Ergo: a New Approach To Multidimensional Item Analysis

1 October 1981

journal article
Published by SAGE Publications in Educational and Psychological Measurement

Vol. 41 (3) , 643-659
https://doi.org/10.1177/001316448104100304

Abstract

Cliff (1977) suggests a series of indices, intended for a testing context, that establish a relation between dominance matrices and classical measurement. Cliff's index c derived from an item dominance matrix is utilized in a clustering approach (termed ERGO) to isolate Guttman-type item hierarchies. A comparison of factor analysis to the ERGO is made on social distance data involving multiple ethnic groups. The ERGO procedure surpassed the factor analysis by satisfactorily identifying both the number of hypothetical item hierarchies as well as the developmental order within each hierarchy.

Keywords

This publication has 3 references indexed in Scilit:

The varimax criterion for analytic rotation in factor analysis
Psychometrika, 1958
A Basis for Scaling Qualitative Data
American Sociological Review, 1944
The Theory of the Estimation of Test Reliability
Psychometrika, 1937