Dornsife College of
Letters, Arts and
Sciences,
Department of
Economics
ECONOMICS 318, 26134R- Introduction to Econometrics
Units: 4
Summer 2016, Tue, Wed, Thu 10:00-11:50 am
Location: KAP-147.
Instructor: Manochehr Rashidian
Office: KAP-116B
Office Hours

CHAPTER 7
SOLUTIONS TO PROBLEMS
7.2 (i) If cigs = 10 then ! log(bwght ) = .0044(10) = .044, which means about a 4.4% lower
birth weight.
(ii) A white child is estimated to weigh about 5.5% more, other factors in the first equation
fixed. Further, twhite 4

Econ 318
Exam 2
Name_
1- In the following model of production function of corn, Output is quantity of output measured in 1000 lb, L is # of
workers, K is $ capital, R is rainfall in inches, T is average temperature in month of April and Ln is natural log.

Econ 318
Exam 1-S16
1- Consider the following bivariate probability distribution for X and Y:
X=1
0.10
0.15
0.25
Y=0
Y=2
Y=4
Name_
X=2
0.15
0.10
0.25
Find the following:
E(X)=1.5
E(Y)=2.5
E(Z) where Z=2Y-X
E(Z)=2E(Y)-E(X)=3.5
E(Y|X=2)=0(.15/.5)+2(.1/.5)+4

CHAPTER 8
SOLUTIONS TO PROBLEMS
8.4 (i) These coefficients have the anticipated signs. If a student takes courses where grades are,
on average, higher as reflected by higher crsgpa then his/her grades will be higher. The
better the student has been in the

Class problem for chapter 10
Use Ramanathan 9-6 data to complete the following problem.
1- Given all 3 variables are trending (have a time trend), Estimate the following model and
interpret the parameter estimates and the R2.
Model 1:
Intratet =0+ 1lmoney

1.
2.
3.
4.
5.
6.
7.
Solution to extra homework from heteroskedasticity chapter
Using data set ramanathan 9-3 where reskwh=B0 +B1nocust + B2 price +B3cdd + u
Test for heteroskedasticity (5%) using G-Q test with nocust as cause of heteroscedasticity.
Test

CHAPTER 6
SOLUTIONS TO PROBLEMS
6.3 (i) The turnaround point is given by 1 /(2| 2 |), or .0003/(.000000014) 21,428.57;
remember, this is sales in millions of dollars.
(ii) Probably. Its t statistic is about 1.89, which is significant against the one-sided

Data: Ramanathan 4-4, demand for bus travel.
1- Use method of OLS to estimate the parameters of the following model:
BUSTRAVL = 0+ 1FARE+ 2GASPRICE+ 3INCOME+ 4POP+ 5DENSITY+ 6LANDAREA+u
a. Do parameter estimates have the expected sign? Explain
b. Test for

Data: Ramanathan 4-4, demand for bus travel.
1- Use method of OLS to estimate the parameters of the following model:
BUSTRAVL = 0+ 1FARE+ 2GASPRICE+ 3INCOME+ 4POP+ 5DENSITY+ 6LANDAREA+u
a. Do parameter estimates have the expected sign? Explain
Model 1: OL

Class Problem Set 2
1-Which one of the following estimators of population mean () is unbiased? Which one is more
MSE efficient? (Y1,Y2, and Y3 are 3 random and independent observations)
M1=0.15Y1+0.25Y2+0.6Y3
M2=0.33Y1+0.34Y2+0.35Y3
E(M1)=.15+.25+.6=
Unbi

CHAPTER 10
10.5 The functional form was not specified, but a reasonable one is
log(hsestrtst) = 0 + 1t + 1Q2t + 2Q3t + 3Q3t + 1intt +2log(pcinct) + ut,
Where Q2t, Q3t, and Q4t are quarterly dummy variables (the omitted quarter is the first) and the
other

Class problem for chapter 10
Use Ramanathan 9-6 data to complete the following problem.
1- Given all 3 variables are trending (have a time trend), Estimate the following model and
interpret the parameter estimates and the R2.
Model 1:
Intratet =0+ 1lmoney

Class problem 7, Heteroscedasticity
Use data set ramanathan 9-3 to work with the following model:
Model (1) reskwh=0 +1nocust + 2 price +3cdd + u
1.
2.
3.
4.
Test for heteroskedasticity (5%) using G-Q test with nocust as cause of heteroscedasticity.
Test

Class problem set 3
You need to show your work. All parts must be done manually without use of a software.
Sales
Experience
2
1
2100
17
2253.349 -153.3491
23516.0
2
2000
20
2587.670 -587.6704
345356.5
3
3500
28
3479.194
4
2400
22
2810.551 -410.5513
168552

CHAPTER 12
SOLUTIONS TO PROBLEMS
12.3 (i) Because U.S. presidential elections occur only every four years, it seems reasonable to
think the unobserved shocks that is, elements in ut in one election have pretty much
dissipated four years later. This would

Use data GREENE7_8 for the following exercise.
Consider the following 2 models:
Model 1:
G = 0 + 1Pg + 2 ln(Y) + 3Pnc + u
Model 2:
ln(G) = 0 + 1Pg + 2 ln(Y) + 3Pnc + u
1- Estimate both models
2- Make a prediction for average G from model 1 when Pg=3, Y=10