×

Sufficient dimension reduction in regressions with categorical predictors. (English) Zbl 1012.62036

Summary: We describe how the theory of sufficient dimension reduction, and a well-known inference method for it (sliced inverse regression), can be extended to regression analyses involving both quantitative and categorical predictor variables. As statistics faces an increasing need for effective analysis strategies for high-dimensional data, the results we present significantly widen the applicative scope of sufficient dimension reduction and open the way for a new class of theoretical and methodological developments.

MSC:

62G08 Nonparametric regression and quantile regression
62H05 Characterization and structure theory for multivariate probability distributions; copulas
62G09 Nonparametric statistical resampling methods
Full Text: DOI

References:

[1] CARROLL, R. J. and LI, K.-C. (1995). Binary regressors in dimension reduction models: A new look at treatment comparisons. Statist. Sinica 5 667-688. · Zbl 0828.62033
[2] CHIAROMONTE, F. and COOK, R. D. (2002). Sufficient dimension reduction and graphics in regression. Ann. Inst. Statist. Math. · Zbl 1047.62066 · doi:10.1023/A:1022411301790
[3] COOK, R. D. (1998). Regression Graphics. Wiley, New York. · Zbl 0903.62001
[4] COOK, R. D. and CRITCHLEY, F. (2000). Identifying regression outliers and mixtures graphically. J. Amer. Statist. Assoc. 95 781-794. JSTOR: · Zbl 0999.62056 · doi:10.2307/2669462
[5] COOK, R. D. and WEISBERG, S. (1991). Discussion of ”Sliced inverse regression for dimension reduction.” J. Amer. Statist. Assoc. 86 328-332. · Zbl 0949.47013
[6] COOK, R. D. and WEISBERG, S. (1994). An Introduction to Regression Graphics. Wiley, New York. · Zbl 0925.62287
[7] COOK, R. D. and WEISBERG, S. (1999a). Graphics in statistical analysis: Is the medium the message? Amer. Statist. 53 29-37.
[8] COOK, R. D. and WEISBERG, S. (1999b). Applied Regression Including Computing and Graphics. Wiley, New York. · Zbl 0928.62045
[9] DAWID, A. P. (1979). Conditional independence in statistical theory (with discussion). J. Roy. Statist. Soc. Ser. B 41 1-31. JSTOR: · Zbl 0408.62004
[10] EATON, M. L. and TYLER, D. E. (1994). The asymptotic distribution of singular values with applications to canonical correlations and correspondence analysis. J. Multivariate Anal. 50 238-264. · Zbl 0805.62020 · doi:10.1006/jmva.1994.1041
[11] LI, K.-C. (1991). Sliced inverse regression for dimension reduction (with discussion). J Amer. Statist. Assoc. 86 316-342. JSTOR: · Zbl 0742.62044 · doi:10.2307/2290563
[12] LI, K.-C. (1992). On principal Hessian directions for data visualization and dimension reduction: Another application of Stein’s lemma. J. Amer. Statist. Assoc. 87 1025-1039. JSTOR: · Zbl 0765.62003 · doi:10.2307/2290640
[13] LI, K.-C. and DUAN, N. (1989). Regression analysis under link violation. Ann. Statist. 17 1009- 1052. · Zbl 0753.62041 · doi:10.1214/aos/1176347254
[14] NEVILL, A. M. and HOLDER, R. L. (1995). Body mass index: A measure of fatness or leanness? British Journal of Nutrition 73 507-516.
[15] SCHOTT, J. (1994). Determining the dimensionality in sliced inverse regression. J. Amer. Statist. Assoc. 89 141-148. JSTOR: · Zbl 0791.62069 · doi:10.2307/2291210
[16] VELILLA, S. (1998). Assessing the number of linear components in a general regression problem. J. Amer. Statist. Assoc. 93 1088-1098. JSTOR: · Zbl 1063.62553 · doi:10.2307/2669852
[17] UNIVERSITY PARK, PENNSYLVANIA 16802 E-MAIL: chiaro@stat.psu.edu R. D. COOK SCHOOL OF STATISTICS 1994 BUFORD AVENUE UNIVERSITY OF MINNESOTA ST. PAUL, MINNESOTA 55108 E-MAIL: dennis@stat.umn.edu B. LI DEPARTMENT OF STATISTICS PENNSYLVANIA STATE UNIVERSITY 326 THOMAS BUILDING UNIVERSITY PARK, PENNSYLVANIA 16802 E-MAIL: bing@stat.psu.edu
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.