Fdist - n 2-1) S 2 2 σ 2 2 , then Z 1 and Z 2 are...

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

View Full Document Right Arrow Icon
Statistics 351 (Fall 2007) Fisher’s F -distribution and Statistical Hypothesis Testing For Problem #4 on page 27 you are asked to manipulate Fisher’s F -distribution. The F -distribution arises in the following context. (See Section 10.9 in the Stat 251 textbook by Wackerly, et al.) Let Y 1 ,...,Y n 1 be i.i.d. N ( μ 1 2 1 ), and let X 1 ,...,X n 2 be i.i.d. N ( μ 2 2 2 ) with both μ i and σ 2 i unknown. Suppose that we wish to test H 0 : σ 2 1 = σ 2 2 vs. H A : σ 2 1 > σ 2 2 . The likelihood ratio test gives the rejection region as RR = ± S 2 1 S 2 2 > k ² where k is a suitably chosen constant, S 2 1 = 1 n 1 - 1 n 1 X j =1 ( Y j - Y ) 2 with Y = 1 n 1 n 1 X j =1 Y j , and S 2 2 = 1 n 2 - 1 n 2 X j =1 ( X j - X ) 2 with X = 1 n 2 n 2 X j =1 X j . Fact. If Z 1 = ( n 1 - 1) S 2 1 σ 2 1 and Z 2 = (
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: n 2-1) S 2 2 σ 2 2 , then Z 1 and Z 2 are independent random variables with Z i ∈ χ 2 ( n i ). If F = Z 1 / ( n 1-1) Z 2 / ( n 2-2) = ( n 1-1) S 2 1 σ 2 1 ( n 1-1) ( n 2-1) S 2 2 σ 2 2 ( n 2-1) = S 2 1 /σ 2 1 S 2 2 /σ 2 2 = S 2 1 σ 2 2 S 2 2 σ 2 1 , then F has the F-distribution with ( n 1-1) numerator degrees-of-freedom and ( n 2-1) denominator degrees-of-freedom. This is written as F ∈ F ( n 1-1 ,n 2-1). Problem #10 on page 28 asks you to verify this fact....
View Full Document

This note was uploaded on 03/26/2012 for the course STAT 351 taught by Professor Michaelkozdron during the Fall '08 term at University of Regina.

Ask a homework question - tutors are online