Scribd
Upload
35 views3 pages

STATA 2 Class

Uploaded by

wasay usmani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
35 views3 pages

STATA 2 Class

Uploaded by

wasay usmani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

STATA-2 [25 marks]

WASAY USMANI AND SHAYAN ASKARI

Based on Jacob Mincer’s “Schooling, Experience, and Earnings” work published in 1974, we will explore
the impact of education (years of schooling) on labor market earnings.

1. Download the dataset Table19_4 from CANVAS and import it into STATA. [1 mark]
2. Exploring the data.
a. How many white people are in the data? Create a dummy variable “white”. [1 mark]
b. Plot a histogram of earnings with percent on the y-axis. Export and paste the output
below. Comment on the shape of the distribution. What, if anything, needs to be done
before using the variable in a regression? [3 marks]

Ans ) This is positively skewed as we can see the tail going towards the left. It has an
asymmetrical distribution.
3. Consider the variables: s (schooling), sm (mother’s schooling) and sf (father's schooling).
a. Construct a variable “parental_education” that captures the expected value of parental
education. [1 mark]
b. Using the new variable run a regression model to determine how inter-generational
education has changed? [2 marks]
c. Determine if the model suffers from multicollinearity or heteroscedasticity. What, if
anything, needs to be done? [3 marks]
Ans) estat hettest

Breusch–Pagan/Cook–Weisberg test for heteroskedasticity


Assumption: Normal error terms
Variable: Fitted values of parental_education

H0: Constant variance

chi2(1) = 0.48
Prob > chi2 = 0.4902

The value shows no heteroskedasticity.

. estat vif ( MULTICOLINEARITY TEST)

Variable | VIF 1/VIF


-------------+----------------------
s | 1.00 1.000000
-------------+----------------------
Mean VIF | 1.00

NO multicollinearity since value is less than 5.

4. Consider the model: Earning s i=B 1+ B2 S i +B 3 Wex p i+ B 4 Female i+ B5 Ethnicit y i +ui


a. Using appropriate variables run the regression and interpret all significant coefficients.
[5 marks]
b. Determine if the model suffers from multicollinearity or heteroscedasticity. What, if
anything, needs to be done? [3 marks]
c. Any omitted variables? Hint: use command ovtest, paste output below, and interpret
the results. [3 marks]
5. Replicate
a. Create a fully functional DO file of all the commands used in this exercise. Your
DO file should include group number, names of members, date, title, and
comments for each command so that it can be easily read by others. [3 marks]

You might also like