In this paper, a method for multivariate testing based on low-dimensional, data-dependent, linear scores is proposed. The new approach reduces the dimensionality of observations and increases the stability of the solutions. The method is reliable, even if there are many redundant variables. As a key feature, the score coefficients are chosen such that a left-spherical distribution of the scores is reached under the null hypothesis. Therefore, well-known tests become applicable in high-dimensional situations, too. The presented strategy is an alternative to least squares and maximum likelihood approaches. In a natural way, standard problems of multivariate analysis thus induce the occurrence of left-spherical, nonnormal distributions. Hence, new fields of application are opened up to the generalized multivariate analysis. The proposed methodology is not restricted to normally distributed data, but can also be extended to any left-spherically distributed observations.
References
Anderson, T. W. (1993). Nonnormal multivariate distributions: inference based on elliptically contoured distributions. In Multivariate Analy sis: Future Directions (C. R. Rao, ed.) 1-24. North-Holland, Amsterdam. MR94j:62118 0798.62068Anderson, T. W. (1993). Nonnormal multivariate distributions: inference based on elliptically contoured distributions. In Multivariate Analy sis: Future Directions (C. R. Rao, ed.) 1-24. North-Holland, Amsterdam. MR94j:62118 0798.62068
Anderson, T. W., Fang, K.-T. and Hsu, H. (1990). Maximum-likelihood estimates and likelihoodratio criteria for multivariate elliptically contoured distributions. In Statistical Inference in Elliptically Contoured and Related Distributions (K.-T. Fang and T. W. Anderson, eds.) 217-223. Allerton Press, New York. MR1066905Anderson, T. W., Fang, K.-T. and Hsu, H. (1990). Maximum-likelihood estimates and likelihoodratio criteria for multivariate elliptically contoured distributions. In Statistical Inference in Elliptically Contoured and Related Distributions (K.-T. Fang and T. W. Anderson, eds.) 217-223. Allerton Press, New York. MR1066905
Barlow, R. E., Bartholomew, D. J., Bremner, J. M. and Brunk, H. D. (1972). Statistical Inference Under Order Restrictions. Wiley, New York. MR48:5229 0246.62038Barlow, R. E., Bartholomew, D. J., Bremner, J. M. and Brunk, H. D. (1972). Statistical Inference Under Order Restrictions. Wiley, New York. MR48:5229 0246.62038
Dunnett, C. W. (1955). A multiple comparison procedure for comparing several treatments with a control. J. Amer. Statist. Assoc. 50 1096-1121. 0066.12603Dunnett, C. W. (1955). A multiple comparison procedure for comparing several treatments with a control. J. Amer. Statist. Assoc. 50 1096-1121. 0066.12603
Dunnett, C. W. and Tamhane, A. C. (1991). Step-down multiple tests for comparing treatments with a control in unbalanced one-way lay out. Statistics in Medicine 10 939-947. Dunnett, C. W. and Tamhane, A. C. (1991). Step-down multiple tests for comparing treatments with a control in unbalanced one-way lay out. Statistics in Medicine 10 939-947.
