Some Methods for Respecifying Measurement Models to Obtain Unidimensional Construct Measurement
Open Access
- 1 November 1982
- journal article
- research article
- Published by SAGE Publications in Journal of Marketing Research
- Vol. 19 (4) , 453-460
- https://doi.org/10.1177/002224378201900407
Abstract
Lack of unidimensionality in structural equation models most often represents misspecification. The authors review the necessary conditions for unidimensional measurement of constructs. Two methods which assist the researcher in measurement model respecification, multiple-groups analysis and similarity coefficients, are presented and an example illustrating the use of these methods is given.Keywords
This publication has 32 references indexed in Scilit:
- Significance tests and goodness of fit in the analysis of covariance structures.Psychological Bulletin, 1980
- DETECTION OF CORRELATED ERRORS IN LONGITUDINAL DATABritish Journal of Mathematical and Statistical Psychology, 1975
- On Estimating the Reliability of Composite Indexes Through Factor AnalysisSociological Methods & Research, 1974
- Confirmatory Factor-Analytic Structures and the Theory Construction ProcessSociological Methods & Research, 1973
- METHODS OF REORDERING THE CORRELATION MATRIX TO FACILITATE VISUAL INSPECTION AND PRELIMINARY CLUSTER ANALYSISJournal of Educational Measurement, 1973
- A general method for analysis of covariance structuresBiometrika, 1970
- Validity, Invalidity, and ReliabilitySociological Methodology, 1970
- Package: a System of Computer Routines for the Analysis of Correlational DataEducational and Psychological Measurement, 1969
- Coefficient alpha and the internal structure of testsPsychometrika, 1951
- Demonstration of Formulae for True Measurement of CorrelationThe American Journal of Psychology, 1907