This preview shows pages 1–6. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Threeway Contingency Tables Lecture 13 ILRST 212 CochranMantel Haenszel This section shows whether sample data are consistent with homogenous associations or conditional independence. Cochran Mantel Haenszel method present a test of conditional independence and test of homogenous association for the K conditional odds ratios in 2*2*K tables. Example: table 3.3, page 60 CochranMantel Haenszel For a 2*2*K tables, the null hypothesis that X and Y are conditionally independent, given Z, means that the conditional odds ratio θ xy(k) between X and Y equals 1 in each partial table. Ho: θ xy(1) = θ xy(2) = θ xy(3) = ………………………………… θ xy(k)= 1 Ha: Atleast one of the odds ratio is not equal to 1 CochranMantel Haenszel The test statistic utilizes n 11k in each partial table. When the true odds ratio θ xy(k) exceeds 1.0 in partial table k, we expect to observe (n 11k  11k ) >0. The test statistic combines these differences across all K tables. μ CochranMantel Haenszel Hence CMH statistic takes larger values when (n 11k  11k ) is consistently positive or consistently negative for all tables, rather than positive for some or negative for others....
View
Full
Document
This note was uploaded on 09/28/2007 for the course BTRY 6030 taught by Professor Das,t. during the Spring '06 term at Cornell University (Engineering School).
 Spring '06
 DAS,T.
 Epidemiology, .........

Click to edit the document details