Testing linear hypothesis of high-dimensional means with unequal covariance matrices

다국어 초록 (Multilingual Abstract)

In this paper, we propose a new scalar-transformation-invariant test for linear hypothesis on mean vectors of normal population with unequal covariance matrices in high-dimensional data. The asymptotic null and non-null distributions of our new test are obtained under some regularity conditions. The performance of the proposed test is conducted by numerical simulation and a real data example, which illustrates our new test outperforms competitors in the considered cases. Moreover, numerical studies show that our new test can also be applied to non-normal data.

참고문헌 (Reference)

1 Aoshima, M., "Two-stage procedures for high-dimensional data" 30 : 356-399, 2011

2 Feng, L., "Two-sample Behrens-Fisher problem for high dimensional data" 25 : 1297-1312, 2015

3 Cai, T., "Two sample test of high dimensional means under dependence" 76 : 349-372, 2014

4 Srivastava, M., "Tests for multivariate analysis of variance in high dimension under non-normality" 115 : 204-216, 2013

5 Lehmann, E. L., "Testing statistical hypotheses" Springer 2008

6 Nishiyama, T., "Testing linear hypotheses of mean vectors for highdimension data with unequal covariance matrices" 143 : 1898-1911, 2013

7 Yamada, T., "Testing homogeneity of mean vectors under heteroscedasticity in high-dimension" 139 : 7-27, 2015

8 Li, H., "Test on the linear combinations of mean vectors in high-dimensional data" 26 : 188-208, 2017

9 Srivastava, M., "Some tests concerning the covariance matrix in high dimensional data" 35 : 251-272, 2005

10 Schott, J., "Some high-dimensional tests for a one-way MANOVA" 98 : 1825-1839, 2007

11 Locantore, N., "Robust principal component analysis for functional data" 8 : 1-73, 1999

12 Zhang, J., "Linear hypothesis testing in high-dimensional one-way MANOVA" 155 : 200-216, 2017

13 Dandan Jiang, "Likelihood-based tests on moderate-high-dimensional mean vectors with unequal covariance matrices" 한국통계학회 46 (46): 451-461, 2017

14 Wang, R., "Least favorable direction test for multivariate analysis of variance in high dimension" 31 : 723-747, 2021

15 Cai, T., "High-dimensional sparse MANOVA" 131 : 174-196, 2014

16 Zhou, B., "High-dimensional general linear hypothesis testing under heteroscedasticity" 188 : 36-54, 2017

17 Bai, Z., "Efect of high dimension : By an example of a two sample problem" 6 : 311-329, 1996

18 Fujikoshi, Y., "Asymptotic results of a high dimensional MANOVA test and power comparisons when the dimension is large compared to the sample size" 34 : 19-26, 2004

19 Aoshima, M., "Asymptotic normality for inference on multisample, high-dimensional mean vectors under mild conditions" 17 : 419-439, 2015

20 Anderson, T., "An introduction to multivariate statistical analysis" Wiley 2003

21 Chen, S., "A two-sample test for high-dimensional data with applications to gene-set testing" 38 : 808-835, 2010

22 Gregory, K. B., "A two-sample test for equality of means in high dimension" 110 : 837-849, 2015

23 Srivastava, M., "A two sample test in high dimensional data" 114 : 349-358, 2013

24 Cao, M., "A test on linear hypothesis of k-sample means in high-dimensional data" 13 : 27-36, 2020

25 Srivastava, M., "A test for the mean vector with fewer observations than the dimension under nonnormality" 100 : 518-532, 2009

26 Srivastava, M., "A test for the mean vector with fewer observations than the dimension" 99 : 386-402, 2008

27 Park, J., "A test for the mean vector in large dimension and small samples" 143 : 929-943, 2013

28 Cao, M., "A test for the k sample Behrens-Fisher problem in high dimensional data" 201 : 86-102, 2019

29 Zhang, L., "A simple scale-invariant two-sample test for high-dimensional data" 14 : 131-144, 2020

30 Feng, L., "A note on high-dimensional two-sample test" 105 : 29-36, 2015

31 Zhu, T., "A new k-nearest neighbors classifer for functional data"