SOC210 Lecture 14: Bivariate Measure of Association
Document Summary
Soc 210 lecture 15 - bivariate measure of association. Measure of association: provide information about the strength and direction of relationship. Two variables are said to be associated when they vary or change together. Biggest difference in column percentages for any row of the table. Approximate way to measure strength of association. In positive relationships, the variables vary in the same direction. In negative relationship, the variables vary in the opposite direction. Maximum difference: 72. 5 36. 84 = 35. 66, so it is a strong relationship. Indicates independent variable the usefulness of predicting the dependent variable. Often shows the direction of the relationship from the. Proportional reduction of error (pre) based measure. Cramer"s v = (x2/ (n) (min r 1, c - 1))1/2. Range in value form 0 (no association) to 1 (perfect association) E1: errors of prediction made when the independent variable is ignored. E2: errors of prediction made when the prediction is based on the independent variable.