Theoretical properties of Cook's Principal Fitted Components algorithm

Add to your list(s) Download to your calendar using vCal

• Oliver Johnson (University of Bath)
• Friday 31 October 2008, 16:00-17:30
• MR12, CMS, Wilberforce Road, Cambridge, CB3 0WB.

If you have a question about this talk, please contact HoD Secretary, DPMMS.

This talk has been canceled/deleted

I will talk about how to reduce the dimension of the linear regression space. In particular, I will consider the theoretical properties of the estimators resulting from Dennis Cook’s Principal Fitted Components algorithm. I will give sufficient conditions for root(n)-consistency and explain some of the simulation results in Cook’s Fisher Lecture. I will argue further that, under Cook’s model at least, the PFC algorithm outperforms the more standard Principal Components algorithm. (paper to appear in Electronic Journal of Statistics)

This talk is part of the Probability series.

This talk is included in these lists:

This talk is not included in any other list

Note that ex-directory lists are not shown.