This preview shows pages 1–12. 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 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 DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: ’ & ST3241 Categorical Data Analysis I Twoway Contingency Tables 2 × 2 Tables, Relative Risks and Odds Ratios 1 ’ & What Is A Contingency Table (p.16) • Suppose X and Y are two categorical variables • X has I categories • Y has J categories • Display the IJ possible combinations of outcomes in a rectangular table having I rows for the categories of X and J columns for the categories of Y . • A table of this form in which the cells contain frequency counts of outcomes is called a contingency table . 2 ’ & Example: Belief In Afterlife Data (p.18) Belief in Afterlife Gender Yes No or Undecided Female 435 147 Male 375 134 • A contingency table that cross classifies two variables is called a two way table . • A table which cross classifies three variables is called a three way table . • A twoway table having I rows and J columns is called an I × J table. 3 ’ & Some Notations, Definitions ··· • π ij = P [ X = i,Y = j ] = probability that ( X,Y ) falls in the cell in row i and column j . • The probabilities { π ij } form the joint distribution of X and Y . • Note that, I X i =1 J X j =1 π ij = 1 4 ’ & Marginal Distributions (p.17) • The marginal distribution of X is π i + , which is obtained by the row sums, that is, π i + = J X j =1 π ij • The marginal distribution of Y is π + j , which is obtained by the column sums, that is π + j = I X i =1 π ij • For example, for a 2 × 2 table π 1+ = π 11 + π 12 ,π +1 = π 11 + π 21 5 ’ & Notations For The Data • Cell counts are denoted by { n ij } , with n = I X i =1 J X j =1 n ij • Cell proportions are p ij = n ij n • The marginal frequencies are row totals { n i + } and column totals { n + j } 6 ’ & Example Belief in Afterlife Gender Yes No or Undecided Total Female n 11 =435 n 12 =147 n 1+ =582 Male n 21 =375 n 22 =134 n 2+ =509 Total n +1 =810 n +2 =281 n =1091 7 ’ & Example: Sample Proportions Belief in Afterlife Gender Yes No or Undecided Total Female p 11 =0.398 p 12 =0.135 p 1+ =0.533 Male p 21 =0.344 p 22 =0.123 p 2+ =0.467 Total p +1 =0.742 p +2 =0.258 p =1.00 8 ’ & Conditional Probabilities • Let Y be a response variable and X be an explanatory variable. • It is informative to construct separate probability distributions for Y at each level of X . • Such a distribution consists of conditional probabilities for Y given the level of X and is called a conditional distribution . 9 ’ & Example: Sample Conditional Distributions • For females, – Proportion of yes responses = 0.747 – Proportion of no responses = 0.253 • For males, – Proportion of yes responses = 0.737 – Proportion of no responses = 0.263 10 ’ & Independence • Is the belief in afterlife is independent of gender?...
View
Full
Document
This note was uploaded on 11/20/2011 for the course STATISTICS ST3241 taught by Professor Manwai's during the Spring '11 term at National University of Singapore.
 Spring '11
 ManWai's

Click to edit the document details