Department of Economics Columbia University SOLUTION TO Problem Set 4 Introduction to Econometrics Prof. Marcelo J. Moreira and Seyhan E Arkonac, PhD Spring 2010
W3412 Spring 2010
1. Use Table 2 to answer the following questions. Table 2 presents the resu
SOLUTIONS TO Problem Set 1 Introduction to Econometrics prepared by Prof. Marcelo J. Moreira and Seyhan E Arkonac, PhD for all sections Spring 2010 "Calculator" was once a job description. This problem set gives you an opportunity to do some calculations
Problem Set 2: Simple Linear Regression
Chris Conlon and Christoph Rothe
Due: Feb 6
You may want to take a look at the R/ggplot2 plotting cookbook: http:/www.cookbook-r.com/
Graphs/Plotting_distributions_(ggplot2)
Question 1: Testing the Superbowl Theory
Problem Set 1: Statistics Review
Chris Conlon and Christoph Rothe
January 29, 2015
Question 1
N
1
Let X, Y be i.i.d. random variables with realizations (xi , yi ) for i = 1, . . . , N . Let x = N i=1 xi and
N
1
y = N i=1 yi with sample correlation coecien
Department of Economics
Columbia University
W3412
Fall 2014
SOLUTIONS TO
Problem Set 2
Introduction to Econometrics
Profs. Seyhan E Arkonac and Miikka Rokkanen
for all sections
Part I
True, False, Uncertain with Explanation:
1. [graded] The assumption tha
Department of Economics Columbia University SOLUTIONS TO Problem Set 6 Introduction to Econometrics Prof. Marcelo J. Moreira and Seyhan E Arkonac, PhD for all sections Spring 2010
W3412 Spring 2010
1)
Create a new binary variable higdppc, which equals one
Department of Economics Columbia University SOLUTIONS TO Problem Set 5 Introduction to Econometrics Prof. Marcelo J. Moreira and Seyhan E Arkonac, PhD for all sections Spring 2010
W3412 Spring 2010
1. hprice1.dta is a data set collected from the real esta
Department of Economics Columbia University SOLUTIONS TO Problem Set 3 Introduction to Econometrics Prof. Marcelo J. Moreira and Seyhan E Arkonac, PhD for all sections Spring 2010
W3412 Spring 2010
1. The following question is a continuation of problem se
Department of Economics
Columbia University
W3412
Spring 2012
SOLUTIONS to Problem Set 2
Introduction to Econometrics
Profs: Seyhan E Arkonac and Chris C Conlon
for all sections
Question I:
Testing the Superbowl Theory:
We have provided you with the STATA
Department of Economics
Columbia University
W3412
Fall 2015
SOLUTIONS to Problem Set 7
Introduction to Econometrics
Profs. Seyhan Erden and Miikka Rokkanen
for all sections.
Part I
True, False, Uncertain with Explanation:
(=1 | )
(a) In a probit /logit mo
Columbia University
Department of Economics
W3412
Spring 2012
SOLUTIONS TO Problem Set 5
Introduction to Econometrics
Profs: Seyhan E Arkonac and Chris C Conlon
for all sections
1)
Create a new binary variable higdppc, which equals one if gdppc is greater
Problem Set 8: Instrumental Variables
Profs. Christopher T. Conlon and Seyhan E. Arkonac, Columbia University
W3412 Spring 2012
Question 1
Consider the following regression model Yi =
0
+
1 Xi
+ ui and two estimators OLS and I V .
(a) Rewrite the variance
Department of Economics Columbia University SOLUTION TO Problem Set 8 Introduction to Econometrics Prof. Marcelo J. Moreira and Seyhan E Arkonac, PhD for all sections Spring 2010
W3412 Spring 2010
Question I: SW Exercises 12.1 (page 457)
(a) The change in
Department of Economics
Columbia University
W3412
Spring 2012
SOLUTIONS TO Problem Set 3
Introduction to Econometrics
Profs: Seyhan Erden Arkonac and Chris C Conlon
for all sections
Question I:
Use the data in .hprice1.dta. to estimate the following model
Department of Economics Columbia University SOLUTION TO Problem Set 7 Introduction to Econometrics Prof. Marcelo J. Moreira and Seyhan E Arkonac, PhD for all sections Spring 2010 Question I: 10.1
W3412 Spring 2010
(a) Yes. The t-statistic for the coeffici
Department of Economics
Columbia University
W3412
Spring 2012
SOLUTIONS to Problem Set 6
Introduction to Econometrics
Profs. Seyhan E Arkonac and Chris C. Conlon
for all sections
1. Some U.S. states have enacted laws that allow citizens to carry concealed
SOLUTIONS TO Problem Set 2 Introduction to Econometrics prepared by Prof. Marcelo J. Moreira and Seyhan E Arkonac, PhD for all sections Spring 2010 1. Suppose you have some money to invest for simplicity, $1 and you are planning to put a fraction w into a
Department of Economics
Columbia University
W3412
Spring 2012
SOLUTIONS TO Problem Set 9
Introduction to Econometrics
Profs. Seyhan E Arkonac and Christopher T. Conlon
for all sections.
