Exact robustness studies of the test of independence based on four multivariate criteria and their distribution problems under violations

作者: K. C. S. Pillai , Yu-Sheng Hsu

DOI: 10.1007/BF02480267

关键词:

摘要: Exact robustness studies against non-normality have been carried out for test of independence based on the four multivariate criteria: Hotelling's trace,U (p) , Pillai's trace,V Wilks' criterion,W and Roy's largest root,L . The density functions ofU ,W andL obtained in canonical correlation case further moments m.g.f. ofV derived. All study is distribution characteristic roots under violations. Numerical results power function tabulated two-roots case. Slight does not affect seriously.V (2) found to be most robust nonnormality.

参考文章(8)
K. V. MARDIA, Measures of multivariate skewness and kurtosis with applications Biometrika. ,vol. 57, pp. 519- 530 ,(1970) , 10.1093/BIOMET/57.3.519
A. G. Constantine, Some Non-Central Distribution Problems in Multivariate Analysis Annals of Mathematical Statistics. ,vol. 34, pp. 1270- 1285 ,(1963) , 10.1214/AOMS/1177703863
A. G. Constantine, The Distribution of Hotelling's Generalised $T_0^2$ Annals of Mathematical Statistics. ,vol. 37, pp. 215- 225 ,(1966) , 10.1214/AOMS/1177699611
K. C. S. Pillai, Yu-Sheng Hsu, The distribution of the characteristic roots ofS 1 S 2 −1 under violations in the complex case and power comparisons of four tests Annals of the Institute of Statistical Mathematics. ,vol. 31, pp. 445- 463 ,(1979) , 10.1007/BF02480301
Chester L. Olson, Comparative Robustness of Six Tests in Multivariate Analysis of Variance Journal of the American Statistical Association. ,vol. 69, pp. 894- 908 ,(1974) , 10.1080/01621459.1974.10480224
K. C. S. Pillai, The Distribution of the Characteristic Roots of $S_1S_2^{-1}$ Under Violations Annals of Statistics. ,vol. 3, pp. 773- 779 ,(1975) , 10.1214/AOS/1176343144