This preview shows pages 1–2. Sign up to view the full content.
Professor Tanya Molodtsova
ECON 422
Office: Rich 319
Econometrics
Email:
[email protected]
Fall 2011
SOLUTION  Problem Set 3
Q1. (5 points) Download the Stata file gpa.dta you have used in Problem Set 2. Open the data in
Stata following the steps we learned in class.

Start Stata

Save Excel file as a .csv file in your working folder, (make sure that your .csv file
contains only one worksheet)

Specify your working folder in Stata by using the “cd” command

Open the saved .csv file in Stata, by typing “insheet using gpa.csv”
a.
Regress GPA on HSGPA, SEX, and RACE. Show your Stata output for this regression.
Carefully interpret the coefficient on HSGPA. Is it different from the coefficient on
HSGPA in the simple regression model you have estimated in Problem Set 2?
b.
Carry out a ttest for the hypothesis the coefficient on HSGPA is statistically significant
at the 5% level.
c.
Generate a series of residuals from this regression by typing after running the regression:
predict uhat, resid. Draw a histogram for the residuals. Do they look normally distributed? To
draw the
histogram, use:
histogram uhat, normal
d.
You want to study the variance of your residuals to see if heteroskedasticity is present in
the data. Generate a series of squared residuals:
gen uhatsq=uhat*uhat
Examine the scatter plots of uhatsq against your dependent variables:
scatter uhatsq hsgpa
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview. Sign up
to
access the rest of the document.
This note was uploaded on 11/20/2011 for the course ECON 420 taught by Professor Silous during the Spring '11 term at Emory.
 Spring '11
 silous
 Econometrics

Click to edit the document details