This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Multiple Regression Specification of a multiple regression model: Model: i ki k i i i u x x x y + + + + + = β β β β ... 2 2 1 1 Note: a total of (k+1) parameters needs to be estimated; hence, the number of degrees of freedom is n-(k+1). Interpretation of Coefficients: Model: i ki k i i i u x x x y + + + + + = β β β β ... 2 2 1 1 β is the intercept i.e. the value of the dependent variable when ALL INDEPENDENT VARIABLES ARE ZERO k β β β ,..., , 2 1 are partial slope coefficients. For example, 2 β is the partial slope coefficient for x2 meaning that it indicates the effect of a 1-unit change in x2 on the dependent variable (y), holding constant all the other independent variables (x3,x4, …,xk). In econometrics, holding constant (x3,x4,…,xk) is also referred to as controlling for (x3,x4,…,xk). Model: i ki k i i i u x x x y + + + + + = β β β β ... 2 2 1 1 Assumptions: 1. Zero mean : ) ,..., / ( 2 , 1 = ki i i i x x x u E 2. Constant variance (homoskedasticity) : 2 2 , 1 ) ,..., / ( σ = ki i i i...
View Full Document
This note was uploaded on 04/28/2011 for the course ECON 2P91 taught by Professor Ogwang during the Winter '09 term at Brock University.
- Winter '09