Final Exam (Answers)
Economics 1123
Instructions.
1.Do not turn the page until instructed
2.This exam is three hours long.
3.This exam has six parts for a total of 100 points. Please put each part in a separate blue
book. Put your name and Harvard ID numb
Ec1123
Section 11
Peter Tu
[email protected]
30 November 2015
Peter Tu
Ec1123
30 November 2015
Table of Contents
1
PSET #9 Recap
2
Dynamic Causal Effects
3
Standard Errors Review
HAC or HAR
4
PSET #10 Preview
5
Regression Discontinuity (RD) Design
P
John Coglianese: [email protected]
Office Hours: Monday 10:30am-12:30pm Littauer M-42
Section 1: Multiple Variable Regression
Suppose we are interested in estimating the effect of schooling on income. We run the following linear
regression,
Incom
Ec1123
Section 09
Peter Tu
[email protected]
13 November 2015
Peter Tu
Ec1123
13 November 2015
Table of Contents
1
Problem Set # 8 Preview
2
An Instrument Example
3
Forecasting and Time Series
Models
Stationarity
Peter Tu
Ec1123
13 November 2015
Pro
Ec1123
Section 4
Peter Tu
[email protected]
2 October 2015
Peter Tu
Ec1123
2 October 2015
Table of Contents
1
PSET #3 Recap
2
Binary Dependent Variables
Linear Probability Model
Probit & Logit
Interpreting Coefficients
Maximum Likelihood Estimation
John Coglianese
OH Monday 10:30am - 12:30pm Littauer M-42
Section 4: Binary dependent variables
1
Definition: Binary Dependent Variables
Yi takes on only two values, 0 and 1. Yi is called a binary dependent variable. Example: We
observe whether survey res
Daniel Lewis
OH Monday 9-11am Littauer M-42
Section 7: Instrumental Variables Regression
1. Motivation for IV:
Suppose we are interested in estimating that casual effect of X on Y - 1 - using the regression
Yi = 0 + 1 Xi + ui , but Xi and ui are correlate
John Coglianese
OH Monday 10:30am-12:30pm Littauer M-42
Section 3: Review and Interaction Effects
1
Review of Problem Set 2
Lets consider a regression using the dataset from Problem Set 2:
. regress lnftmpop lngdppc lngdppc2, robust
Linear regression
Numb
Daniel Lewis
OH Monday 9-11am Littauer M-42
Ec1123 Section 11 - November 19, 2015
Section 10: Time Series II
In this section, we will try to find a good model for movements in the long-term interest rate for Spanish bonds.1
(a) Levels
(b) Changes (percent
Ec1123 Section 8 - November 8, 2015
John Coglianese: [email protected]; OH Monday 10:30am-12:30pm Littauer M-42
1
1.1
Experiments and quasi-experiments
Introduction
We would like to know the casual effect of a treatment on an outcome we are inter
John Coglianese
OH Monday 10:30am-12:30pm Littauer M-42
Section 5: Panel data
1
Introduction
In the first part of this course, we looked at cross-sectional data sets. The linear model that we wanted
to estimate had one observation for each unit i and a to
Ec1123 Section 9 - November 15, 2015
John Coglianese: [email protected]; OH Monday 10:30am-12:30pm, Littauer M-42
Section 9: Time Series I
1. Forecasting and time series models
(a) Time series data are repeated measures of some variable over time
Supplemental Notes on F-statistics
Daniel Lewis
September 10, 2015
These notes draw heavily on the slides accompanying Stock and Watson Introduction to
Econometrics, Third Edition.
