Homework 4
This assignment is worth 20 points in total. It is composed of 2 parts:
Part 1 - Multiple Choice (15 points, 3 attempts, no time limit)
There will be 15 multiple choices. Each question is worth 1 point.
Part 2 - Code and Code Output (5 points, unlimited attempts, no time limit)
You need to present both code and code output for each question in order to receive full 10
points. Upload your code unde
Assignments - Homework 4 (Upload Your Code Here) . I accept html, word, or pdf
file.
Problem 7.20
In this exercise, we will explore some of the factors predicting costs at American universities
using the data file poolcoll2 and observations outside the great recession. Let:
TC = the real ($2008) total cost per student,
FTUG = number of full-time undergraduate students,
FTGRAD = number of full-time graduate students,
FTEF = full-time faculty per 100 students,
CF = number of contract faculty per 100 students,
FTENAP = full-time nonacademic professionals per 100 students.
Quesiton 1:
Estimate the regression of ln(TC) on the remaining variables. What are the predicted effects of
additional undergraduate students? Note that measurement for variable FTUG is per 1000
students, not per student (round to 2 decimals)
Quesiton 2:
Based on the results in Question 1, what are the predicted effects of additional graduate
students on total cost per student? Note that measurement for variable FTGRAD is per 1000
students, not per student (round to 2 decimals)
Question 3:
ECON 123A: ECONOMETRICS I
Homework 4
(Due: November 30 Tuesday at 3 pm, Pacific Time)
Based on the results in Question 1, what are the predicted effects of additional full-time faculty,
contract faculty, and nonacademic professionals on total cost per student? (round to 2 decimals)
Question 4:
Add the indicator variable PRIVATE to the model in Questions 1. Provide the estimated model.
(round to 4 decimals)
Question 5:
Do you predict higher or lower total cost per student at private universities? Is this a statistically
significant factor in predicting total cost per student? (use integer)
Question 6:
Estimate the model in Question 1 twice, once for private universities and once for public
universities. Call the sum of squared residuals for the private universities SSE1, and the sum of
squared residuals for the public universities SSE0. Report values for SSE1 and SSE0. (round to
4 decimals)
Quesiton 7: Add to the model in Question 1 not only PRIVATE but also PRIVATE times all the
other variables. Call the sum of squared residuals from this model SSE2. Report value for SSE2.
(round to 4 decimals)
Question 8: Compare SSE1 + SSE0 to SSE2. What do you conclude? (round to 4 decimals)
Problem 7.23
In the STAR experiment (Section 7.5.3), children were randomly assigned within schools into
three types of classes: small classes with 13–17 students, regular-sized classes with 22–25
students, and regular-sized classes with a full-time teacher aide to assist the teacher. Student
scores on achievement tests were recorded as well as some information about the students,
teachers, and schools. Data for the kindergarten classes is contained in the data file
star5_small2.csv .
Consider the regression:
   (equation (A))
Question 9: Estimate the regression model in equation (A), where AIDE is an indicator variable
equaling 1 for classes taught by a teacher and an aide, and 0 otherwise.Test the statistical
significance of at the 5% level. (round to 4 decimals)
Question 10: Add the additional explanatory variable TCHEXPER in equation (A). Does its
addition to the model affect the estimates of and ? (round to 4 decimals)
Problem 7.30
MATHSCOR = + SMAL + AID +Ei β1 β2 Li β3 Ei ei
β3
β2 β3
What effect does having public health insurance have on the number of doctor visits a person
has during a year? Using 1988 data, rwm88.csv , from Germany we will explore this
question.
Question 11: Construct a histogram of DOCVIS (use 9 bins for the histogram). How many
doctor visits do most patients in the survey have during the year? (use integer)
Question 12: Based on the results in Question 11, what are the mean and median number of
doctor visits? (round to 2 decimals)
Question 13: Based on the results in Question 11, what is the 90th percentile? (use integer)
Question 14: Estimate the regression model with dependent variable DOCVIS and explanatory
variables FEMALE, HHKIDS, MARRIED, SELF, EDUC2, HHNINC2. Comment on the
significance of these predictor variables.
Question 15: Estimate the regression model with dependent variable DOCVIS and explanatory
variables FEMALE, HHKIDS, MARRIED, SELF, EDUC2, HHNINC2 separately for those with
public insurance (MODEL 1) and those who do not have public insurance (MODEL 2). Compare
the coefficients from the two models.