This preview shows pages 1–3. Sign up to view the full content.
Econometric Analysis of Panel Data
Professor William Greene
Phone: 212.998.0876
Office: KMC
790
Home page:www.stern.nyu.edu/~wgreene
Email: wgreene@stern.nyu.edu
URL for course web page:
www.stern.nyu.edu/~wgreene/Econometrics/PanelDataEconometrics.htm
Final Examination: Spring 2010
This is a ‘take home’ examination.
Today is Tuesday, April 27, 2010.
Your answers are due
on Friday, May 7, 2010.
You may use any resources you wish – textbooks, computer, the web, etc. –
but please work alone and submit only your own answers to the questions.
The six parts of the exam are weighted as follows:
Part I.
The Hausman and Taylor Estimator
10
Part II.
Panel Data Regressions
20
Part III.
Instrumental Variable and GMM Estimation
10
Part IV.
Binary Choice Models
20
Part V.
Sample Selection
20
Part VI.
A Loglinear Model
20
Note, in parts of the exam in which you are asked to report the results of computation, please filter your
response so that you present the numerical results as part of an organized discussion of the question. Do
not submit long, unannotated pages of computer output.
Part I.
(Continuing the tradition)
The Hausman and Taylor Estimator
Write out a full statement of the procedure that Hausman and Taylor devised for estimation of
the parameters in a panel data model in which some independent variables are correlated with the time
invariant part of the disturbance in a random effects model.
Now, show how the Arellano/Bond/Bover
estimator uses the Hausman and Taylor result.
Department of Economics
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentPart II.
Panel Data Regressions
The course website contains the following data file
http://pages.stern.nyu.edu/~wgreene/Econometrics/railroads.txt
as well in the form of an Excel spreadsheet file, .xls format and a limdep/nlogit project file, .lpj format.
The data in the file are a balanced panel on the following variables for 37 Swiss railroads observed in 13
years:
id
= identifying number of railroad
year
= 85 – 97, years 1985 to 1997
logcost
= log of total cost
logq1
= log of passenger output
logq2
= log of freight output
logpk
= log of capital price
logpl
= log of labor price
logpe
= log of electricity price.
tunnel
= time invariant dummy variable indicates if railroad route includes long tunnels
Do this exercise with Stata, R,
LIMDEP
(or
NLOGIT
), or any other software you wish to use.
The basic model of interest is
Y
it
=
β
1
X1
it
+
β
2
X2
it
+
β
3
X3
it
+
β
4
X4
it
+ β
5
X5
it
+ c
i
+
ε
it
(1)
Where Y is logcost, X1 is logq1, X2 is logq2, X3 is logpk,
X4 is logpl and X5 is logpe.
This is a Cobb
Douglas cost function.
a.
Fit the “pooled” model and report your results.
(Note, the pooled and random effects models must
also contain a constant term.)
b. Fit a random effects model and a fixed effects model.
Use your model results to decide which is the
preferable model.
If you find that neither panel data model is preferred to the pooled model, show how
you reached that conclusion.
As part of the analysis, test the hypothesis that there are no “railroad
This is the end of the preview. Sign up
to
access the rest of the document.
 Fall '11
 WillamGreene

Click to edit the document details