University of California, San Diego
Economics 120B
Summer Session II 2015
Problem Set 1
Due Wednesday, Aug. 19
Please staple your Stata output (.log) file to your answers. Include the Stata output
for results you report in question #4.
1. Sir Francis Galt
Econometrics Spring 2013
Lecture Note 4: Linear Regression with One Regressor
(SW 4.14.5)
1
The Linear Regression Model and Assumptions
The model we consider is
Yi = 0 + 1 Xi + ui
for i = 1, . . . , n, where
Yi is the dependent variable, the regressand,
ECON 120C  SYLLABUS (SUMMER II, 2015)
Foster, UCSD, September 4, 2015
Teaching Staff and Consultation Hours
Name/Position
Times
Room
Contact Info
MW
Carroll B. Foster
ECON
11cfoster @ mail.ucsd.edu
(PhD/Lecturer)
110C
noon
Roy Allen
rhallen @ ucsd.edu
Ka
Problem Set 3, Econ 120B
Prof. Yixiao Sun
Due on August 28
Part A
1. Let
Y = E (Y jX) + [Y
where f (X) = E (Y jX) and u = Y
E (Y jX)] = f (X) + u
E (Y jX) : Show that Eu = 0:
2. Let Y = X 3 +u where X and u are independent standard normals. Compute E (Y j
The Islamic University of Gaza
Faculty of Commerce
Economics Department
Econometrics & Quantitative Analysis Dr. Samir Safi
2/3/2013
Midterm Examination #1
NAME:_ID:_
Question #1 (20 Points):
For each question below, circle the correct answer
1) Analyzing

name: <unnamed>
log: C:\Users\shlay\Desktop\Sharon Lay HW 3.log
log type: text
opened on: 11 Mar 2015, 17:10:55
. gen ln_income=ln(income)
. reg fatalityrate sb_useage speed65 speed70 ba08 drinkage21 ln_income age, r
Linear regression Number of obs
University of California, San Diego
Department of Economics
Summer Session II 2015
ECON 120B: Econometrics
Prof. Augusto Nieto Barthaburu
Lectures: TuTh 11:001:50 PM at Center Hall 113
Discussion section: W 2:003:50 PM (location TBA)
Email: anieto@ucsd.
Econ 120B: Econometrics
Summer Session II, 2015
UCSD
Confidence Intervals
Confidence Intervals
A 95% confidence interval for Y is an interval that contains the
true value of Y in 95% of repeated samples.
Digression: What is random here? The values of Y1,Y
Econ 120B: Econometrics
Summer Session II, 2015
UCSD
Regression with a Single Regressor:
Hypothesis Tests and Confidence Intervals
Overview
Now that we have the sampling distribution of OLS
estimator, we are ready to perform hypothesis tests about 1
and
Econ 120B: Econometrics
Summer Session II, 2015
UCSD
Probability: events best thought of as uncertain
Events:
A Chargers beat Raiders on Sunday (0no,1yes)
B  Chargers beat Raiders by over ten points
C  Alibaba stock price rises above $90 sometime this
Econ 120B: Econometrics
Summer Session II, 2015
UCSD
Discussion Section Tomorrow
Tomorrows section will be held in the computer
lab at SH 142 once again
The TA will show you how to import data and
compute sample statistics and regression using
Stata
12
Econ 120B: Econometrics
Summer Session II, 2015
UCSD
Heteroskedasticity and Homoskedasticity
What do these two terms mean?
o If var(uX=x) is constant that is, if the variance of the
conditional distribution of u given X does not depend on X
then u is s
Ec 120BC ECONOMETRICS B and C
Foster, UCSD
LECTURE NOTES
September 4, 2015
TOPIC 12. MULTIPLE OLS REGRESSION
A. Classical Multiple Linear Regression Model
1. Assumptions of the OLS Model:
A
1
A
2
A
3
A
4
A
5
A
6
CLRM Assumptions
Yi = 1 + 2Xi + 3Wi + + kHi
Ec 120B  ECONOMETRICS B
Foster, UCSD
LECTURE NOTES
September 4, 2015
TOPIC 11. SIMPLE OLS REGRESSION
A. Overview of Econometrics
1. Definitions:
a) Econometrics the application of mathematical/statistical methods to economic data to
investigate relations
Problem Set 2
Econ 120B, UCSD
Prof. Yixiao Sun, O ce: Econ 219
Due on August 21
1. (a) Suppose there is no explanatory variable. Derive the formula for the OLS estimator of
a regression of Y on a constant/intercept only. Your solution should give the form
Problem Set 1
Econ 120B, UCSD
Prof. Yixiao Sun, O ce: Econ 219
Due on August 10
1. Let X1 and X2 be iid random variables with
8
< 8; with probability of 1/4
4; with probability of 1/2 i = 1; 2
Xi =
:
0; with probability of 1/4
(a) What is the mean of Xi ?