Gupta, A. K. and Varga, T. (1993). Elliptically Contoured Models in Statistics. Kluwer, Dordrecht. Hsu, H. (1990a). Generalized T2-test for multivariate elliptically contoured distributions. In Statistical Inference in Elliptically Contoured and Related Distributions (K.-T. Fang and T. W. Anderson, eds.) 243-256. Allerton Press, New York. Hsu, H. (1990b). Invariant tests for multivariate elliptically contoured distributions. In Statistical Inference in Elliptically Contoured and Related Distributions (K.-T. Fang and T. W. Anderson, eds.) 257-274. Allerton Press, New York. MR95a:62038 0789.62037Gupta, A. K. and Varga, T. (1993). Elliptically Contoured Models in Statistics. Kluwer, Dordrecht. Hsu, H. (1990a). Generalized T2-test for multivariate elliptically contoured distributions. In Statistical Inference in Elliptically Contoured and Related Distributions (K.-T. Fang and T. W. Anderson, eds.) 243-256. Allerton Press, New York. Hsu, H. (1990b). Invariant tests for multivariate elliptically contoured distributions. In Statistical Inference in Elliptically Contoured and Related Distributions (K.-T. Fang and T. W. Anderson, eds.) 257-274. Allerton Press, New York. MR95a:62038 0789.62037
Kariy a, T. and Sinha, B. K. (1989). Robustness of Statistical Tests. Academic Press, San Diego. Kropf, S., Hothorn, L. A. and L¨auter, J. (1997a). Multivariate many-to-one procedures with applications to pre-clinical trials. Drug Information J. 31 433-447. Kropf, S., L¨auter, J. and Glimm, E. (1997b). Stabilized multivariate procedures in tests and prediction. Unpublished manuscript. MR90k:62118 0699.62033Kariy a, T. and Sinha, B. K. (1989). Robustness of Statistical Tests. Academic Press, San Diego. Kropf, S., Hothorn, L. A. and L¨auter, J. (1997a). Multivariate many-to-one procedures with applications to pre-clinical trials. Drug Information J. 31 433-447. Kropf, S., L¨auter, J. and Glimm, E. (1997b). Stabilized multivariate procedures in tests and prediction. Unpublished manuscript. MR90k:62118 0699.62033
L¨auter, J. (1996). Exact t and F tests for analyzing studies with multiple endpoints. Biometrics 52 964-970. MR98b:62193 0006-341X%28199609%2952%3A3%3C964%3AETAFTF%3E2.0.CO%3B2-6L¨auter, J. (1996). Exact t and F tests for analyzing studies with multiple endpoints. Biometrics 52 964-970. MR98b:62193 0006-341X%28199609%2952%3A3%3C964%3AETAFTF%3E2.0.CO%3B2-6
L¨auter, J., Glimm, E. and Kropf, S. (1996). New multivariate tests for data with an inherent structure. Biometrical J. 38 5-23. MR97f:62100L¨auter, J., Glimm, E. and Kropf, S. (1996). New multivariate tests for data with an inherent structure. Biometrical J. 38 5-23. MR97f:62100
Marcus, R., Peritz, E. and Gabriel, K. R. (1976). On closed testing procedures with special reference to ordered analysis of variance. Biometrika 63 655-660. MR57:7895 0353.62037 0006-3444%28197612%2963%3A3%3C655%3AOCTPWS%3E2.0.CO%3B2-%23Marcus, R., Peritz, E. and Gabriel, K. R. (1976). On closed testing procedures with special reference to ordered analysis of variance. Biometrika 63 655-660. MR57:7895 0353.62037 0006-3444%28197612%2963%3A3%3C655%3AOCTPWS%3E2.0.CO%3B2-%23
O'Brien, P. C. (1984). Procedures for comparing samples with multiple endpoints. Biometrics 40 1079-1087. MR86j:62105 0006-341X%28198412%2940%3A4%3C1079%3APFCSWM%3E2.0.CO%3B2-TO'Brien, P. C. (1984). Procedures for comparing samples with multiple endpoints. Biometrics 40 1079-1087. MR86j:62105 0006-341X%28198412%2940%3A4%3C1079%3APFCSWM%3E2.0.CO%3B2-T
Seber, G. A. F. (1984). Multivariate Observations. Wiley, New York. MR86f:62080 0627.62052Seber, G. A. F. (1984). Multivariate Observations. Wiley, New York. MR86f:62080 0627.62052
Tang, D., Geller, N. L. and Pocock, S. J. (1993). On the design and analysis of randomized clinical trials with multiple endpoints. Biometrics 49 23-30. MR1221403 0775.62313 0006-341X%28199303%2949%3A1%3C23%3AOTDAAO%3E2.0.CO%3B2-QTang, D., Geller, N. L. and Pocock, S. J. (1993). On the design and analysis of randomized clinical trials with multiple endpoints. Biometrics 49 23-30. MR1221403 0775.62313 0006-341X%28199303%2949%3A1%3C23%3AOTDAAO%3E2.0.CO%3B2-Q
