lect25_2010

lect25_2010 - 1 / 22 Introduction to Econometrics Econ 322...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: 1 / 22 Introduction to Econometrics Econ 322 Fall, 2010 Lecture 25: Instrumental Variables Estimation (IV) II December 1, 2010 Topics Covered triangleright Topics Covered Checking Instrument Validity Checking Assumption 1: Instrument Relevance What happens when Instruments are Weak? Why does the normal approximation fail? Measuring the strength of instruments in practice: The first-stage F-statistic Checking for weak instruments with a single X What to do if you have weak instruments? Confidence intervals with weak instruments Estimation with weak instruments Checking Assumption 2: Instrument Exogeneity Testing overidentifying restrictions The J-Test Distribution of J-Test An Example: The Demand for Cigarettes 2 / 22 1. Instrument Validity Assumptions 2. Checking for Instrument Validity 3. An example Checking Instrument Validity Topics Covered triangleright Checking Instrument Validity Checking Assumption 1: Instrument Relevance What happens when Instruments are Weak? Why does the normal approximation fail? Measuring the strength of instruments in practice: The first-stage F-statistic Checking for weak instruments with a single X What to do if you have weak instruments? Confidence intervals with weak instruments Estimation with weak instruments Checking Assumption 2: Instrument Exogeneity Testing overidentifying restrictions The J-Test Distribution of J-Test An Example: The Demand for Cigarettes 3 / 22 square Recall the two requirements for valid instruments: 1. Relevance (special case of one X) At least one instrument must enter the population counterpart of the first stage regression. 2. Exogeneity All the instruments must be uncorrelated with the error term: corr ( Z 1 i , epsilon1 i ) = 0 , . . ., corr ( Z mi , epsilon1 i ) = 0 square What happens if one of these requirements isnt satisfied? square How can you check? square What do you do? square If you have multiple instruments, which should you use? Checking Assumption 1: Instrument Relevance Topics Covered Checking Instrument Validity triangleright Checking Assumption 1: Instrument Relevance What happens when Instruments are Weak? Why does the normal approximation fail? Measuring the strength of instruments in practice: The first-stage F-statistic Checking for weak instruments with a single X What to do if you have weak instruments? Confidence intervals with weak instruments Estimation with weak instruments Checking Assumption 2: Instrument Exogeneity Testing overidentifying restrictions The J-Test Distribution of J-Test An Example: The Demand for Cigarettes 4 / 22 square We will focus on a single included endogenous regressor: Y i = + 1 X i + 2 W 1 i + . . . + 1+ r W ri + epsilon1 i square First stage regression: X i = + 1 Z 1 i + . . . + m Z mi + m +1 W 1 i + . . . + m + k W ki + epsilon1 i square The instruments are relevant if at least one of 1 , . . ., m are nonzero....
View Full Document

This document was uploaded on 10/26/2011 for the course ECON 327 at Rutgers.

Page1 / 22

lect25_2010 - 1 / 22 Introduction to Econometrics Econ 322...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online