Test: ECON2300 Quiz 5 (Semester 2, 2022) – [...
Take Test: ECON2300 Quiz 5 (Semester 2, 2022)
[ECON2300] Introductory Econometrics (St Lucia & external). Semester 2, 2022 ECON2300S_7260_62727
Assessment Quizzes: Problem Solving Exercises
Take Test: ECON2300 Quiz 5 (Semester 2, 2022)
Test Information
Description
Instructions
Multiple
Attempts
Not allowed. This test can only be taken once.
Force
Completion
This test can be saved and resumed later.
Your answers are saved automatically.
Due date: 4pm, Friday, October 21, 2022
Please read all instructions carefully before opening the quiz.
Please pay close attention to the number of decimal places required for each answer.
The required number of decimal places may differ from question to question.
Avoid rounding during intermediate calculations where possible.
Some answers in this quiz will involve percentages or dollar figures. Do not include
a % or $ sign in any of your answers. For example, if the answer is 12%, just enter
12
The quiz is not timed. This means that you can open the quiz and return to it as
many times as you need to (provided that you do not click submit).
There is only one attempt for this quiz.
The quiz is marked out of 7, and contributes 7% towards your final grade.
The closing time for this quiz is 4pm on Friday, October 21, 2022. Please make
sure that you have submitted your answers by this time. Remember that you need
to click submit before the deadline for your quiz to be marked.
Please Note: If you encounter any technical issues with the quiz, please email the
CML coordinator at cml.2300@uq.edu.au. Do not email quiz issues to the Course
Coordinator or Course Administrator. Otherwise there may be a delay in responding to
your enquiry.
QUESTION 1 0.5 points Save Answer
Question Completion Status: Welcome Organisations Help
Click Save and Submit to save and submit. Click Save All Answers to save all answers.
Courses Bolong Wang 12
2022/10/18 14:55 Take Test: ECON2300 Quiz 5 (Semester 2, 2022) – [...
https://learn.uq.edu.au/webapps/assessment/take/launch.jsp?course_assessment_id=_261538_1&course_id=_161292_1&content_id=_8012459_1&step=null 2/6
1. Within each Factory, products are assigned randomly to
Process A or Process B.
2. Production costs for each product are recorded.
Suppose a manufacturing firm has two factories (Factory 1 and
Factory 2), and a single production process (Process A) that is used
in both factories. A new process (Process B) is developed that
potentially reduces production costs. To test whether Process B is
less costly than Process A, an experiment is designed where:
Note that resources (i.e. materials, workers, equipment) are not
reassigned across factories.
Let Yi be the cost of producing product i, let Xi be 1 if Process B is
used to produce i and 0 if Process A is used, and let Wi be 1 if
product i is produced in Factory 1 and 0 if it is produced in Factory 2.
In a regression of Yi on X, it is advisable to:
Exclude Wi as products are randomly assigned and including
Wi would increase standard errors
Exclude Wi as it is uncorrelated with Xi
Include Wi as E(ui | Xi) ≠ 0, but E(Xi | Wi) = 0
Include Wi as E(ui | Xi) ≠ 0, but E(ui | Xi, Wi) = E(ui | Wi
QUESTION 2
Continue to use the example from Question 1.
Suppose each product is randomly assigned to a process by a
computer program, but some products get reassigned on the factory
floor (for practical reasons). Let Zi denote the original assignment and
Xi the actual process used to produce i. In a regression of Yi
on Xi and Wi, OLS is:
Potentially biased because Wi should not be included
Potentially biased, but an IV regression using Zi as an
instrument can be used to obtain a consistent estimator
Unbiased because the products were randomly assigned in the
beginning
Unbiased as long as Zi is also included as a control variable
0.5 points Save Answer
QUESTION 3 0.5 points Save Answer
Question Completion Status:
Click Save and Submit to save and submit. Click Save All Answers to save all answers.
2022/10/18 14:55 Take Test: ECON2300 Quiz 5 (Semester 2, 2022) – [...
https://learn.uq.edu.au/webapps/assessment/take/launch.jsp?course_assessment_id=_261538_1&course_id=_161292_1&content_id=_8012459_1&step=null 3/6
Questions 3-6 require information from the following table.
Suppose that the Federal Government is considering a new tax on
cigarettes that is estimated to increase the retail price by $0.25 per
pack. If the current price per pack is $6.75, use the regression in
column (2) to predict the change in demand.
What is the (approximate) predicted percentage change in the
quantity of cigarettes? Report your answer as a percentage to two
decimal places without a percentage sign.
QUESTION 4
Continue to use the information in column (2) from Question 3.
Is there evidence that the instrument in this column is weak?
What is the relevant test statistic? (Report
the number as it appears in the table).
Therefore, does this suggest that the instrument is weak? (Type Yes
or No)
1 points Save Answer
a.
b.
c.
d.
QUESTION 5
For this question use information in column (3) from Question 3.
