A computationally efficient nonparametric algorithm is proposed for the selection of variables in allocatory discriminant analysis. The efficiency of the algorithm derives from an ability to reuse calculations for the inverse of a nonsingular matrix. A subset of the original variables is found for which the leave-one-out estimate of the conditional probability of misclassification is never significantly greater than the estimated conditional probability of misclassification for the full set of predicate variables.
References
1.
Habbema, J. D. F. and Hermans, J. (1977). Selection of variables in discriminant analysis by F-statistic and error rate. Technometrics, 19, 487-493.
2.
Hecker, R. and Wegener, H. (1978). The validation of classification rates in stepwise discriminant analysis. Biometrical Journal, 20, 713-727.
3.
Huberty, C. J. (1984). Issues in the use and interpretation of discriminant analysis. Psychological Bulletin, 95, 156-171.
4.
Jain, A. K. and Waller, W. G. (1979). On the optimal number of features in the classification of multivariate Gaussian data. Pattern Recognition, 10, 365-374.
5.
Kittler, J. (1978). Classification of incomplete pattern vectors using modified discriminant functions. IEEE Transactions on Computers, C-27, 367-374.
6.
Lachenbruch, P. A. (1967). An almost unbiased method of obtaining confidence intervals for the probability of misclassification in discriminant analysis. Biometrics, 23, 639-645.
7.
McKay, R. J. and Campbell, N. A. (1982). Variable selection techniques in discriminant analysis II: Allocation. British Journal of Mathematical and Statistical Psychology, 35, 30-41.
8.
McLachlan, G. J. (1976). A criterion for selecting variables for the linear discriminant function. Biometrics, 32, 529-534.
9.
McLachlan, G. J. (1980). On the relationship between the F test and the overall error rate for variable selection in two-group discriminant analysis. Biometrics, 36, 501-510.
10.
McLachlan, G. J. (1986). Assessing the performance of an allocation rule. Computers and Mathematics with Applications, 12A (2), 261-272.
11.
Narendra, P. M. and Fukanaga, K. (1977). A branch and bound algorithm for feature subset selection. IEEE Transactions in Computing C, 26, 917-922.
12.
VanNess, J. W. and Simpson, C. (1976). On the effects of dimension in discriminant analysis. Technometrics, 18, 175-187.
