01:830:200 Lecture Notes - Lecture 6: Homoscedasticity, Zirconium, Repeated Measures Design
Document Summary
When both the iv (x) and dv (y) are interval/ratio level, r , is a measure of the strength and direction of their association. Can"t be over 1. 00 1 equals perfect correlation. Range of values is not restricted (from low and high end of the data) Clarification on causal conclusions only draw causal relationships from experimental studies. Effect size (coefficient of determination) = r 2. In other words, for each subject you will have a z-score on x and a z-score on y. Calculate the product for each subject, sum the products and divide the sum by sample size. Round to two decimal places after each step. Comparing two pearson"s r"s: fisher"s z-test for a difference between two r"s. Step 1: convert pearson"s r values into fisher"s zr (pg. Step 2: do all the shit, then compare to the alpha levels for z (1. 96, 2. 58)