Lecture29-2010

# Lecture29-2010 - Distribution of Estimates and Multivariate...

This preview shows pages 1–3. Sign up to view the full content.

Distribution of Estimates and Multivariate Regression: Lecture XXIX Charles B. Moss November 16, 2010 I. Models and Distributional Assumptions A. Conditional Normal Model 1. The conditional normal model assumes that the observed ran- dom variables are distributed y i N ± α + βx i 2 ² (1) Thus, E[ y i | x i ]= α + βx i (2) and the variance of y i equals σ 2 . The conditional normal can be expressed as y i = α + βx i + ± i ± i N ± 0 2 ² (3) Further, the are independently and identically distributed (consistent with our BLUE proof). 2. Given this formulation, the likelihood function for the simple linear model can be written L ± α, β, σ 2 | x ² = n Y i =1 1 2 πσ exp " ( y i ( α + βx i )) 2 2 σ 2 # (4) Taking the log of this likelihood function yields 1

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
AEB 6571 Econometric Methods I Professor Charles B. Moss Lecture XXIX Fall 2010 ln ( L )= n 2 ln (2 π ) n 2 ln ± σ 2 ² 1 2 σ 2 n X i =1 ( y i α βx i ) 2 (5) As discussed in Lecture XVII, this likelihood function can be concentrated in such a way so that ln ( L ) ∝− n 2 ln ± ˆ σ 2 ² n 2 ˆ σ 2 = 1 n n X i =1 ( y i α βx i ) 2 (6) So that the least squares estimator are also maximum likeli- hood estimators if the error terms are normal. 3. Proof of the variance of β can be derived from the Gauss- Markov results. a) Note from last lecture ˆ β = n X i =1 d i y i = n X i =1 ( x i ¯ x ) S xx ( α + βx i + ± i ) = n X i =1 d i α + n X i =1 d i βx i + n X i =1 d i ± i (7) b) Under our standard assumptions about the error term, we
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 07/15/2011 for the course AEB 6180 taught by Professor Staff during the Spring '10 term at University of Florida.

### Page1 / 7

Lecture29-2010 - Distribution of Estimates and Multivariate...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online