sta 2006 1011_chap8

# sta 2006 1011_chap8 - Elementary Nonparametric Methods Dr....

This preview shows pages 1–4. Sign up to view the full content.

Elementary Nonparametric Methods Dr. Phillip YAM 2010/2011 Spring Semester Reference: Chapter 8: Section 1 of “Nonparametric Methods” by Hogg and Tanis.

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

View Full Document
Section 8.1 Chi-square Goodness-Of-Fit Tests I Chi-square statistic (Karl Pearson (1900)): to test the appropriateness of diﬀerent probabilistic models (as a competitor of the Kolmogorov-Smirnov test). I Y 1 follows b ( n , p 1 ) with 0 < p 1 < 1. Z = Y 1 - np 1 p np 1 (1 - p 1 ) is approximately N (0 , 1) for large n . And hence Q 1 = Z 2 is approximately χ 2 (1). I Let Y 2 = n - Y 1 and p 2 = 1 - p 1 , Q 1 = ( Y 1 - np 1 ) 2 np 1 (1 - p 1 ) = ( Y 1 - np 1 ) 2 np 1 + ( Y 1 - np 1 ) 2 n (1 - p 1 ) . ( Y 1 - np 1 ) 2 = ( n - Y 1 - n [1 - p 1 ]) 2 = ( Y 2 - np 2 ) 2 , Q 1 = ( Y 1 - np 1 ) 2 np 1 + ( Y 2 - np 2 ) 2 np 2 . I Q 1 measures the “closeness” of the observed numbers to the corresponding expected numbers.
Section 8.1 Chi-square Goodness-Of-Fit Tests I An experiment have k mutually exclusive and exhaustive outcomes, say, A 1 , A 2 , ··· , A k . Let p i = P ( A i ) and thus k i =1 p i = 1. The experiment is repeated n independent times, Y i represent the number of times the experiment results in A i , i = 1 , 2 , ··· , k . I Joint p.d.f. of Y 1 , Y 2 , ··· , Y k - 1 : f ( y 1 , y 2 , ··· , y k - 1 ) = n ! y 1 ! y 2 ! ··· y k ! p y 1 1 p y 2 2 ··· p y k k . where

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

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 06/05/2011 for the course STATISTICS 2006 taught by Professor Ho during the Spring '11 term at CUHK.

### Page1 / 11

sta 2006 1011_chap8 - Elementary Nonparametric Methods Dr....

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online