In discriminant analysis, the correlations between the variables and the discriminant functions-structure coefficients-are used in interpretation. Rules of thumb are used to set a cutoff value because there are no formulas for the standard error of structure coefficients. The bootstrap procedure can be used to estimate standard errors and confidence intervals via resampling. A set of SAS macros are described that perform a bootstrap analysis on structure coefficients from a discriminant analysis.
Get full access to this article
View all access options for this article.
References
1.
Boomsma, A. (1991). BOJA: A program for bootstrap and jackknife analysis. Groningen, The Netherlands: iec ProGAMMA.
2.
Bray, J. H. , & Maxwell, S. E. (1982). Analyzing and interpreting significant MANOVAs. Review of Educational Research, 52, 340-367.
3.
Chant, D. , & Dalgleish, L. I. (1992). A SAS macro for jackknifing the results of discriminant analyses. Multivariate Behavioral Research, 27, 301-311.
4.
Clarkson, D. B. (1979). Estimating the standard errors of rotated factor loadings. Psychometrika, 44, 297-314.
5.
Dalgleish, L. I. (1992). When the jackknife fails: A comparison of the jackknife and the bootstrap for discriminant analysis [Abstract]. Proceedings of the 55th Annual Meeting of the Institute of Mathematical Statistics, p. 334.
6.
Dalgleish, L. I. (1994). Discriminant analysis: Statistical inference using the jackknife and bootstrap procedures. Psychological Bulletin, 116, 498-508.
7.
Dalgleish, L. I. (in press). Bootstrapping and jackknifing with BOJA. Statistics & Computing.
8.
Efron, B. (1982). The jackknife, the bootstrap, and other resampling plans. Philadelphia: Society for Industrial and Applied Mathematics.
9.
Efron, B. (1987). Better bootstrap confidence intervals. Journal of the American Statistical Association, 82, 171-185.
10.
Efron, B. (1988). Bootstrap confidence intervals: Good or bad?Psychological Bulletin, 104, 293-296.
11.
Efron, B. , & Gong, G. (1983). A leisurely look at the bootstrap, the jackknife, and cross-validation. American Statistician, 37, 36-48.
12.
Hall, P. (1992). Efficient bootstrap simulation. In R. Lepage & L. Billard (Eds.), Exploring the limits of bootstrap. New York: Wiley.
13.
Lambert, Z. V. , Wildt, A. R., & Durand, R. M. (1991). Approximating confidence intervals for factor loadings. Multivariate Behavioral Research, 26, 421-434.
14.
Lunneborg, C. E. (1985). Estimating the correlation coefficient: The bootstrap approach. Psychological Bulletin, 98, 209-215.
15.
Lunneborg, C. E. (1987). Bootstrap applications for the behavioral sciences (Vol. 1). Seattle, WA: Author.
16.
Mosteller, F. , & Tukey, J. W. (1977). Data analysis and regression: A second course in statistics. Reading, MA: Addison-Wesley.
17.
Rasmussen, J. L. (1987). Estimating the correlation coefficient: Bootstrap and parametric approaches. Psychological Bulletin, 101, 136-139.
18.
Rasmussen, J. L. (1988). "Bootstrap confidence intervals: Good or bad": Comments on Efron (1988) and Strube (1988) and further evaluation. Psychological Bulletin, 104, 297-299.
19.
SAS. (1988). Release, Version 6 edition. Cary, NC: SAS Institute.
20.
Strube, M. J. (1988). Bootstrap Type I error rates for the correlation coefficient: An examination of alternative procedures. Psychological Bulletin, 104, 290-292.
21.
Tabachnick, B. G. , & Fidell, L. S. (1989). Using multivariate statistics (2nd ed.). New York: Harper & Row.
22.
Thompson, B. (1992). DISCTRA: A computer program that computes bootstrap resampling estimates of descriptive discriminant analysis function and structure coefficients and group centroids. Educational and Psychological Measurement, 52, 905-911.
23.
Wildt, A. R. , Lambert, Z. V., & Durand, R. M. (1982). Applying the jackknife statistic in testing and interpreting canonical weights, loadings, and cross-loadings. Journal of Marketing Research, 19, 99-107.