1. Data set cpi_unemp_1948_2011.dta is downloaded from St Louis Fed w
Department of Economics
Columbia University
W3412
Spring 2012
SOLUTION to Problem Set 7
Introduction to Econometrics
Profs. Seyhan E Arkonac and Chris topher T. Conlon
for all sections .
1. Who smokes? The data set smoker.dta contains a random sample of 1
Department of Economics
Columbia University
W3412
Spring 2012
SOLUTIONS TO Problem Set 4
Introduction to Econometrics
Profs: Seyhan E Arkonac and Chris C Conlon
for all sections
1. Preliminary data analysis:
a) Produce the scatterplot of ftmpop vs. gdppc.
Department of Economics
Columbia University
W3412
Fall 2014
SOLUTIONS TO Problem Set 8
Introduction to Econometrics
Profs. Seyhan Erden and Miikka Rokkanen
for all sections.
Part I:
True, False, Uncertain with Explanation:
1. You want to estimate a supply
Department of Economics
Columbia University
W3412
Fall 2015
SOLUTIONS TO Problem Set 8
Introduction to Econometrics
Profs. Seyhan Erden and Miikka Rokkanen
for all sections.
Part I:
True, False, Uncertain with Explanation:
1. You want to estimate a supply
Problem Set 7: Binary Dependent Variables
April 5, 2012
Question 4
Consider a dataset with three observations (Y1 , Y2 , Y3 ) and (X1 , X2 , X3 ) where the Y s are binary outcomes.
(a) Write the likelihood function of logit model where Z = 0 + 1 X + 2 X 2
The Last Problem Set: Time Series
Profs. Christopher Conlon and Christoph Rothe
Due: May 1st at Noon
Question 1
Consider a simple AR(1) model:
with t N (0, 2 ) for t = 1, . . . , T and Y0 = 0
Yt = Yt1 + t
(a) What is the distribution of Y1 ? What is the d
Problem Set 6: Multiple Regression
Chris Conlon and Christoph Rothe
Question 1
Consider the log-linear regression model
log(Yi ) = 0 + 1 Xi + Ui .
(a) We have seen in class that 1 can be interpreted as the approximate percentage increase in Yi in response
Problem Set 7: Panel Data Analysis
Profs: Chris Conlon and Christoph Rothe
Question 1
Consider the following xed eects specication:
yit = 0 + 1 xit + i + t + it
a. What is the interpretation of i ? How does it aect the regression line?
It is an entity xed
Problem Set 5: Multiple Regression
Chris Conlon and Christoph Rothe
Question 1
This problem looks at the production of 140 French apple producers from the year 1986. These data have
been extracted from a panel dataset used in Ivaldi et al. (1996). The poi
Problem Set 3: Simple Linear Regression
Chris Conlon and Christoph Rothe
Question 1
A professor decides to run an experiment to measure the eect of time pressure on nal exam scores. He gives
each of the 400 students in his course the same nal exam, but so
Department of Economics
Columbia University
W3412
Fall 2015
SOLUTIONS Problem Set 9
Introduction to Econometrics
Profs. Seyhan Erden and Miikka Rokkanen
for all sections.
Part I:
True, False, Uncertain with Explanation:
(a) The first difference of the log
Department of Economics Columbia University SOLUTIONS TO Problem Set 10 Introduction to Econometrics Prof. Marcelo J. Moreira and Seyhan E Arkonac, PhD for all sections Spring 2010
Suggested Solutions are in 10 point Arial
W3412 Spring 2010
Question I: To
Multiple Regression I and II
(Heteroskedasticity,
Multicollinearity)
(Fall 2015)
Lecture 7 and 8
Seyhan Erden, PhD
Problem Set 2 is due NOW.
1
The Extended Least Squares
Assumptions
These consist of the three LS assumptions, plus two more:
1. E(u|X = x) =
Department of Economics
Columbia University
Economics W3412
Fall 2013
SOLUTIONS TO Final Exam
Section 2 (Tue/Thur section)
(Seyhan Erden Arkonac)
Instructions
1. Do not turn this page until so instructed.
2. This exam ends promptly at 4pm.
3. This exam ha
Experiments and Quasi
Experiments
Lecture 22
Seyhan Erden, PhD
Columbia University
1
Experiments and QuasiExperiments
Why study experiments?
Ideal randomized controlled experiments provide a
benchmark for assessing observational studies.
Actual experime
Multiple Regression III
Lecture 9 and 10
Seyhan Erden, PhD
Columbia University
Problem Set #4 is posted.
1
Quick Review:
Problem we may encounter (so far) in regression
analysis:
(1) Hetereskodasticity: definition? solution?
(2) Omitted Variable Bias: def
Time Series Regression
Lectures 23 - 2
Seyhan Erden, PhD
Columbia University
Problem Set 9 is due on Thursday April 8th
1
Introduction to Time Series
Regression and Forecasting
Time series data are data collected on the same observational
unit at multiple