This preview shows pages 1–3. Sign up to view the full content.
1
University of California, Davis
Managerial Economic(ARE) 106, Summer 2009
Instructor: John H. Constantine
Problem Set #6:
NOT DUE
NOTE:
You do NOT NEED TO RUN SHAZAM on this hw.
All SHAZAM computer outputs are
given at the end of this assignment if the problem has one.
The SHAZAM command files are given to
help you understand how to write the code.
You may be asked to state SHAZAM commands on the
final exam.
Problem 1
:
This is problem 9.2 of the text, although it is modified a bit
.
sample 1 229
read(are106/fullmoon.dat) calls t hol fri sat full new
ols calls t hol fri sat full new
test
test full=0
test new=0
end
stop
Do full moons cause strange behavior?
This is an important policy issue in terms of staffing hospitals
(doctors and nurses) and police.
Daily data were collected for the period January 1, 1998 until mid
August.
There were 229 observations.
The variables are defined as follows:
calls
= emergency room cases
t
= trend variable 1, 2, …, 229
hol
= 1 if a holiday, 0 if not (New Year’s Day, Memorial Day, and Easter)
fri
= 1 if the day is a Friday, 0 if not
sat
= 1 if the day is a Saturday, 0 if not
full
= 1 if there is a full moon, 0 if not
new
= 1 if there is a new moon, 0 if not
(a)
Run the OLS using SHAZAM.
Interpret your results.
You are to state explicitly how each
variable will impact “calls”.
Note that most of these independent variables are “dummies”, and
the purpose here to have you understand dummies’ interpretations.
Part of this interpretation
requires a comment of the parameter statistical significance.
(b)
When should emergency rooms expect more calls?
(c)
Test the joint significance of “full” and “new”.
State the null and alternative hypotheses, and use
both the Ftest and pstat to test.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document2
Problem 2
:
This is problem 9.3 of the text, although it is modified a bit
.
SAMPLE 1 4682
READ(are106/stockton.dat) PRICE SQFT AGE D92D96
OLS PRICE SQFT AGE D92 D93 D94 D95 D96
TEST
TEST D92 = 0
TEST D93 = 0
TEST D94 = 0
TEST D95 = 0
TEST D96 = 0
END
STOP
This problem examines housing price trends in Stockton, CA.
The data are on houses sold between
January 1991 and December 1996.
The data are defined as follows:
PRICE
i
= overall price index number for house
i
.
SQFT
i
= square feet of house
i
.
AGE
i
= are of house
i
.
D92
i
= 1 if house
i
sold in 1992; 0 if not (
D93
i
– D96
i
defined similarly)
(a)
State the PRF implied by the SHAZAM command file.
(b)
What is the economic interpretation of
β
1
?
(c)
Discuss the estimated coefficients on
SQFT
i
and
AGE
i
.
Do the results confirm your
a priori
expectations?
(
Note: You need to get into the habit of stating each parameter’s statistical
significance.
)
(d)
Discuss the estimated coefficients on the dummy variables.
(
Note: You need to get into the habit
of stating each parameter’s statistical significance.
)
(e)
State the hypothesis test implied by the TEST command given in the command file.
What is your
conclusion?
(f)
This is the end of the preview. Sign up
to
access the rest of the document.
 Spring '09
 CONSTANTINE

Click to edit the document details