A new algorithm for estimating the effective dimension-reduction subspace
arXiv:math/0701887
Abstract
The statistical problem of estimating the effective dimension-reduction (EDR) subspace in the multi-index regression model with deterministic design and additive noise is considered. A new procedure for recovering the directions of the EDR subspace is proposed. Under mild assumptions, -consistency of the proposed procedure is proved (up to a logarithmic factor) in the case when the structural dimension is not larger than 4. The empirical behavior of the algorithm is studied through numerical simulations.