Dr. Hackney STA Solutions pg 138

Dr. Hackney STA Solutions pg 138 - Second Edition 8-17...

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

View Full Document Right Arrow Icon
Second Edition 8-17 because the cross term is zero. Performing a similar operation on the Y sum yields ˆ σ 2 0 ˆ σ 2 = ( x i - ¯ x ) 2 + ( y i - ¯ y ) 2 + nm n + m x - ¯ y ) 2 ˆ σ 2 = n + m + nm n + m x - ¯ y ) 2 ˆ σ 2 . Because ˆ σ 2 = n + m - 2 n + m S 2 p , large values of ˆ σ 2 0 . ˆ σ 2 are equivalent to large values of (¯ x - ¯ y ) 2 . S 2 p and large values of | T | . Hence, the LRT is the two-sample t -test. b. T = ¯ X - ¯ Y q S 2 p (1 /n + 1 /m ) = ( ¯ X - ¯ Y ) . p σ 2 (1 /n + 1 /m ) q [( n + m - 2) S 2 p 2 ] / ( n + m - 2) . Under H 0 , ( ¯ X - ¯ Y ) n(0 2 (1 /n +1 /m )). Under the model, ( n - 1) S 2 X 2 and ( m - 1) S 2 Y 2 are independent χ 2 random variables with ( n - 1) and ( m - 1) degrees of freedom. Thus, ( n + m - 2) S 2 p 2 = ( n - 1) S 2 X 2 + ( m - 1) S 2 Y 2 χ 2 n + m - 2 . Furthermore, ¯ X - ¯ Y is independent of S 2 X and S 2 Y , and, hence, S 2 p . So T t n + m - 2 . c. The two-sample
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/03/2012 for the course STA 1014 taught by Professor Dr.hackney during the Spring '12 term at UNF.

Ask a homework question - tutors are online