slides_Ch2_W[1]

# Melissa tartari yale econometrics 84 93 the variance

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: stimate β1 Melissa Tartari (Yale) Econometrics 82 / 93 The Variance of the OLS Estimator - Estimation I Premise: is there any di¤erence between the unobservables and the residuals? YES! Melissa Tartari (Yale) Econometrics 83 / 93 The Variance of the OLS Estimator - Estimation I Premise: is there any di¤erence between the unobservables and the residuals? YES! in yi = βo + β1 xi + ui the unobservable for observation i is ui : the unobservable appears in the equation containing the population parameters; the unobservables are never observed Melissa Tartari (Yale) Econometrics 83 / 93 The Variance of the OLS Estimator - Estimation I Premise: is there any di¤erence between the unobservables and the residuals? YES! in yi = βo + β1 xi + ui the unobservable for observation i is ui : the unobservable appears in the equation containing the population parameters; the unobservables are never observed ˆ ˆ in yi = βo + β1 xi + ui the residual for observation i is ui : the residual ˆ b shows up in the estimated equation containing the estimates of the population parameters; the residuals are computed from the data Melissa Tartari (Yale) Econometrics 83 / 93 The Variance of the OLS Estimator - Estimation I Premise: is there any di¤erence between the unobservables and the residuals? YES! in yi = βo + β1 xi + ui the unobservable for observation i is ui : the unobservable appears in the equation containing the population parameters; the unobservables are never observed ˆ ˆ in yi = βo + β1 xi + ui the residual for observation i is ui : the residual ˆ b shows up in the estimated equation containing the estimates of the population parameters; the residuals are computed from the data here is an equation that explicitly gives the di¤erence between ui and ui ˆ ui ui ˆ | {z } = ˆ βo βo ˆ β1 β 1 xi (2.59) in Expected value it is 0 Melissa Tartari (Yale) Econometrics 83 / 93 The Variance of the OLS Estimator - Estimation I ˆ ˆ Notice that Var β1 jx and Var βo jx depend on σ2 and σ2 is ˆ ˆ unknown; thus, Var β1 jx and Var βo jx are...
View Full Document

Ask a homework question - tutors are online