Discrimination with jointly equicorrelated multi-level multivariate data. (English) Zbl 1182.62142

Summary: We study a linear as well as a quadratic discriminant function for multi-level multivariate repeated measurement data under the assumption of multivariate normality. We assume that the \(m\)-variate observations have a jointly equicorrelated covariance structure in addition to a Kronecker product structure on the mean vector. The new discriminant functions are very effective in discriminating individuals when the number of observations is very small. The proposed classification rules are demonstrated on a real data set. The error rates of the proposed classification rules are found to be much less than the error rates of the traditional classification rules, when in fact the traditional classification rules fail most of the time owing to the small sample sizes.


62H30 Classification and discrimination; cluster analysis (statistical aspects)
62H12 Estimation in multivariate analysis
Full Text: DOI


[1] Anderson TW (2003). An introduction to multivariate statistical analysis, 3rd edn. Wiley, New Jersey
[2] Bartlett MS (1951). An inverse matrix adjustment arising in discriminant analysis. Ann Math Statist 22(1): 107–111 · Zbl 0042.38203
[3] Choi SC (1972). Classification of multiple observed data. Biom J 14: 8–11 · Zbl 0276.62057
[4] Gupta AK (1980). On a multivariate statistical classification model. In: Gupta, RP (eds) Multivariate statistical analysis, pp 83–93. Amsterdam, North Holland
[5] Gupta AK (1986). On a classification rule for multiple measurements. Comput Math Appl 12A: 301–308 · Zbl 0608.62070
[6] Johnson RA and Wichern DW (2007). Applied multivariate statistical analysis. 6th edn. Pearson Prentice Hall, New Jersey · Zbl 1269.62044
[7] Krzanowski WJ (1993). Antedependence models in discriminant analysis of high-dimansional spectroscopic data. In: Cuadras, CM and Rao, CR (eds) Multivariate analysis: future directions, vol. 2, pp 301–308. Elsevier, Amsterdam
[8] Krzanowski WJ (1999). Antedependence models in the analysis of multi-group high-dimensional data. J Appl Stat 26(1): 59–67 · Zbl 0939.62057
[9] Leiva R (2007). Linear discrimination with equicorrelated training vectors. J Multivariate Anal 98: 384–409 · Zbl 1112.62057
[10] Leiva RA and Herrera M (1999). Generalización de la distancia de Mahalanobis para el análisis discriminante lineal en poblaciones conmatrices de covarianza desiguales. Revista de la Sociedad Argentina de Estad ística, 3: 64–85
[11] McLachlan GJ (1992). Discriminant analysis and statistical pattern recognition. Wiley, New York
[12] Ritter G and Gallegos M T (2002). Bayesian object identification: variants. J Multivariate Anal 81(2): 301–334 · Zbl 1011.62011
[13] Roy A (2006). A new classification rule for incomplete doubly multivariate data using mixed effects model with performance Comparisons on the Imputed Data. Stat Med 25(10): 1715–1728
[14] Roy A and Khattree R (2005a). On discrimination and classification with multivariate repeated measures data. J Statist Plann Inf 134(2): 462–485 · Zbl 1066.62069
[15] Roy A and Khattree R (2005b). Classification based on multivariate repeated measures with time effect on mean vector and an AR(1) correlation structure on the repeated measures. Calcutta Stat Assoc Bull 57: 49–65 · Zbl 1170.62344
[16] Roy A and Khattree R (2007). Classification of multivariate repeated measures data with temporal autocorrelation. J Appl Stat Sci 15(3): 283–294
[17] Seber GAE (1984). Multivariate observations. Wiley, New York · Zbl 0627.62052
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.