A homogeneity test of large dimensional covariance matrices under non-normality

M. Rauf Ahmad

Kybernetika (2018)

  • Volume: 54, Issue: 5, page 908-920
  • ISSN: 0023-5954

Abstract

top
A test statistic for homogeneity of two or more covariance matrices is presented when the distributions may be non-normal and the dimension may exceed the sample size. Using the Frobenius norm of the difference of null and alternative hypotheses, the statistic is constructed as a linear combination of consistent, location-invariant, estimators of trace functions that constitute the norm. These estimators are defined as U -statistics and the corresponding theory is exploited to derive the normal limit of the statistic under a few mild assumptions as both sample size and dimension grow large. Simulations are used to assess the accuracy of the statistic.

How to cite

top

Ahmad, M. Rauf. "A homogeneity test of large dimensional covariance matrices under non-normality." Kybernetika 54.5 (2018): 908-920. <http://eudml.org/doc/294840>.

@article{Ahmad2018,
abstract = {A test statistic for homogeneity of two or more covariance matrices is presented when the distributions may be non-normal and the dimension may exceed the sample size. Using the Frobenius norm of the difference of null and alternative hypotheses, the statistic is constructed as a linear combination of consistent, location-invariant, estimators of trace functions that constitute the norm. These estimators are defined as $U$-statistics and the corresponding theory is exploited to derive the normal limit of the statistic under a few mild assumptions as both sample size and dimension grow large. Simulations are used to assess the accuracy of the statistic.},
author = {Ahmad, M. Rauf},
journal = {Kybernetika},
keywords = {high-dimensional inference; covariance testing; $U$-statistics; non-normality},
language = {eng},
number = {5},
pages = {908-920},
publisher = {Institute of Information Theory and Automation AS CR},
title = {A homogeneity test of large dimensional covariance matrices under non-normality},
url = {http://eudml.org/doc/294840},
volume = {54},
year = {2018},
}

TY - JOUR
AU - Ahmad, M. Rauf
TI - A homogeneity test of large dimensional covariance matrices under non-normality
JO - Kybernetika
PY - 2018
PB - Institute of Information Theory and Automation AS CR
VL - 54
IS - 5
SP - 908
EP - 920
AB - A test statistic for homogeneity of two or more covariance matrices is presented when the distributions may be non-normal and the dimension may exceed the sample size. Using the Frobenius norm of the difference of null and alternative hypotheses, the statistic is constructed as a linear combination of consistent, location-invariant, estimators of trace functions that constitute the norm. These estimators are defined as $U$-statistics and the corresponding theory is exploited to derive the normal limit of the statistic under a few mild assumptions as both sample size and dimension grow large. Simulations are used to assess the accuracy of the statistic.
LA - eng
KW - high-dimensional inference; covariance testing; $U$-statistics; non-normality
UR - http://eudml.org/doc/294840
ER -

References

top
  1. Ahmad, M. R., 10.1111/sjos.12262, Scand. J. Stat. 44 (2017b), 500-523. MR3658524DOI10.1111/sjos.12262
  2. Ahmad, M. R., 10.1080/03610926.2015.1073310, Comm. Stat. Theory Methods 46 (2017a), 3738-3753. MR3590835DOI10.1080/03610926.2015.1073310
  3. Ahmad, M. R., 10.3103/s1066530716020034, Math. Meth. Stat. 25 (2016), 121-132. MR3519645DOI10.3103/s1066530716020034
  4. Anderson, T.W., An Introduction to Multivariate Statistical Analysis. Third edition., Wiley, NY 2003. MR1990662
  5. Aoshima, M., Yata, K., 10.1080/07474946.2011.619088, Seq. An. 30 (2011), 356-399. MR2855952DOI10.1080/07474946.2011.619088
  6. Cai, T., Liu, W., Xia, Y., 10.1080/01621459.2012.758041, J. Amer. Statist. Assoc. 108 (2013), 265-277. MR3174618DOI10.1080/01621459.2012.758041
  7. Fujikoshi, Y., Ulyanov, V. V., Shimizu, R., Multivariate statistics: High-dimensional and large-sample approximations., Wiley, NY 2010. MR2640807
  8. Hájek, J., Šidák, Z., Sen, P. K., Theory of Rank Tests., Academic Press, SD 1999. Zbl0944.62045MR1680991
  9. Kim, T. Y., Luo, Z-M., Kim, C., 10.1080/10485252.2011.556193, J. Nonparam. Stat. 23 (2011), 683-699. MR2836284DOI10.1080/10485252.2011.556193
  10. Koroljuk, V. S., Borovskich, Y. V., 10.1007/978-94-017-3515-5, Kluwer Academic Press, Dordrecht 1994. MR1472486DOI10.1007/978-94-017-3515-5
  11. Lee, A. J., U -statistics: Theory and Practice., CRC Press, Boca Raton 1990. 
  12. Lehmann, E. L., 10.1007/b98855, Springer, NY 1999. MR1663158DOI10.1007/b98855
  13. Li, J., Chen, S. X., 10.1214/12-aos993, Ann. Stat. 40 (2012), 908-940. MR2985938DOI10.1214/12-aos993
  14. Liu, B., Xu, L., Zheng, S., Tian, G-L., 10.1016/j.jmva.2014.06.008, J. Multiv. An. 131 (2014), 293-308. MR3252651DOI10.1016/j.jmva.2014.06.008
  15. Mikosch, T., 10.1007/bf02213365, J. Theoret. Prob. 7 (1991), 147-173. MR1256396DOI10.1007/bf02213365
  16. Mikosch, T., 10.1006/jmva.1993.1072, J. Multiv. An. 47 (1993), 82-102. MR1239107DOI10.1006/jmva.1993.1072
  17. Muirhead, R. J., 10.1002/9780470316559, Wiley, NY 2005 MR0652932DOI10.1002/9780470316559
  18. Pinheiro, A., Sen, K., Pinheiro, H. P., 10.1016/j.jmva.2009.01.007, J. Multiv. An. 100 (2009), 1645-1656. MR2535376DOI10.1016/j.jmva.2009.01.007
  19. Qiu, Y., Chen, S. X., 10.1214/12-aos1002, Ann. Stat. 40 (2012) 1285-1314. MR3015026DOI10.1214/12-aos1002
  20. Schott, J. R., 10.1016/j.csda.2007.03.004, Computat. Statist. Data Analysis 51 (2007), 6535-6542. MR2408613DOI10.1016/j.csda.2007.03.004
  21. Seber, G. A. F., 10.1002/9780470316641, Wiley, NY 2004. MR0746474DOI10.1002/9780470316641
  22. Sen, P. K., Robust statistical inference for high-dimensional data models with applications in genomics., Aust. J. Stat. 35 (2006), 197-214. 
  23. Serfling, R. J., 10.1002/9780470316481, Wiley, Weinheim 1980. MR0595165DOI10.1002/9780470316481
  24. Srivastava, M. S., Yanagihara, H., 10.1016/j.jmva.2009.12.010, J. Multiv. An. 101, 1319-1329. MR2609494DOI10.1016/j.jmva.2009.12.010
  25. Vaart, A. W. van der, 10.1017/cbo9780511802256, Cambridge University Press, 1998. MR1652247DOI10.1017/cbo9780511802256
  26. Zhong, P-S., Chen, S. X., 10.1198/jasa.2011.tm10284, J. Amer. Statist. Assoc. 106 (2011), 260-274. MR2816719DOI10.1198/jasa.2011.tm10284

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.