From the information provided, what can we conclude about the
exogeneity of the instruments? Use a 5% level of significance.
Both the instruments are exogenous.
Neither of the instruments are exogenous.
At least one of the instruments is exogenous.
At least one of the instruments is endogenous.
0.5 points Save Answer
Question Completion Status:
Click Save and Submit to save and submit. Click Save All Answers to save all answers.
2022/10/18 14:55 Take Test: ECON2300 Quiz 5 (Semester 2, 2022) – [...
https://learn.uq.edu.au/webapps/assessment/take/launch.jsp?course_assessment_id=_261538_1&course_id=_161292_1&content_id=_8012459_1&step=null 4/6
a.
b.
c.
d.
QUESTION 6
For this question use information in column (2) of question 3.
Can you test for the exogeneity of the instrument in this model?
Yes, I can use a t-test.
I don't need to test, instruments are always exogeneous.
Yes, I can use a J-test, even if it is not reported in the table.
No, in order to test for exogeneity, the model must be
overidentified, with the number of instruments strictly larger
than the number of endogenous variables.
0.5 points Save Answer
a.
b.
c.
d.
e.
f.
QUESTION 7
Estimation of the IV regression model:
is possible if the number of instruments is equal to the
number of endogenous variables.
is possible if the model is over-identified.
is possible if the number of instruments is larger than the
number of endogenous variables.
is possible if there is exact identification.
All of the above.
None of the above.
0.5 points Save Answer
a.
b.
c.
d.
e.
f.
QUESTION 8
Which one of the following statements is true:
If E(u|X)≠ 0, OLS is an inconsistent estimator.
If E(u|Z)=0 and Corr(X,Z)≠ 0, then Z is a valid instrument.
If E(u|X)=0, you don’t need to look for instruments.
If E(u|X)≠ 0 and Corr(X,Z) = 0, then Z is not a valid
instrument.
All of the above.
None of the above.
0.5 points Save Answer
Question Completion Status:
Click Save and Submit to save and submit. Click Save All Answers to save all answers.
2022/10/18 14:55 Take Test: ECON2300 Quiz 5 (Semester 2, 2022) – [...
https://learn.uq.edu.au/webapps/assessment/take/launch.jsp?course_assessment_id=_261538_1&course_id=_161292_1&content_id=_8012459_1&step=null 5/6
a.
b.
c.
d.
e.
f.
QUESTION 9
When calculating the TSLS estimator:
you regress X on Z and then Y on the predicted values of the
first regression.
you regress X on Z and then Y on Z.
you regress Y on X and then regress Y on Z.
you regress Z on X and then Y on the predicted values of the
first regression.
you regress Y on Z and then X on the predicted values of Y.
None of the above.
0.5 points Save Answer
a.
b.
c.
d.
e.
f.
QUESTION 10
Having many relevant instruments:
is good because they provide more information.
leads to underidentification.
typically results in larger standard errors for the TSLS
estimator.
means that we will have more than one first stage regression.
All of the above.
None of the above.
0.5 points Save Answer
a.
b.
c.
d.
e.
f.
QUESTION 11
Assume that data are available on other characteristics of the
subjects that are relevant to determining the randomized
experimental outcome. Then not including these determinants
explicitly results in:
the limited dependent variable model.
omitted variable bias.
the multiple regression model.
large scale equilibrium effects.
All of the above.
None of the above.
0.5 points Save Answer
Question Completion Status:
Click Save and Submit to save and submit. Click Save All Answers to save all answers.
2022/10/18 14:55 Take Test: ECON2300 Quiz 5 (Semester 2, 2022) – [...
https://learn.uq.edu.au/webapps/assessment/take/launch.jsp?course_assessment_id=_261538_1&course_id=_161292_1&content_id=_8012459_1&step=null 6/6
a.
b.
c.
d.
e.
f.
QUESTION 12
Causal effects that depend on the value of an observable variable,
say W : i
cannot be estimated.
can be estimated by interacting the treatment variable
with W .i
result in the OLS estimator being inefficient.
requires use of homoskedasticity-only standard errors.
All of the above.
None of the above.
0.5 points Save Answer
a.
b.
c.
d.
e.
f.
QUESTION 13
In the context of a controlled experiment, consider the simple linear
regression formulation Y = β + β X + u . Let the Y be the
outcome, X the treatment level when the treatment is binary,
and u contain all the additional determinants of the outcome. Then:
i 0 1 i i i
i
i
the OLS estimator of the slope will be inconsistent in the
case of a randomly assigned X since there are omitted
variables present.
i
X and u will not be independently distributed if the X are
randomly assigned.
i i i
β represents the causal effect of X on Y when X is zero.0
E(Y|X= 1) is the expected value for the treatment group.
All of the above.
None of the above.
0.5 points Save Answer
Question Completion Status:
Click Save and Submit to save and submit. Click Save All Answers to save all answers.