Statistical invariance procedures provide a way of looking at the generalizability of research results from sample to sample when the research has not been validated by replication. This paper discusses the Procrustean Rotation invariance procedure following a canonical correlation analysis. The computer program RELATE is used to gauge the replicability and generalizability of the illustrative substantive research results. A Procrustean rotation forces orthogonal (uncorrelated) functions of factors to a best fit position after setting the factor vectors to unit length (1.0) in order to equalize the contribution of each factor vector to the determination of the amount of rotation necessary. This rotation technique can be used as a cross-validation procedure, splitting data from a single sample and comparing factor vectors for each half. The sample used to illustrate the procedure is from a study of leadership styles conducted by M. L. Tucker (1990) using data from 106 college faculty and administrators, with the university research sample split into two uneven data sets (n=48 and n=58). Two tables of illustrative data and an 11-item list of references are included. (SLD)
Authors
- Peer Reviewed
- F
- Publication Type
- ['Reports - Evaluative', 'Speeches/Meeting Papers']
- Published in
- United States of America
Table of Contents
- ED 343 913 1
- TITLE NOTE 1
- Jan 92 1
- MF01PC01 Plus Postage. Rotations Factor Analysis 1
- IDENTIFIERS Rotation 1
- APPLYING PROCRUSTEAN ROTATION TO EVALUATE THE GENERALIZABILITY OF 2
- PLEASE CORRESPOND WITH 2
- Procrustean Rotation invariaice procedure fol- 3
- The computer program RELATE is 3
- Repetition 4
- When 5
- The current study applied an 5
- Veldman 1967 p. 238. 5
- Although either function 7
- The resulting predictor variable 7
- Table 1. 7
- The deci- 7
- HERE 9
- REFERENCES 10
- Fish L. J. 10
- Unpublished masters 10
- Hillsdale 10
- Lawrence Erlbaum Associates. 10
- Relating 10
- San Diego 10
- Kerlinger F. N. 10
- Fort Worth TX 10
- Thompson B. 10
- Thompson B. 10
- Thompson B. 10
- Research 10
- 50 101-104. 10
- Tucker M. L. 11
- Unpublished doctoral 11
- Tukey J. W. 11
- Analyzing date 11
- Veldman D. J. 11
- New York 11
- Holt Rinehart and Winston. 11
- Table 1 12
- Split-Sample Canonical Run 12
- Function II Function III 12
- 0.98000 0.64000 12
- 1.04100 12
- 0.00700 0.01500 12
- 1.34600 12
- 0.02900 0.40000 12
- MATRIX B n 12
- Function I Function II 12
- Function III 12
- 0.61100 12
- 0.00100 12
- 1.29900 12
- 0.38200 12
- Table 2 12
- With Test rs 12
- Function I 12
- Function II 12
- Function III 12
- Function I 0.0661 12
- 0.0006 12
- Function II 12
- 0.0145 12
- Function III 12
- 0.0645 0.2103 12
- TEST rs were 0.9971 12
- 0.9979 and 0.9979. 12
