Chapter 10--Hypothesis Testing--Categorical Data

in general assume the table is rearranged in such a

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

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

Unformatted text preview: P (X ≤ 2) = P (X = 0) + P (X = 1) + P (X = 2). Chapter 10: Hypothesis Testing: Categorical Data Stat 491: Biostatistics Introduction Two-Sample Test for Binomial Proportions McNemar’s Test Estimation of Sample Size and Power R × C Contingency Tables Chi-Square Goodness-of-Fit Test The Kappa Statistic Normal-Theory Method Fisher’s-Exact Test Fisher’s-Exact Test Cont’d... In general, assume the table is rearranged in such a way that n1 ≤ n2 and M1 ≤ M2 . Then your p1 corresponds to the population with the smaller sample. Let k = min(M1 , n1 ). For the lower-sided alternative Ha : p1 < p2 , p −value = P (X ≤ a) = P (X = 0)+P (X = 1)+· · ·+P (X = a) This can be computed in R using phyper(a,n1,n2,M1). For upper-sided alternative Ha : p1 > p2 p −value = P (X ≥ a) = P (X = a)+P (X = a+1)+· · ·+P (X = k ) For the two-sided alternative Ha : p1 = p2 p −value = 2 × min[P (X ≤ a), P (X ≥ a), 0.5]. Evaluate the statistical significance of the CVD data. Chapter 10: Hypothesis Testing: Categorical Data Stat 491: Biostatistics Introduction Two-Sample Test for Binomial Proportions McNemar’s Test Estimation of Sample Size and Power R × C Contingency Tables Chi-Square Goodness-of-Fit Test The Kappa Statistic Normal-Theory Method Fisher’s-Exact Test Fisher’s-Exact Test: Random Column Totals The test finds p-value for one subset of the sample space (subset defined by the value assumed by M1 ). The subsets defined by the values of M1 partition the sample space into mutually exclusive subsets. Then we can see that PH0 (X ≥ a) = PH0 (X ≥ a|M1 = m)P (M = m) m ≤ α. Fisher’s exact test is valid for random column margins. The power of the exact test is usually lower than that of a more appropriate power test. Chapter 10: Hypothesis Testing: Categorical Data Stat 491: Biostatistics Introduction Two-Sample Test for Binomial Proportions McNemar’s Test Estimation of Sample Size and Power R × C Contingency Tables Chi-Square Goodness-of-Fit Test The Kappa Statistic McNemar’s Test: Introduction This is a test for two-samples binomial proport...
View Full Document

This note was uploaded on 02/03/2014 for the course STAT 491 taught by Professor Solomonharrar during the Fall '12 term at Montana.

Ask a homework question - tutors are online