On consistency and sparsity for sliced inverse regression in high dimensions

Abstract

We provide here a framework to analyze the phase transition phenomenon of slice inverse regression (SIR), a supervised dimension reduction technique introduced by \cite{Li:1991}. Under mild conditions, the asymptotic ratio $\rho =\lim p/n$ is the phase transition parameter and the SIR estimator is consistent if and only if $\rho =0$. When dimension $p$ is greater than $n$, we propose a diagonal thresholding screening SIR (DT-SIR) algorithm. This method provides us with an estimate of the eigen-space of the covariance matrix of the conditional expectation $var(\mathbf{E}[\mathbf{x}|y])$. The desired dimension reduction space is then obtained by multiplying the inverse of the covariance matrix on the eigen-space. Under certain sparsity assumptions on both the covariance matrix of predictors and the loadings of the directions, we prove the consistency of DT-SIR in estimating the dimension reduction space in high dimensional data analysis. Extensive numerical experiments demonstrate superior performances of the proposed method in comparison to its competitors.

49 pages, 4 figures

References in corpus (1)

• Sparse Principal Components Analysis

Cited by in corpus (6)

• On Stein's Identity and Near-Optimal Estimation in High-dimensional Index Models
• Misspecified Nonconvex Statistical Optimization for Phase Retrieval
• High Dimensional Elliptical Sliced Inverse Regression in non-Gaussian Distributions
• Sparse Sliced Inverse Regression Via Lasso
• Robust Variable and Interaction Selection for Logistic Regression and Multiple Index Models
• Optimal Estimation of Slope Vector in High-dimensional Linear Transformation Model