Econometrics
ECON7020X:
Homework 3
Name: Fill in your name
Due: 11/16/2020 Extended to 11/23/2020 11:59 PM via Blackboard
Instructions:
Use the dataset on California Schools (CASchool) to attempt the questions below. We have used this dataset in the 10/26 class. The 10/26 folder on Blackboard contains some R and SPSS syntax, which would be useful. Additionally, the lecture for 11/9/2020 discusses a table like this.
Please make a note of the following:
1) Submit the word document with your answers pasted here.
2 a) If using R, submit the script file with a .R extension.
2 b) If using SPSS, please upload the output file with a .spv extension.
3) In R/ SPSS, please add comments on what regression is being run. For example: Regression #1 in table.
4) Please fill in your name and title your files Lastname_Firstname_HW3.
Variable description:
|
observation_number |
Observation Number |
|
dist_cod |
District Code |
|
county |
County |
|
district |
District |
|
gr_span |
Grade span of district |
|
enrl_tot |
Total enrollment |
|
teachers |
Number of Teachers |
|
calw_pct |
Percentage of students in the public assistance program, CalWorks |
|
meal_pct |
Percentage of students that qualify for a reduced-price lunch |
|
computer |
Number of computers |
|
testscr |
Average Test scores (read_scr+math_scr)/2 |
|
comp_stu |
Computer per student |
|
expn_stu |
Expenditure per student |
|
str |
Student-Teacher Ratio |
|
avginc |
Average district income |
|
el_pct |
Percentage of students that are English Learners |
|
read_scr |
Average reading score |
|
math_scr |
Average math score |
Before starting, ensure you have 420 observations. Do not delete any observations.
The dependent variable for all regressions is testscr. In the Economic Control variables table, Y indicates it was included and N indicates that the variable was not included while running the regression. The numbers reported in the top portion of the table are parameter estimates, while those in brackets are the standard errors.
Questions:
1. Replicate the regressions with HC1 heteroskedastic errors in the table on the next page. Report the SER and R-square as well. Please arrange your results in the same format. (7 regression x 1=7 points)
For example, in Model (1) in the table on the next page, the run is:
2. For Model 6, run and interpret the hypothesis tests in the lower portion of the table. (3 tests x 1 point = 3 points)