High Dimensional Discriminant Analysis Of Two General Populations

In this paper,we mainly study the misclassification probability of two di?erent general populations covariance matrices,which is the deepening of the research on the probability of misclassification probability.Since the population is no longer a normal population,we need to give a general population distribution;at the same time,since the covariance matrices are no longer equal,we need to find a discriminant function that fits them.In particular,in this paper,it is stipulated that the relationship between the two population covariance matrices is a constant multiple or a diagonal matrix of two inequalities.On this basis,through a series of research calculations,we have obtain the misclassification probability of two general populations and it is finally verified by simulation experiments.The structure of this paper is divided into four parts.The first part introduces the theoretical background of discriminant analysis,including the introduction of discriminant function and the research results of misclassification probability.The second part gives two important theorems of this paper;the third part is the detailed proof of the two important theorems of this paper;the fourth part is the simulation experiment results of this paper.