post6 - Chi-square Tests Karl Pearson (1900) 2 Recall: Xi N...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Chi-square Tests Karl Pearson (1900) Recall: X i N ( μ i 2 i ), indep. n X i =1 X i - μ i σ i ! 2 χ 2 ( n ) i.e. (n indep. std normal) 2 χ 2 ( n ) X 1 b ( n, p 1 ) Y n := X 1 - np 1 np 1 (1 - p 1 ) D N (0 , 1) Moreover, Y 2 n D χ 2 (1) i.e. Y n is approximately N (0 , 1) and Y 2 n is ap- proximately χ 2 (1) for large n . 1 Define X 2 = n - X 1 and p 2 =1 - p 1 Then, Q 1 := Y 2 n = ( X 1 - np 1 ) 2 np 1 + ( X 1 - np 1 ) 2 n (1 - p 1 ) = ( X 1 - np 1 ) 2 np 1 + ( X 2 - np 2 ) 2 np 2 χ 2 (1) H 0 : p 1 = p 10 vs. H 1 : p 1 6 = p 10 Under H 0 , Q 1 = ( X 1 - np 10 ) 2 np 10 + ( X 2 - np 20 ) 2 np 20 χ 2 (1) Rejection region= { Q 1 c } This test is equivalent to the Z -test that we usually use. 2 A 1 , ··· ,A k : a partition of sample space A , p i = P (outcome A i ) Repeat the experiment n times and count the frequencies of outcomes in A i X i = frequency of A i , ( X k = n - X 1 -···- X k - 1 ) X 1 , ,X k - 1 multinomial( n, p 1 , ,p k - 1 ) Then, Q k - 1 := k X i =1 ( X i - np i ) 2 np i χ 2 ( k - 1) 3 H 0 : p 1 = p 10 2 = p 20 , k - 1 = p k - 1 , 0 Under H 0 , Q k - 1 = k X i =1 ( X i - np i 0 ) 2 np i 0 χ 2 ( k - 1) Rejection region= { Q k - 1 c } If c
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 09/10/2009 for the course STATS 517 taught by Professor Song during the Fall '07 term at Purdue.

Page1 / 3

post6 - Chi-square Tests Karl Pearson (1900) 2 Recall: Xi N...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online