PSY202H1 Lecture Notes - Lecture 9: Regression Analysis, Linear Combination
Document Summary
Our goal in the regression is to find the best values of b and a. Another word: b and a determine the regression equation. The prediction value i not perfect unless the correlation is perfect. ( r = 1 is perfect example) The beta is called the standardized regression coefficient. A measure of the standard distance between the predicted y-values on the regression line and the actually y-values in the set of data. In the multiple linear regression, we will incorporate more than one predictor to predict the outcome variable. We want to determine if a second predictor can explain more variance than what can be explained by one predictor. With m-r: we are asking if some sort of linear combination of our predictor variables with predict our outcome variable. We can assign different weight to our different predictor variables to arrive at a predicted value for our outcome variable.
