Information concerning SIR/PHD methods.

Main source: Work of Professor Ker-Chau Li of UCLA

His webpage: web.stat.ucla.edu/~kcli/

Information useful:
(1) His preprint of a book (more than 250 pages) on the topic
"High dimensional data analysis via the SIR/PHD approach"
(Under lecture notes in progress, a pdf file)

(2) His publication list on the topic.

Reading of papers by K.C. Li: 
1. "Sliced inverse regression for dimension reduction", with discussions
Journal of the American Statistical Association (1991), 86, 316-342.

2. On principal Hessian directions for data visualization and dimension 
reduction: another application of Stein's lemma. 
Journal of the American Statistical Association (1992), 87, 1025-1039.


Information on recent development:
1. "An adpative estimation of dimension reduction space" with discussions 
by Xia, Y.m Tong, H., Li, W.K., and Zhu, L.X.
Journal of the Royal Statistical Society, Series B, (2002), 64, 363-410.

2. "A goodness-of-fit test for single-index models" with discussion 
by Xia, Y., Li, W.K., Tong, H., and Zhang, D. 
Statistica Sinica (2004), 1-39.