LS221 Study Guide - Final Guide: Odds Ratio, Correlation And Dependence, Generalized Linear Model
Document Summary
Regression says that a change in an independent variable is likely to be associated with a specific amount of change in the dependent variable. Allows you to control the effects for another variable. Allows us to look at multiple independent variables on a dependent variable. I. e. not just education associated with higher income, but also age/family upbringing etc. etc. By including age in the model, we"re removing the effect it has and isolating the effect education has on income. Allows you to rule out other effects, to account for spuriousness etc. Your testing the relationship between an outcome (dependent variable) and two or more predictors (independent variables) (multivariate analysis) The b value is the regression coefficient, the beta value is the standardized regression coefficient. The p value (sig) says whether its significant (less than 0. 05). A linear regression finds a straight line relationship between the independent variable and the dependent variable.