1
Theory
Consider the population regression
Incomei = 0 + 1 P arentIncomei
Daniel Lewis
OH Tuesday 1-3pm Science Center 111
Section 11: Time Series III
1
HAC standard errors
In time series applications, it often happens that the error term ut is serially correlated, that is, past values of u
help you to forecast future values of
Ec1123
Section 2
Peter Tu
[email protected]
18 September 2015
Peter Tu
Ec1123
18 September 2015
Table of Contents
1
PS01 Review
2
Non-linearities
Polynomials
Logs
Interaction Terms
3
PS02 Preview
Peter Tu
Ec1123
18 September 2015
PS01 Review
Correla
Ec1123
Section 6
Peter Tu
[email protected]
23 October 2015
Peter Tu
Ec1123
23 October 2015
Table of Contents
1
Midterm Recap
2
Simultaneous Causality
3
Instrumental Variable Regression
Conditions
Example
In STATA
Two-Stage Least Squares
Testing the
Department of Economics
Harvard University
Economics 1123
Spring 2012
Problem Set #8
Financial Markets and Political Distress
(Due: Apr. 24)
On January 14th 2011 Tunisian protestors forced the Tunisian leader Ben Ali from
power. In this problem set you us
Department of Economics
Harvard University
Economics 1123
Spring 2012
Problem Set #7
The Effect of Marriage on Earnings
(Due: April 12)
[Note, here there were a few typos that made some of the questions somewhat ambiguous.
These typos are corrected here a
Department of Economics
Harvard University
Economics 1123
Spring 2012
Problem Set #6
The Causal Effect of Class Size on Test Scores
(Due: April 5)
In this problem set you will explore use the determinants of test scores using the Project
Star data set use
Department of Economics
Harvard University
Economics 1123
Spring 2012
Problem Set #5
Children and their Parents Labor Supply
(Due: March 29)
Labor economists are interested in understanding the relationship between fertility and
labor supply (i.e. hours w
Department of Economics
Harvard University
Economics 1123
Spring 2012
Problem Set #3
The Determinants of Test Scores
(Due: Feb. 16)
In this problem set you will explore the determinants of test scores using the Project Star
data set. The project that gene
Department of Economics
Harvard University
Economics 1123
Spring 2012
Problem Set #2
An Empirical Investigation of Economic Growth
(Due: Feb. 9)
In this problem set you will explore the determinants of economic growth using a crosscountry data set. A tabl
Department of Economics
Harvard University
Economics 1123
Spring 2012
Problem Set #1
Rolling the Dice and the Environment
(Due: February 2, 2012)
1. Suppose that you have two dice, one red and the other green. When they are thrown,
there are 36 possible e
Practice Midterm Exam
Economics 1123
Instructions:
1.Do not turn the page until instructed
2.This exam is 80 minutes long.
3.This exam has three parts for a total of 75 points. Please put each part in a separate blue
book. Put your name and Harvard ID num
Ec1123
Section 10
Peter Tu
[email protected]
20 November 2015
Peter Tu
Ec1123
20 November 2015
Table of Contents
1
Problem Set #8 Review
2
Forecasting
Selecting the number of lags p
3
Stationarity
Testing Stationarity
4
Forecasting Errors & Interval
Ec1123
Section 7
Peter Tu
[email protected]
30 October 2015
Peter Tu
Ec1123
30 October 2015
Table of Contents
1
PSET #6 Recap
Instrument Validity
Internal Validity
2
Treatment Effects
Average Treatment Effect
Local Average Treatment Effect (LATE)
LA
Ec1123 Section 7 - November 1, 2015
John Coglianese: [email protected]; OH Monday 10:30am-12:30pm Littauer M-42
Section 7: Instrumental Variables Regression II
1
1.1
Homework Review
F-Tests for second stage IV
The Stata command ivregress 2sls com
Ec1123
Section 8
Peter Tu
[email protected]
6 November 2015
Peter Tu
Ec1123
6 November 2015
Table of Contents
1
PSET #7 Recap
Instrument Validity
ATE v. LATE
2
Program Evaluation
3
Threats to the Validity of Experiments
4
Regression Discontinuity (R
Ec1123
Section 3
Peter Tu
[email protected]
25 September 2015
Peter Tu
Ec1123
25 September 2015
Table of Contents
1
PS 2 Recap
2
Causality
Conditional Mean Independence
3
Omitted Variable Bias
Direction of the Bias
Examples
4
Interaction Terms Revie