Economics 741
Homework #2 Due 6 Oct 2020 (Week 7)
Notes on Write Up
•
A write up
–
If I ask you to compare some numbers, please show me the numbers in the writeup.
–
If you are using LaTeX, print output in table form when it is more than just one number.
–
If you are not using LaTeX, paste things into some sort of table.
•
All code (.do and .R).
•
All output (Stata .log file and R workspace).
1
1 Chapter 5 (80 points)
1.1 Notes on Data Cleaning
•
Your dataset has eight variables in it:
–
perwt: survey weight
–
sex : gender of individual
–
age: age of individual
–
race: individual’s self-reported race
–
hispan: individual’s self-reported ethnicity
–
emptat: employment status of individual – occ1990 : occupation of individual (1990 codes)
–
incwage: labor market earnings of individual
•
Please limit your sample to focus on women who are employed and 35 years older or more.
•
Your initial y variable is incwage, labor earnings. Your key x variable is age.
•
Do the following exercises in Stata and R.
•
To do the R parts, you will just need to export the two key variables (incwage and age) from Stata into a .csv file, that you will import into R.
1.2 Chapter 5 Questions
1.
Run a regression of the key y variable on x in Stata (include a constant). Report the coefficients and standard errors. (10 points)
2.
Repeat this exercise in R. Show that your results match. (25 points)
3.
Interpret and explain the regression results. (15 points)
4.
Explain to me the three terms which contribute to the standard error of the estimate of β. (15 points)
5.
Using R, find the values of each part. Report them and show that you can calculate the standard error based on these three parts. (15 points)
2
2 Chapter 6 Questions (58 points)
1.
Continuing with the regressions from above, report results using White’s Heteroskedasticity Robust Standard Errors. (15 points)
2.
Let’s see how earnings varies with age. Take the log of earnings before running these regressions. Now please use both men and women who are employed and 35 years older or more. (28 points)
(a)
Run a linear regression of earnings on age. (4 points)
(b)
Run a quadratic regression of earnings on age. (4 points)
(c)
Run a cubic regression of earnings on age. (4 points)
(d)
Present the results from your three regressions in one graph. (4 points)
(e)
Make an argument about which specification is best. (6 points)
(f)
Using the cubic, let’s explore marginal effects. (6 points)
i. Report the average marginal effect of age on earnings. Do not use the MFX command! (3 points)
ii. Also report the average of the marginal effects. Do not use the MFX command! (3 points)
3.
We are now going to explore some racial wage gaps. (15 points)
(a)
Please first report summary statistics of doctors by ethnicity/race. Show share of sample and average wages. (3 points) Create five categories:
•
a) Black/African-American (Non-Hispanic)
•
b) Asian (Non-Hispanic)
•
c) Hispanic (Any Race reported)
•
d) Native-American (Non-Hispanic)
•
e) White (Non-Hispanic)
(b)
We will now run regressions on incwage to see if there are racial differences in earnings. Because of the size of the dataset, we will limit our analysis to just three groups: a, c, and e. (12 points)
i. First, run a regression using indicator (dummy) variables to see if there are wage gaps. (3 points)
3
ii. Next, add a control for age to see how this affects your estimates; explain any changes you see and how this relates to one of the assumptions that we talked about with linear models. (3 points)
iii. Finally, properly interact age and your indicators to see if there are different returns to experience for these groups. (6 points)
4
What Students Are Saying About Us
.......... Customer ID: 12*** | Rating: ⭐⭐⭐⭐⭐"Honestly, I was afraid to send my paper to you, but you proved you are a trustworthy service. My essay was done in less than a day, and I received a brilliant piece. I didn’t even believe it was my essay at first 🙂 Great job, thank you!"
.......... Customer ID: 11***| Rating: ⭐⭐⭐⭐⭐
"This company is the best there is. They saved me so many times, I cannot even keep count. Now I recommend it to all my friends, and none of them have complained about it. The writers here are excellent."
"Order a custom Paper on Similar Assignment at essayfount.com! No Plagiarism! Enjoy 20% Discount!"
