Abstract
The possibility of obtaining locally optimal solutions with categorical data is pointed out for the original version of OSMOD development by Saito and Otsu. A revision of the initialization strategy in OSMOD is suggested, and its effectiveness in diminishing this possibility is demonstrated.
Similar content being viewed by others
References
Kuhfeld, W. F., Sarle, W. S., & Young, F. W. (1985). Methods of generating model estimates in the PRINQUAL macro.SAS users group international conference proceedings: SUGI (pp. 962–971). Cary, NC: SAS Institute.
Kuhfeld, W. F., & Young, F. W. (1989). PRINCIPALS versus OSMOD: A comment on Saito and Otsu.Psychometrika, 54, 755–756.
Saito, T., & Otsu, T. (1983). A method of optimal scaling for multivariate ordinal data.Hokkaido Behavioral Science Report, Series M, 5.
Saito, T., & Otsu, T. (1988). A method of optimal scaling for multivariate ordinal data and its extensions,Psychometrika, 53, 5–25.
Tenenhaus, M., & Vachette, J. L. (1977). PRINQUAL: Un programme d'Analyse en composantes principales d'un ensemble de variables nominales ou numeriques,Les Cahiers de Recherche #68 [PRINQUAL: A program for principal component analysis with nominal or numeric variables]. Jouy-en-Josas: CESA.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Otsu, T., Saito, T. The Problem of local optimality with OSMOD. Psychometrika 55, 517–518 (1990). https://doi.org/10.1007/BF02294764
Issue Date:
DOI: https://doi.org/10.1007/BF02294764