Cross-Validation in Canonical Analysis [electronic resource] / Dianne L. Taylor.
The need for using invariance procedures to establish the external validity or generalizability of statistical results has been well documented. Invariance analysis is a tool that can be used to establish confidence in the replicability of research findings. Several approaches to invariance analysis...
Saved in:
| Online Access: |
Full Text (via ERIC) |
|---|---|
| Main Author: | |
| Format: | Electronic eBook |
| Language: | English |
| Published: |
[S.l.] :
Distributed by ERIC Clearinghouse,
1992.
|
| Subjects: |
| Summary: | The need for using invariance procedures to establish the external validity or generalizability of statistical results has been well documented. Invariance analysis is a tool that can be used to establish confidence in the replicability of research findings. Several approaches to invariance analysis are available that are broadly applicable across univariate and multivariate procedures. This paper explains one of these procedures, cross-validation. One form of the technique, double cross-validation, is applied in a canonical correlation analysis using a heuristic data set. A double cross-validation of the weights in a canonical correlation analysis is used to test for invariance in a study of university leadership conducted by M. L. Tucker (1990) with 105 subjects. A brief overview of both invariance testing and canonical correlation analysis is provided. Four tables present data from the analysis, and a 27-item list of references is included. An appendix contains the computer command lines used to generate the cross-validation. (Author/SLD) |
|---|---|
| Item Description: | ERIC Document Number: ED342809. ERIC Note: Paper presented at the Annual Meeting of the Southwest Educational Research Association (Houston, TX, January 31-February 2, 1992). |
| Physical Description: | 24 p. |