Skip Navigation


Biometrika Advance Access originally published online on August 5, 2007
Biometrika 2007 94(3):603-613; doi:10.1093/biomet/asm044
This Article
Right arrow Abstract Freely available
Right arrow Full Text (PDF)
Right arrow Alert me when this article is cited
Right arrow Alert me if a correction is posted
Services
Right arrow Email this article to a friend
Right arrow Similar articles in this journal
Right arrow Alert me to new issues of the journal
Right arrow Add to My Personal Archive
Right arrow Download to citation manager
Right arrowRequest Permissions
Google Scholar
Right arrow Articles by Li, L.
Right arrow Search for Related Content
Social Bookmarking
Add to CiteULike   Add to Connotea   Add to Del.icio.us  
What's this?

Copyright © 2007 Biometrika Trust

Articles

Sparse sufficient dimension reduction

Lexin Li

Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695, U.S.A.

li{at}stat.ncsu.edu

Received for publication 1 December 2005. Revision received 1 December 2006.

Existing sufficient dimension reduction methods suffer from the fact that each dimension reduction component is a linear combination of all the original predictors, so that it is difficult to interpret the resulting estimates. We propose a unified estimation strategy, which combines a regression-type formulation of sufficient dimension reduction methods and shrinkage estimation, to produce sparse and accurate solutions. The method can be applied to most existing sufficient dimension reduction methods such as sliced inverse regression, sliced average variance estimation and principal Hessian directions. We demonstrate the effectiveness of the proposed method by both simulations and real data analysis.

Key Words: Lasso • Shrinkage sparse estimator • Sufficient dimension reduction



References

    Akaike H. Information theory and an extension of the maximum likelihood principle. In: Second International Symposium on Information Theory—Petrov B. N., Csaki F., eds. (1973) Budapest: Akademia Kiado. 267–81.

    Chen C. H., Li K. C. Can SIR be as popular as multiple linear regression? Statist. Sinica (1998) 8:289–316.

    Chiaromonte F., Cook R. D., Li B. Sufficient dimension reduction in regressions with categorical predictors. Ann. Statist. (2002) 30:475–97.[CrossRef]

    Cook R. D. Graphics for regressions with a binary response. J. Am. Statist. Assoc. (1996) 91:983–92.[CrossRef][ISI]

    Cook R. D. Regression Graphics: Ideas for Studying Regressions Through Graphics (1998a) New York: Wiley.

    Cook R. D. Principal Hessian directions revisited. J. Am. Statist. Assoc. (1998b) 93:84–94.[CrossRef][ISI]

    Cook R. D. Testing predictor contributions in sufficient dimension reduction. Ann. Statist. (2004) 32:1061–92.

    Cook R. D., Critchley F. Identifying outliers and regression mixtures graphically. J. Am. Statist. Assoc. (2000) 95:781–94.[CrossRef][ISI]

    Cook R. D., Li B. Dimension reduction for the conditional mean in regression. Ann. Statist. (2002) 30:455–74.[CrossRef]

    Cook R. D., Ni L. Sufficient dimension reduction via inverse regression: a minimum discrepancy approach. J. Am. Statist. Assoc. (2005) 100:410–28.[CrossRef][ISI]

    Cook R. D., Weisberg S. Discussion of Li (1991). J. Am. Statist. Assoc. (1991) 86:328–32.[CrossRef][ISI]

    Cook R. D., Yin X. Dimension reduction and visualization in discriminant analysis. Aust. New Zeal. J. Statist. (2001) 43:147–77.[CrossRef]

    Efron B., Hastie T., Johnstone I., Tibshirani R. Least angle regression (with Discussion). Ann. Statist. (2004) 32:407–99.[CrossRef]

    Fung W. K., He X., Liu L., Shi P. Dimension reduction based on canonical correlation. Statist. Sinica (2002) 12:1093–113.

    Jolliffe I. T., Trendafilov N. T., Uddin M. A modified principal component technique based on the lasso. J. Comp. Graph. Statist. (2003) 12:531–47.[CrossRef]

    Li K. C. Sliced inverse regression for dimension reduction (with Discussion). J. Am. Statist. Assoc. (1991) 86:316–42.[CrossRef][ISI]

    Li K. C. On principal Hessian directions for data visualization and dimension reduction: another application of Stein's Lemma. Ann. Statist. (1992) 87:1025–39.

    Li L., Nachtsheim C. J. Sparse sliced inverse regression. Technometrics (2006) 48:503–10.[CrossRef][ISI]

    Ni L., Cook R. D., Tsai C. L. A note on shrinkage sliced inverse regression. Biometrika (2005) 92:242–7.[Abstract/Free Full Text]

    Setodji C. M., Cook R. D. K-means inverse regression. Technometrics (2004) 46:421–9.[CrossRef][ISI]

    Tibshirani R. Regression shrinkage and selection via the Lasso. J. R. Statist. Soc. (1996) B 58:267–88.

    Ye Z., Weiss R. E. Using the bootstrap to select one of a new class of dimension reduction methods. J. Am. Statist. Assoc. (2003) 98:968–79.[CrossRef][ISI]

    Yin X., Cook R. D. Dimension reduction for the conditional kth moment in regression. J. R. Statist. Soc. (2002) B 64:159–75.[CrossRef]

    Zou H., Hastie T., Tibshirani R. Sparse principal component analysis. J. Comp. Graph. Statist. (2006) 15:265–86.[CrossRef]

    Zou H., Hastie T., Tibshirani R. On the degrees of freedom of the Lasso. Ann. Statist. (2007) In press.


Add to CiteULike CiteULike   Add to Connotea Connotea   Add to Del.icio.us Del.icio.us    What's this?



This Article
Right arrow Abstract Freely available
Right arrow Full Text (PDF)
Right arrow Alert me when this article is cited
Right arrow Alert me if a correction is posted
Services
Right arrow Email this article to a friend
Right arrow Similar articles in this journal
Right arrow Alert me to new issues of the journal
Right arrow Add to My Personal Archive
Right arrow Download to citation manager
Right arrowRequest Permissions
Google Scholar
Right arrow Articles by Li, L.
Right arrow Search for Related Content
Social Bookmarking
Add to CiteULike   Add to Connotea   Add to Del.icio.us  
What's this?