关键词 > ECON440.606
APPLIED ECON 440.606 — Econometrics Midterm Exam
发布时间:2022-08-11
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit
APPLIED ECON 440.606 — Econometrics
Midterm Exam
Problem 1 (25 Points)
In a Master’s Program in Applied Economics, a professor has observed the following final grade and attendance of his students in Microeconomics:
Student Type |
Grade |
Attendance |
A |
70 |
60 |
B |
100 |
80 |
C |
60 |
70 |
D |
90 |
100 |
E |
80 |
75 |
Considering this information, answer the following questions:
a) Draw a graph to illustrate this relationship between Attendance (X) and Grade (Y). What kind of association (positive, negative, or neutral) do you find in the graph? Explain why (5 points).
b) Show one formula (either matrix or sum) to obtain the linear relationship between grade and attendance. Then, calculate the intercept and the slope using the formula presented. Interpret your eventual answer (10 points).
c) Show the formula for the R-square and calculate it using the formula proposed. How can you interpret this outcome? (5 points).
d) If you are willing to take this course and you want to finish with a grade B+ (88 or 89), what should your attendance be? Interpret your result (5 points).
Problem 2 (25 Points)
A researcher is interested to understand what affects the time spent sleeping among students from the master’s program at John Hopkins University. She believes that sleeping time is a linear function of the total daily time spent working, individual’s age and individual’s weight. Having this information, please answer the following questions:
a) If you write down the econometric specification for this investigation, provide at least one example of what could be in the error term (affects time spent sleeping but it is NOT one of these three variables and it is difficult to measure) (3 points).
b) After running the regression with the referred variables, the estimated equation is
ŝleep = 2 − 0.3 totwoTk + 0.01age + 0.05weigℎt
Where the total number of students in the sample is 706. What happens if someone decides to work one extra hour? What is the expected sleeping time if someone weights 98.4 kg, is 28 years old and works 4 hours daily? Interpret your answers (7 points).
c) Among these 706 students, the average age is 25, average weight is 79 kg, and the average time spent sleeping is 8. Based on that, what can you say about the average time working? Interpret your answer (5 points).
d) After collecting the data from the students, another researcher suggested to include the number of years of education, but she observed that all students have the same number of years studying. Discuss the pros and cons of introducing the number of years of education as an independent variable in this regression (10 points).
Problem 3 (25 Points)
A researcher collected Covid death rates across 300 municipalities in a particular country from 2021. He wants to understand whether the percentage of people vaccinated can explain the death rates, but he knows that other factors might also affect it. In summary, he has estimated the model and got the following outcome
deâtℎTate = 20 − 2 VaCPeTC + 3.2 RiSkPeTC + 4 0ldPeTC + 1.5 AtℎletPeTC
(4.5) (0.5) (0.8) (1.2) (2.0)
Where deathrate is the percentage of people who died of covid, VacPerc is the percentage of people vaccinated, RiskPerc is the percentage of people with high health risk, OldPerc is the percentage of people older than 60 and AthletPerc is the percentage of people who are athletes in the city. Based on this information (SE is below the estimated parameter), answer the following questions below.
a) Evaluate whether all the parameters are statistically significant to explain the percentage of people who died of covid (Hint: do not forget to draw the graphs) . (10 points)
b) If the researcher has used the number of deaths and the number of vaccinated people, both in logs, how would you interpret this new parameter estimated. (5 points)
c) Someone says that you should eliminate any parameter that is not statistically significant. After doing that, your unrestricted model has SSR = 183 and R-squared = 0.6, while your restricted model has SSR = 198 and R-squared = 0.5. What do you conclude after doing an F-test for this? Why should (or should not) you compare the R-squared to decide to include or not the variables with non-significant parameters? (10 points)
Problem 4 (25 Points)
A professor of Economics wants to evaluate whether he has any gender bias on grading the students as well as whether students perform worst when taking online courses. After collecting data from the last two years, he obtained the following outcome when regressing the grade on two dummies: gender (male=1, female=0), online (online=1, in-person=0).
ĝrade = 90 − 1. 98 gender − 13. 45 Online
(3.60) (2.56) (3.60)
n=178, R-squared = 0.07
a) Based on the rule of thumb, how do you interpret this outcome? (5 points)
b) Someone told this professor that he needs to consider the efforts made by his students. Then, this professor decided to run another regression including the grades from the Problem Sets and the Midterm. After adding these new variables, he found the following:
Interpret this new outcome [gender, online, problem sets (ps), and mdexam (midterm exam grade)], stressing the differences that you have found in letter a. (10 points)
c) He showed his outcome to a gender specialist, and this person said: “You should know that the pandemic has affected much more women than men, so your outcome might be influenced by the grades obtained by woman attending in person without any home obligation. Their performance might have offset the bad outcomes of those suffering doing their home tasks while attending your classes. Everyone knows that women perform much better than men in any course when they have the same opportunities .” Then, this professor ran another regression creating other dummies for gender and online, and he found the following outcome.
Knowing that femonl is a dummy for women attending the class online, femperson is a dummy for women attending class in-person and maleperson is a dummy for men attending class in-person. How can these results explain the claims made by this gender specialist? After seeing these results, the gender specialist said: “You have not controlled by male online, so your parameters are biased.” How should this professor respond to this comment? (5 points)
d) If this professor wants to test whether these two dummies’ parameters are statistically non-significant together, which restricted model should he use? The one from letter a or the one below?
Based on your answer, do you have all the information to test whether the parameters for gender and online are both jointly equal to zero? If yes, calculate it and interpret it. (5 points).