastic multidimensional scaling procedure called CATSCALE for the analysis of three-way sorting data (as typically collected in categorization studies). We briefly present a review of the role of sorting tasks, especially in categorization studies, as well as a description of several traditional modes of analysis. The CATSCALE model and maximum likelihood based estimation procedure are described. An application of CATSCALE is presented with respect to a behavioral accounting study examining auditor's categorization processes with respect to various types of errors found in typical financial statements.
Keywords: Multidimensional scaling, Sorting tasks, Categorization, Maximum likelihood, Behavioral accounting
Suggested Citation: Suggested Citation