STA302H1 Midterm: UTSG STA 302 testf07
Document Summary
Sta 302 h1f / 1001 hf fall 2007. Instructions: time: 90 minutes, aids allowed: calculator, a table of values from the t distribution is on the last page (page 8), total points: 50 b1 = p(xi x)(yi y ) 1p(xi x)2 = p( yi y )2. 2{ yh} = var( yh) = 2(cid:18) 1 n + (xh x)2 r = p(xi x)(yi y ) pp(xi x)2p(yi y )2. P(xi x)2(cid:19) 2{pred} = var(yh yh) = 2(cid:18)1 + 1. Working-hotelling coe cient: w = p2 f2,n 2; n + (xh x)2. 1: the following questions require derivations of results for the simple linear regression model. i=1 eixi = 0. Justify your answer. i=1 ei = 0 and pn what is pn (b) (5 marks) show that the total sum of squares in a regression can be decomposed as n. You may use any results that were derived in lecture. (c) (5 marks) assume that the xi are non-random.
