Ch14 - 0011 0010 1010 1101 0001 0100 1011 Chi-Square Tests...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

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

Unformatted text preview: 0011 0010 1010 1101 0001 0100 1011 Chi-Square Tests 0011 0010 1010 1101 0001 0100 1011 Chapter edit Click to 14 Master subtitle style 12/14/10 45 1 23 Chi-square test for independence 0011 0010 1010 1101 0001 0100 1011 • Why? – – – Test relationship (correlation) between CATEGORICAL, non-quantifiable variables Examples… Base on contingency table 12/14/10 45 1 23 r x c Contingency Table 0011 0010 1010 1101 0001 0100 1011 Variable B MAJOR: Systems Marketing Accounting Finance Management Undeclared MALE (frequencies) (frequencies) (frequencies) (frequencies) (frequencies) (frequencies) Variable A FEMALE (frequencies) (frequencies) (frequencies) (frequencies) (frequencies) (frequencies) 6 x 2 Contingency table 12/14/10 45 1 23 Chi-square test for independence 0011 0010 1010 1101 0001 0100 1011 • • • • • Compare observed with expected (assuming independence) H0: Independent H1: Dependent Always right-tail test What do we expect chi-square to be? 12/14/10 45 1 23 Chi-square test for independence 0011 0010 1010 1101 0001 0100 1011 • Expected frequencies: Test statistic: ejk = RjCk/n • Degrees of freedom v = (r-1)(c-1) 12/14/10 45 1 23 0011 0010 1010 1101 0001 0100 1011 Examples 0011 0010 1010 1101 0001 0100 1011 Excel spreadsheet… Click to edit Master subtitle style 12/14/10 45 1 23 Goodness of fit 0011 0010 1010 1101 0001 0100 1011 • For multinomial distribution: • Degrees of freedom: v = c - m - 1 (m is # of parameters estimated…always 0 for this class) 12/14/10 45 1 23 Example: GOF, multinomial 0011 0010 1010 1101 0001 0100 1011 12/14/10 45 1 23 ...
View Full Document

This note was uploaded on 12/13/2010 for the course LEEDS BCOR 1020 taught by Professor Heatheradams during the Spring '08 term at Colorado.

Page1 / 8

Ch14 - 0011 0010 1010 1101 0001 0100 1011 Chi-Square Tests...

This preview shows document pages 1 - 8. Sign up to view the full document.

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