×

Classification of higher-order data with separable covariance and structured multiplicative or additive mean models. (English) Zbl 1462.62390

Summary: Although devised in 1936 by Fisher, discriminant analysis is still rapidly evolving, as the complexity of contemporary data sets grows exponentially. Our classification rules explore these complexities by modeling various correlations in higher-order data. Moreover, our classification rules are suitable to data sets where the number of response variables is comparable or larger than the number of observations. We assume that the higher-order observations have a separable variance-covariance matrix and two different Kronecker product structures on the mean vector. In this article, we develop quadratic classification rules among \(g\) different populations where each individual has \(\kappa\)th order \((\kappa \geq 2)\) measurements. We also provide the computational algorithms to compute the maximum likelihood estimates for the model parameters and eventually the sample classification rules.

MSC:

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

References:

[1] Akdemir D., Technical Report. Department of Mathematics and Statistics at the Bowling Green State University (2011)
[2] DOI: 10.1016/S0165-1684(02)00474-7 · Zbl 1144.90448 · doi:10.1016/S0165-1684(02)00474-7
[3] DOI: 10.1198/016214502753479248 · Zbl 1073.62576 · doi:10.1198/016214502753479248
[4] DOI: 10.1080/00949659908811970 · Zbl 0960.62056 · doi:10.1080/00949659908811970
[5] DOI: 10.1093/biostatistics/kxm045 · Zbl 1143.62076 · doi:10.1093/biostatistics/kxm045
[6] DOI: 10.1080/03610929408831436 · Zbl 0875.62274 · doi:10.1080/03610929408831436
[7] DOI: 10.1007/b98818 · doi:10.1007/b98818
[8] DOI: 10.1214/11-BA601 · Zbl 1330.62258 · doi:10.1214/11-BA601
[9] DOI: 10.1093/biostatistics/kxq069 · Zbl 05932590 · doi:10.1093/biostatistics/kxq069
[10] DOI: 10.1007/1-4020-3419-9 · doi:10.1007/1-4020-3419-9
[11] DOI: 10.1002/9780470238004 · Zbl 1160.62002 · doi:10.1002/9780470238004
[12] DOI: 10.1007/s00362-009-0259-z · Zbl 1247.62155 · doi:10.1007/s00362-009-0259-z
[13] DOI: 10.1186/1471-2105-7-235 · Zbl 05326038 · doi:10.1186/1471-2105-7-235
[14] DOI: 10.3103/S1066530710010060 · doi:10.3103/S1066530710010060
[15] DOI: 10.1016/j.jmva.2006.06.002 · Zbl 1112.62057 · doi:10.1016/j.jmva.2006.06.002
[16] DOI: 10.1016/j.jspi.2008.11.013 · Zbl 1162.62059 · doi:10.1016/j.jspi.2008.11.013
[17] DOI: 10.1016/j.jspi.2010.12.001 · Zbl 1207.62137 · doi:10.1016/j.jspi.2010.12.001
[18] Leiva R., The University of Texas at San Antonio, College Of Business (2012)
[19] DOI: 10.1016/j.csda.2011.10.007 · Zbl 1243.62094 · doi:10.1016/j.csda.2011.10.007
[20] DOI: 10.3389/fpsyg.2010.00146 · doi:10.3389/fpsyg.2010.00146
[21] DOI: 10.1016/j.spl.2005.04.020 · Zbl 1071.62052 · doi:10.1016/j.spl.2005.04.020
[22] DOI: 10.1016/j.cam.2012.09.017 · Zbl 1255.65029 · doi:10.1016/j.cam.2012.09.017
[23] DOI: 10.1002/0471725293 · doi:10.1002/0471725293
[24] DOI: 10.1016/j.jmva.2011.05.015 · Zbl 1354.60015 · doi:10.1016/j.jmva.2011.05.015
[25] DOI: 10.1016/0167-7152(94)00048-4 · Zbl 0825.62545 · doi:10.1016/0167-7152(94)00048-4
[26] DOI: 10.1080/03610929408831463 · Zbl 0825.62240 · doi:10.1080/03610929408831463
[27] DOI: 10.1080/02664763.2012.663346 · Zbl 1473.62227 · doi:10.1080/02664763.2012.663346
[28] Roy A., Proc. Amer. Statist. Assoc. pp 2157– (2007)
[29] Roy A., J. Appl. Statist. Sci. 12 (2) pp 91– (2003)
[30] DOI: 10.1016/j.jspi.2004.04.012 · Zbl 1066.62069 · doi:10.1016/j.jspi.2004.04.012
[31] DOI: 10.1007/s11634-007-0013-0 · Zbl 1182.62142 · doi:10.1007/s11634-007-0013-0
[32] Roy A., J. Appl. Statist. Sci. 15 (3) pp 283– (2007)
[33] Roy A., Proc. Amer. Statist. Assoc. Statistical Computing Section pp 1940– (2008)
[34] DOI: 10.1080/03610926.2011.615971 · Zbl 1271.62121 · doi:10.1080/03610926.2011.615971
[35] DOI: 10.3103/S1066530708040066 · Zbl 1231.62101 · doi:10.3103/S1066530708040066
[36] Yu L., Proc. Twentieth Int. Conf. Mach. Learn. (ICML-2003). (2003)
[37] Zhu D., IEEE Workshop Statist. Signal Process. Proc. 1628818 pp 1420– (2005)
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. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.