论文信息 - Some asymptotic results on the effect of autocorrelation on the error rates of the sample linear discriminant function

Some asymptotic results on the effect of autocorrelation on the error rates of the sample linear discriminant function

Abstract The effect of serial correlation of the training samples on the error rates associated with the sample linear disciminant function has been studied recently by Tubbs.(1) This paper investigates the effect of serial correlation under more general conditions. Also, it is noted that the asymptotic expansion of the change in the expected error rate differs from that given by Tubbs.(1)

Geoffrey J. McLachlan | Charles R. O. Lawoko | G. McLachlan | C. Lawoko

[1] M. Okamoto. Correction Notes: Correction to "An Asymptotic Expansion for the Distribution of the Linear Discriminant Function" , 1968 .

[2] Patrick L. Odell,et al. Effect of intraclass correlation among training samples on the misclassification probabilities of bayes procedure , 1974, Pattern Recognit..

[3] R. G. Craig,et al. Autocorrelation in Landsat data , 1979 .

[4] T. W. Anderson,et al. An Introduction to Multivariate Statistical Analysis , 1959 .

[5] G. McLachlan. The relationship in terms of asymptotic mean square error between the separate problems of estimating each of the three types of error rate of the linear discriminant function , 1974 .

[6] M. Okamoto. An Asymptotic Expansion for the Distribution of the Linear Discriminant Function , 1963 .

[7] Geoffrey J. McLachlan,et al. Further results on the effect of intraclass correlation among training samples in discriminant analysis , 1976, Pattern Recognit..

[8] T. W. Anderson. An Introduction to Multivariate Statistical Analysis , 1959 .

[9] Jake D. Tubbs,et al. Effect of autocorrelated training samples on Bayes' probabilities of misclassification , 1980, Pattern Recognit..