ECMT1020 Introduction to Econometrics 2022S2
Assignment
Due 28 October, 11:59 pm
Academic Dishonesty and Plagiarism
Academic honesty is a core value of the University, so all students are required to act honestly,
ethically and with integrity. This means that the University is opposed to and will not tolerate
academic dishonesty or plagiarism, and will treat all allegations of academic dishonesty and
plagiarism seriously. The consequences of engaging in plagiarism and academic dishonesty, along
with the process by which they are determined and applied, are set out in the Academic Honesty
in Coursework Policy 2015.1
Instructions
1. There are 10 questions in this assignment each worth 3 marks. The assignment has a
maximum of 30 marks and accounts for 15% of your final grade.
2. This assignment entails the use of econometric models and statistical tools in an economic
application. You will use a statistical software, Stata, to analyze data on educational
attainment and wages.
3. Your assigned dataset is the CSV spreadsheet EAWE#.csv, where # is the last digit of your
University of Sydney SID. Please use your assigned dataset to answer the questions. Write
your dataset number on the front page of your work. Using the wrong dataset will be
reviewed as a potential case of Academic Dishonesty.
4. Answer all the questions. Show all numerical answers to 3 decimal places. Carry out all
tests using a 5% level of significance. You may include Stata outputs in your answers, but
your own interpretations and explanations are necessary for earning marks.
5. When answering the questions, please keep your statements concise as well as accurate.
Excessively long responses indicate a lack of understanding and will be penalized accor-
dingly.
6. You will have to type your answers. Handwritten submissions will not be accepted.
7. The assignment is anonymously marked. Save your answers in a pdf file2 named 123456789.pdf
where 123456789 is your 9-digit SID. Do NOT put your name in your work or anywhere
in your submission. Do NOT include a cover sheet.
8. Submit the pdf file through Turnitin under the Canvas module ‘Assignment’. Late sub-
mission is subject to a penalty of 5% per calendar day. Work submitted more than 10
days after the due date will receive a mark of zero.
1You can find these documents at http://www.sydney.edu.au/policies (enter ‘Academic Honesty’ in the
search field).
2You can write your answers in a Word document and then save it as a pdf file.
1
Data Description
You will use a subset consisting of 500 observations of the Educational Attainment and
Wage Equations (EAWE) dataset to answer the questions. The description of the dataset and
contained variables can be found in Appendix B on p.565–569 of the textbook.
Questions
1. Fit an educational attainment function using your dataset. Regress S on ASV ABC, SM
and SF , and interpret the regression results. Perform t tests on the coefficients of the
variables in the education attainment function.
2. Perform a F test of the explanatory power of the equation you obtained in Question 1.
Calculate the F statistic using R2 and verify it is the same as the F statistic in your Stata
output.
3. Regress the logarithm of EARNINGS on S and EXP . Interpret the regression results,
perform t tests on the coefficients and F test of the explanatory power of the model.
4. Regress logarithm of EARNINGS on S, EXP ,MALE, ETHHISP and ETHBLACK.
Interpret the regression results and perform t tests on the coefficients.
5. Redo Question 4 making ETHBLACK the reference category. What are the impacts of
change of reference on the interpretation of the coefficients and the statistical tests (t tests
of the coefficients and F test of the model)
6. Define a slope dummy variable as the product of MALE and S. Regress the logarithm of
EARNINGS on S, EXP , ETHHISP , ETHBLACK, MALE, and the slope dummy
variable. Interpret the equation and perform appropriate statistical tests (t tests of the
coefficients and F test of the model). Is the effect of education on earnings different for
males and females
7. The composite measure of cognitive ability, ASV ABC, in the dataset was constructed as
a weighted average of the scores of tests of arithmetic reasoning, ASV ABAR, word know-
ledge, ASV ABWK, and paragraph comprehension, ASV ABPC, with ASV ABAR being
given double weight. Show mathematically that, when fitting the educational attainment
function
S = β1 + β2SM + β3SF + β4ASV ABC + u,
instead of the model using the individual scores
S = β1 + β2SM + β3SF + γ1ASV ABAR+ γ2ASV ABWK + γ3ASV ABPC + u,
one is implicitly imposing the restrictions γ1 = 2γ2 and γ1 = 2γ3. Perform a test of these
restrictions using your dataset.
8. Fit a wage equation with EARNINGS as the dependent variable and S, EXP andMALE
as the explanatory variables. Perform a Goldfeld-Quandt test for heteroskedasticity in the
S dimension.
9. Fit a wage equation using the same specification as in Question 8. Perform a White test
for heteroskedasticity.
10. Perform an OLS regression of the logarithm of hourly earnings on S, EXP , ASV ABC,
MALE, ETHBLACK and ETHHISP using your dataset and an IV regression using
SM , SF , and SIBLINGS as instruments for ASV ABC. Perform a Durbin-Wu-Hausman
test to evaluate whether ASV ABC appears to be subject to measurement error.
