STAT 602 Texas A&M

ASSIGNMENT 2 (Due: Feb 21st, 2001) (1) Let X be an n p + 1 matrix with rank p + 1. Suppose the rst column of X is vector of 1s say 1. Then show that 1 (i) P 1=1 where P is the projection matrix X(X T X) X T . (ii) J/n, P-J/n and I-P are idempotent a

ASSIGNMENT 4 1. Prove Sherman-Morrison-Woodbury Theorem, which is for a square nonsingular matrix A (say p p) and a p-dimensional column vector z (A - zz T )-1 = A-1 + A-1 zz T A-1 . 1 - z T A-1 z 2. In the regression diagnostic framework (it means

Preface Introductory Guide to S-Plus Final Version B.D. Ripley Professor of Applied Statistics, University of Oxford e-mail: ripley@stats.ox.ac.uk This guide was originally written for graduate students in Statistics at the University of Oxford. Th

HOMEWORK #2, due Feb. 20 PROBLEM #1: Consider the model, Yi = 0 + 1 Xi + i , i = 1, 2, , n. Suppose now we rewrite the model at its centered form, Yi = 0 + 1 Xi + i , where Xi = Xi X and X is the sample mean of Xs. Let denote (0 , 1 )t (a) Writ

Preface Introductory Guide to S-Plus Final Version B.D. Ripley Professor of Applied Statistics, University of Oxford e-mail: ripley@stats.ox.ac.uk This guide was originally written for graduate students in Statistics at the University of Oxford. Th