Chapter18 - Case Studies Difference of Two Proportions...

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: Case Studies Difference of Two Proportions Ratio of Odds Retrospective Studies Chapter 18: Comparisons of Proportions or Odds STAT 3022 Fall 2011 University of Minnesota November 18, 2011 Case Studies Difference of Two Proportions Ratio of Odds Retrospective Studies Introduction Return to the setting of comparing two groups: response measurement on each subject is a binary variable (takes on values 0 or 1) way of coding a two-group categorical response e.g., dead or alive, diseased or not diseased into a number make conclusions about population proportions or probabilities or conclusions about odds Case Studies Difference of Two Proportions Ratio of Odds Retrospective Studies Obesity and Heart Disease Example Two schools of thought about physiological relationship between obesity and heart disease: 1 proponents: higher risk of heart problems for obese persons 2 opponents: strain of social stigma brought on by obesity is to blame One study conducted in Samoa, where obesity is common and socially desirable to shed light on this controversy. 3,112 Samoan women were categorized as obese or not in 1976. Researchers recorded whether subjects died of cardiovascular disease (CVD) between 1976 and 1981. Case Studies Difference of Two Proportions Ratio of Odds Retrospective Studies Data for Samoan Women Example CVD death Yes No Totals Obese 16 2,045 2,061 Not obese 7 1,044 1,051 Totals 23 3,089 3,112 Is CVD death in the population of Samoan women related to obesity? Proportion of CVD deaths among obese women: 16 2061 = 0 . 00776 Proportion among non-obese women: 7 1051 = 0 . 00666 Case Studies Difference of Two Proportions Ratio of Odds Retrospective Studies Vitamin C and the Common Cold Example Does the use of vitamin C prevent the common cold? 818 volunteer subjects in Canada beginning of winter, subjects randomly divided into two groups: vitamin C group received 1,000 mg of vitamin C per day placebo group received same amount of sugar pills end of cold season, subjects interviewed by physician who determined whether subjects had suffered a cold double-blind experiment; physician did not know which subjects were in which treatment group Case Studies Difference of Two Proportions Ratio of Odds Retrospective Studies Data for Vitamin C Study Example Outcome Cold No Cold Totals Placebo 335 76 411 Vitamin C 302 105 407 Totals 637 181 818 Can the risk of a cold be reduced by using vitamin C? 82% of placebo subjects caught colds, while only 74% of vitamin C subjects caught colds. How to determine if this is strong enough evidence that vitamin C reduces risk of cold, in the population? Case Studies Difference of Two Proportions Ratio of Odds Retrospective Studies Binary Response Variables Suppose population of units is classified as yes or no . For example, Samoan women classified as yes if died of CVD, no if not....
View Full Document

This note was uploaded on 01/22/2012 for the course STAT 3022 taught by Professor Staff during the Fall '08 term at Minnesota.

Page1 / 50

Chapter18 - Case Studies Difference of Two Proportions...

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