STAT244.Lecture.05.06 9

STAT244.Lecture.05.06 9 - Var ( y i ) = λ i ; E ( y i y j...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
Blind-Factor Models I Linear factor models: R t = Bf t + a t ; both B and f are unknown. Let Cov ( R t ) = Ω; Use PCA: Σ = P N i =1 λ i v i v 0 i , where λ i ’s are eigenvalues and v i ’s are corresponding eigenvectors; y i = v 0 i R , i = 1 , 2 , . . . , N are the transformed variables,
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Var ( y i ) = λ i ; E ( y i y j ) = 0. I Truncate at k ± N ; Results are sensitive to outliers; sensitive to the choice of ‘ k ’....
View Full Document

This note was uploaded on 10/16/2010 for the course STAT 244 taught by Professor Dr.velu during the Summer '10 term at Stanford.

Ask a homework question - tutors are online