This preview shows pages 1–12. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Introduction to Econometrics Econ 322 Summer, 2011 Ruby HENRY June 27, 2011 Ruby HENRY () Introduction to Econometrics Econ 322 Summer, 2011 June 27, 2011 1 / 1 Part I  Topics Covered Homoscedasticity and Heteroscedasticity Hypothesis testing Con&dence Intervals Ruby HENRY () Introduction to Econometrics Econ 322 Summer, 2011 June 27, 2011 2 / 1 Some Additional Assumptions So far we have made very few assumptions. Our assumptions so far are: Ruby HENRY () Introduction to Econometrics Econ 322 Summer, 2011 June 27, 2011 3 / 1 Some Additional Assumptions So far we have made very few assumptions. Our assumptions so far are: E ( e i j X ) = 0 for each i Ruby HENRY () Introduction to Econometrics Econ 322 Summer, 2011 June 27, 2011 3 / 1 Some Additional Assumptions So far we have made very few assumptions. Our assumptions so far are: E ( e i j X ) = 0 for each i the sample is random Ruby HENRY () Introduction to Econometrics Econ 322 Summer, 2011 June 27, 2011 3 / 1 Some Additional Assumptions So far we have made very few assumptions. Our assumptions so far are: E ( e i j X ) = 0 for each i the sample is random X and e have &nite fourth moments Ruby HENRY () Introduction to Econometrics Econ 322 Summer, 2011 June 27, 2011 3 / 1 Some Additional Assumptions So far we have made very few assumptions. Our assumptions so far are: E ( e i j X ) = 0 for each i the sample is random X and e have &nite fourth moments Lets now think about the regression error, e i . Ruby HENRY () Introduction to Econometrics Econ 322 Summer, 2011 June 27, 2011 3 / 1 Some Additional Assumptions So far we have made very few assumptions. Our assumptions so far are: E ( e i j X ) = 0 for each i the sample is random X and e have &nite fourth moments Lets now think about the regression error, e i . In almost every econometrics text book you will see the following assumption about the distribution of the regression error. It is commonly referred to as an assumption of homoscedasticity . Ruby HENRY () Introduction to Econometrics Econ 322 Summer, 2011 June 27, 2011 3 / 1 Some Additional Assumptions So far we have made very few assumptions. Our assumptions so far are: E ( e i j X ) = 0 for each i the sample is random X and e have &nite fourth moments Lets now think about the regression error, e i . In almost every econometrics text book you will see the following assumption about the distribution of the regression error. It is commonly referred to as an assumption of homoscedasticity . We assume that e i & ( , 2 e ) for all i . This assumption states that the regression error for each observation is identically distributed with the same variance. Ruby HENRY () Introduction to Econometrics Econ 322 Summer, 2011 June 27, 2011 3 / 1 Homoscedasticity Assumption Implications of this assumption Ruby HENRY () Introduction to Econometrics Econ 322 Summer, 2011 June 27, 2011 4 / 1 Homoscedasticity Assumption Implications of this assumption If we assume that the regression error is homoscedastic then we can...
View
Full
Document
This note was uploaded on 09/29/2011 for the course ECON 322 taught by Professor Francisco during the Summer '07 term at Rutgers.
 Summer '07
 Francisco
 Econometrics

Click to edit the document details