This preview shows pages 1–2. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Section 7 - Econ 140 GSIs: Hedvig, Tarso, Xiaoyu * 1 Omitted Variable Bias Omitted variable bias is the bias in the OLS estimator that arises when one or more included regressors are correlated with an omitted variable. For omitted variable bias to arise, two things must be true: 1. At least one of the included regressors must be correlated with the omitted variable. 2. The variable must be a determinant of the dependent variable, Y i . To better understan the problem, let's come back to the linear regression model with one explanatory variable, Y i = + 1 X i + u i . In this case, the formula for omitted variable bias is 1 p 1 + Xu u X . This formula means that, as the sample size increases, 1 approaches 1 + Xu u X . It summarizes the main ideas about omitted variable bias: 1. Omitted variable bias is a problem whether the sample size is large or small. 2. Whether this bias (= Xu u X ) is large or small in practice depends on the correlation Xu between the regressor and the error term. The larger is | Xu | , the larger is the bias....
View Full Document
- Spring '08