Dimension reduction for non-elliptically distributed predictors: second-order methods
- 29 April 2010
- journal article
- research article
- Published by Oxford University Press (OUP) in Biometrika
- Vol. 97 (2) , 279-294
Abstract
Many classical dimension reduction methods, especially those based on inverse conditional moments, require the predictors to have elliptical distributions, or at least to satisfy a linearity condition. Such conditions, however, are too strong for some applications. Li and Dong (2009) introduced the notion of the central solution space and used it to modify first-order methods, such as sliced inverse regression, so that they no longer rely on these conditions. In this paper we generalize this idea to second-order methods, such as sliced average variance estimation and directional regression. In doing so we demonstrate that the central solution space is a versatile framework: we can use it to modify essentially all inverse conditional moment-based methods to relax the distributional assumption on the predictors. Simulation studies and an application show a substantial improvement of the modified methods over their classical counterparts.Keywords
This publication has 19 references indexed in Scilit:
- Dimension reduction for nonelliptically distributed predictorsThe Annals of Statistics, 2009
- On Directional Regression for Dimension ReductionJournal of the American Statistical Association, 2007
- Determining the dimension of iterative Hessian transformationThe Annals of Statistics, 2004
- Dimension reduction for conditional mean in regressionThe Annals of Statistics, 2002
- Estimating the Structural Dimension of Regressions Via Parametric Inverse RegressionJournal of the Royal Statistical Society Series B: Statistical Methodology, 2001
- Principal Hessian Directions RevisitedJournal of the American Statistical Association, 1998
- Graphics for Regressions with a Binary ResponseJournal of the American Statistical Association, 1996
- On the Interpretation of Regression PlotsJournal of the American Statistical Association, 1994
- Sliced Inverse Regression for Dimension ReductionJournal of the American Statistical Association, 1991
- On Large-Sample Estimation and Testing in Parametric ModelsInternational Statistical Review, 1990