Following a brief interpretation of a multivariate analysis, purposes of such an analysis are reviewed. A discussion of two primary purposes, prediction and structure identification, and of the secondary purpose of response variable ordering is given. Concluding comments are made pertaining to the necessity of a sound initial choice of response variables and to the questionable use of a multivariate analysis preliminary to simpler analyses if the latter constitute the analysis of interpretive interest.
References
1.
Conger, A. J. (1984). Statistical considerations. In M. Hersen, L. Michelson, & A. S. Bellack (Eds.), Issues in psychotherapy research (pp. 285-309). New York: Plenum.
2.
Darlington, R. J. (1990). Regression and linear models. New York: McGraw-Hill.
3.
Ehrenberg, A.S.C. (1990). The unimportance of relative importance. American Statistician, 44, 260.
4.
Harris, R. J. (1985). A primer of multivariate statistics. Orlando, FL: Academic Press.
5.
Huberty, C. J (1989). Problems with stepwise methods-Better alternatives. In B. Thompson (Ed.), Advances in social science methodology (Vol. 1, pp. 43-70). Greenwich, CT: JAI.
6.
Huberty, C. J (1994). Applied discriminant analysis. New York: Wiley.
7.
Huberty, C. J , & Morris, J. D. (1989). Multivariate analysis versus multiple univariate analyses. Psychological Bulletin, 105, 302-308.
8.
Huberty, C. J , & Wisenbaker, J. M. (1992a). Discriminant analysis: Potential improvements in typical practice. In B. Thompson (Ed.), Advances in social science methodology (Vol. 2, pp. 169-208). Greenwich, CT: JAI.
9.
Huberty, C. J , & Wisenbaker, J. M. (1992b). Variable importance in multivariate group comparisons. Journal of Educational Statistics, 17, 75-91.
10.
Kaplan, A. (1964). The conduct of inquiry. San Francisco: Chandler.
11.
Kruskal, W. , & Majors, R. (1989). Concepts of relative importance in recent scientific literature. The American Statistician, 43, 2-6.
12.
Li, J. , Olejnik, S. F., & Huberty, C. J (1992, April). Multiple testing with modified Bonferroni methods. Paper presented at the annual meeting of the American Educational Research Association, San Francisco.
13.
MacCorquodale, K. , & Meehl, P. E. (1948). On a distinction between hypothetical constructs and intervening variables. Psychological Review, 55, 95-107.
14.
Maxwell, S. E. (1992). Recent developments in MANOVA applications. In B. Thompson (Ed.), Advances in social science methodology (Vol. 2, pp. 137-168). Greenwich, CT: JAI.
15.
McDonald, R. P. (1984). Factor analysis and related methods. Hillsdale, NJ: Lawrence Erlbaum.
16.
Mulaik, S. A. (1994). The critique of pure statistics: Artifact and objectivity in multivariate statistics. In B. Thompson (Ed.), Advances in social science methodology (Vol. 3, pp. 241-289). Greenwich, CT: JAI.
17.
Rencher, A. C. (1992). Interpretation of canonical discriminant functions, canonical variates, and principal components. American Statistician, 46, 217-225.
18.
Stevens, J. (1992). Applied multivariate statistics for the social sciences. Hillsdale, NJ: Lawrence Erlbaum.
19.
Sullivan, J. L. , & Feldman, S. (1979). Multiple indicators. Beverly Hills, CA: Sage.
20.
Tatsuoka, M. M. (1988). Multivariate analysis. New York: Macmillan.
