Linear discrimination for three-level multivariate data with a separable additive mean vector and a doubly exchangeable covariance structure

In this article, we study a new linear discriminant function for three-level m-variate observations under the assumption of multivariate normality. We assume that the m-variate observations have a doubly exchangeable covariance structure consisting of three unstructured covariance matrices for three multivariate levels and a separable additive structure on the mean vector. The new discriminant function is very efficient in discriminating individuals in a small sample scenario. An iterative algorithm is proposed to calculate the maximum likelihood estimates of the unknown population parameters as closed form solutions do not exist for these unknown parameters. The new discriminant function is applied to a real data set as well as to simulated data sets. We compare our findings with other linear discriminant functions for three-level multivariate data as well as with the traditional linear discriminant function.

[1]  J. Lindsey,et al.  MODELING PHARMACOKINETIC DATA USING HEAVY-TAILED MULTIVARIATE DISTRIBUTIONS , 2000, Journal of biopharmaceutical statistics.

[2]  Andreas Ziegler,et al.  Generalized Estimating Equations , 2011 .

[3]  A. Roy,et al.  Classification rules for triply multivariate data with an AR(1) correlation structure on the repeated measures over time , 2009 .

[4]  J. Lindsey,et al.  Multivariate Elliptically Contoured Distributions for Repeated Measurements , 1999, Biometrics.

[5]  K. Lange,et al.  An MM Algorithm for Multicategory Vertex Discriminant Analysis , 2008 .

[6]  Arjun K. Gupta,et al.  Elliptically contoured models in statistics , 1993 .

[7]  P. Kroonenberg.  Applied Multiway Data Analysis , 2008 .

[8]  Anuradha Roy,et al.  Discrimination with jointly equicorrelated multi-level multivariate data , 2007, Adv. Data Anal. Classif..

[9]  Ricardo Leiva,et al.  Linear discrimination with equicorrelated training vectors , 2007 .

[10]  G. Chaudhuri,et al.  Bhattacharyya distance based linear discriminant function for stationary time series , 1991 .

[11]  Myriam Herrera,et al.  Generalización de la distancia de mahalanobis para el análisis discriminante lineal en poblaciones con matrices de covarianza desiguales , 1999 .

[12]  T. W. Anderson,et al.  Statistical Inference in Elliptically Contoured and Related Distributions , 1990 .

[13]  K. Lange,et al.  Multicategory vertex discriminant analysis for high-dimensional data , 2010, 1101.0952.

[14]  G. McLachlan.  Discriminant Analysis and Statistical Pattern Recognition , 1992 .

[15]  Vasil Simeonov,et al.  Modeling of environmental four-way data from air quality control , 2005 .

[16]  Richard A. Johnson,et al.  Applied Multivariate Statistical Analysis , 1983 .

[17]  Bülent Yener,et al.  Multiway modeling and analysis in stem cell systems biology , 2008, BMC Systems Biology.

[18]  A. Kshirsagar,et al.  Distances between normal populations when covariance matrices are unequal , 1994 .

[19]  Selecting variables for discrimination when covariance matrices are unequal , 1994 .

[20]  Arjun K. Gupta,et al.  Array Variate Random Variables with Multiway Kro- necker Delta Covariance Matrix Structure , 2011 .

[21]  Anuradha Roy,et al.  Linear discrimination for multi-level multivariate data with separable means and jointly equicorrela , 2011 .

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

[23]  Kai-Tai Fang,et al.  Maximum‐likelihood estimates and likelihood‐ratio criteria for multivariate elliptically contoured distributions , 1986 .