BOSTON COLLEGE
Department of Economics
EC 228 Econometrics, Prof. Baum, Ms. Yu, Fall 2003
Problem Set 2
Due at classtime, 25 September 2003
Problem sets will not be accepted after their due dates.
Please make sure your name is legible on each page of your answers.
1. Do the following exercise with Stata (available in the SLSC). Hand in a
printout of your work (most easily done by turning on "log", and then
printing the log when you are finished). To access the data (over the
Internet), you will use the command
use http://fmwww.bc.edu/ec-p/data/wooldridge/ceosal2,clear
to read in the data set (as described on the course home page). The
description of variables may be accessed in Stata via the command
type http://fmwww.bc.edu/ec-p/data/wooldridge/CEOSAL2.des
or by viewing that web page in your browser. When it reads it successfully,
you will just get a dot prompt.
a. What is the average salary and average tenure of CEOs in this sample?
(hint: use the summarize command)
b. Test the hypothesis that the average CEO salary is a million dollars
(note that salary is measured in thousands of dollars; see the ttest command
(help ttest)
c. Test the hypothesis that CEOs that went to college make more money
(again, help ttest; you will use the "by" option). Does
the result surprise you? Why do you suppose this is so?
d. How many CEOs attended graduate school? Do they make more money than
those who did not?
e. Theory would suggest that executive pay should be related to
profitability of the firm. Using the variable profmarg, calculate the
correlation between profitability and salary. What do you find? How might
you explain your findings? (hint: help correlate)
- 2. Problem 2.1
- 3. Problem 2.2
- 4. Problem 2.3
- 5. Problem 2.5
- 6. Problem 2.8, part i only
- 7. Problem 2.11
- 8. Problem 2.13
- 9. Problem 3.1 (no estimation required)
For some of these problems, you must use Stata, but will not make use of the
RAW files listed in the text, as all of these data are available in Stata format over
the Internet. Please consult the "Wooldridge datasets: descriptions and access commands"
link on the course home page. All you need to do is copy the "use http://fmwww..." line
from each dataset to be used into Stata's command window. The name of each dataset is
that given in the text, without the .RAW extension; e.g. CEOSAL2.RAW is referred to as
just CEOSAL2 (with no period nor extension). For example,
. use http://fmwww.bc.edu/ec-p/data/wooldridge/ceosal2
For each of the empirical problems, hand in a printout from Stata, annotated with your comments.
The "log" icon in the Stata toolbar may be used to create a file containing both your commands and Stata's
response. It may be easier to work with a text-format log; the command 'log using ps2.log' will create a
text log. Use the 'Viewer' within Stata to examine and print the log.
Stata commands you may need (use "help" within Stata for those commands):
- summarize (summ)
-
regress
-
predict yhat, xb
-
predict eps, r
-
list vars [in... or if...]
-
display (which can be used like a calculator; note that after a regression of yvar on xvar1 and xvar2, you can refer
to the estimated coefficient on xvar1 as _b[xvar1], etc.)