论文信息 - A Monte Carlo Investigation of the Robustness of Hotelling's One- and Two-Sample T 2 Tests

A Monte Carlo Investigation of the Robustness of Hotelling's One- and Two-Sample T 2 Tests

Abstract The robustness of Hotelling's one- and two-sample tests is investigated by Monte Carlo methods. Samples are presented from uniform, exponential, and lognormal distributions. The results show that the two-sample test is far more robust to departures from normality than the one-sample test, and that the latter may be badly affected by departures due to extreme skewness.

Brian Everitt | B. Everitt

[1] K. Mardia. Measures of multivariate skewness and kurtosis with applications , 1970 .

[2] Olive Jean Dunn,et al. The Robustness of Hotelling's T 2 , 1967 .

[3] G. E. Thomas,et al. Remark AS R19 and Algorithm AS 109: A Remark on Algorithms: AS 63: The Incomplete Beta Integral AS 64: Inverse of the Incomplete Beta Function Ratio , 1977 .

[4] K. Mardia. Assessment of multinormality and the robustness of Hotelling's T^2 test , 1975 .

[5] J. W. Hopkins,et al. Some Empirical Distributions of Bivariate T 2 and Homoscedasticity Criterion M Under Unequal Variance and Leptokurtosis , 1963 .

[6] G. P. Bhattacharjee,et al. Algorithm AS 63: The Incomplete Beta Integral , 1973 .

[7] Bradley Efron,et al. Hotelling's T2 Test Under Symmetry Conditions , 1970 .

[8] J. L. Warner,et al. Methods for Assessing Multivariate Normality , 1973 .

[9] W. Bulgren,et al. A Monte Carlo Investigation of the Robustness of T 2 , 1971 .