Title: On minimum average conditional variance method to dimension reduction in
	regression.

by Howell Tong, London School of Economics 
and the University of Hong Kong

Abstract:

We discuss the recently introduced minimum average conditional variance
(MAVE) method to dimension reduction in regression within a
semi-parametric setting. Without any undersmoothing of the nonparametric
estimator of the link function, the MAVE method achieves a faster rate
of convergence for the estimator of the parameters. The MAVE method leads
to a consistent estimation of the dimension of the effective dimension
reduction space.