Chapter 4 & 5
CHAPTER 4  Agency:
1. Who is considered the Principal in a real estate relationship? Define
'agency' as according to the California Civil Code. Explain what is a Fiduciary
Relationship, how is it created and how does it obligate the agent?
Econometrics Spring 2013
Lecture Note 2: Review of Probability (2.52.6)
1
Random Sampling and the Distribution of the Sample Average
1.1
Random sampling
In statistical inference, it is important to distinguish the dierence between population and sample.
Econometrics Spring 2013
Lecture Note 5: Regression with a Single Regressor: Hypothesis
Tests and Condence Intervals (SW 5.15.4)
1
Testing Hypotheses About One of the Regression Coecients
1.1
TwoSided Hypotheses Concerning 1
Testing hypotheses about the
Econometrics Spring 2013
Lecture Note 1: Review of Probability (SW 2.12.4)
1
Sample Space and Probability
Denition 1 (Experiment)
An experiment is a process with an observable uncertain outcome.
Denition 2 (Sample space)
The sample space () is the set of
Econometrics Spring 2013
Lecture Note 7: Hypothesis Tests and Condence Intervals in
Multiple Regression (SW 7.17.3, 7.5)
1
Hypothesis Tests and Condence Intervals for a Single Coecient
1.1
Hypothesis Tests for a Single Coecient
The model is
Yi
= 0 + 1 X1
Econometrics Spring 2013
Lecture Note 3: Review of Statistics (SW 3.13.3)
1
Estimation of the Population Mean
Suppose that you want to know the population mean. Given i.i.d. observations Y1 , . . . , Yn with E[Yi ] =
and Var[Yi ] = 2 , the most natural
Midterm, Econ120B
Summer 2013, UCSD, Professor: Yixiao Sun
Last Name
First Name
UCSD PID
INSTRUCTIONS
1. Do not turn this page until instructed.
2. The exam has a total of 100 points. The number of points for each question is indicated with
the question.
Problem Set 3, Econ 120B
Prof. Yixiao Sun
Due on August 28
Part A
1. (1) Let
Y = E(Y jX) + [Y
where f (X) = E(Y jX) and u = Y
E(Y jX)] = f (X) + u
(1)
E(Y jX): Show that Eu = 0:
<Answer> It is straight forward to show that Eu = E [Y E(Y jX)] = E[Y ] E [E(
Econometrics Spring 2013
Lecture Note 6: Linear Regression with Multiple Regressors
(SW 6.16.7)
One of the main goals of modern econometrics is to infer a causal relationship among variables. Simply
nding two variables are correlated is not enough to con
Key concepts for the nal
Yixiao Sun
September 3, 2013
Recap: hypothesis testing: dierence of means
construct t statistic
condence interval
LLN and CLT
Linear regression with one regressor
OLS estimation: minimize sum of squared residuals, obtain formu
Final Exam, Econ120B
Summer 2011, UCSD, Professor: Yixiao Sun
1. Place all multiple choice answers in the table below.
Answers elsewhere won't be counted.
Q1
D
Q6
A
Q11
D
Q16
C
Q2
A
Q7
C
Q12
C
Q17
C
Q3
D
Q8
D
Q13
D
Q18
B
Q4
C
Q9
D
Q14
D
Q19
C
Q5
A
Q10
B
Q
1
Practice Midterm
Econ120B
1. Do you agree or disagree with the following statements? Circle your answer. There is no need
to provide any explanation. (The real mid term will have 10 statements)
(a) Suppose Yi s iid with mean : Then Y has the smallest va
Midterm, Econ120B
Summer 2011, UCSD, Professor: Yixiao Sun
1. (25 points) Do you agree or disagree with the following statements? Circle your answer. There
is no need to provide any explanation. 2.5pts for each statement.
(a) Suppose E(U ) = EX = 0: If E(