Econometrics: Exercises

Econometrics I

Yarine Fawaz

Exercises Econometrics: Set 1-Correction

Computer exercises:
1) Use the data in SLEEP75.RAW from Biddle and Hamermesh (1990) to study whether there is a tradeoff between the time spent sleeping per week and the time spent in paid work. We could use either variable as the dependent variable.
For concreteness, estimate the model sleep  0  1totwork  u , where sleep is minutes spent sleeping at night per week and totwrk is total minutes worked during the week.
(i)
Report your results in equation form along with the number of observations and R2. What does the intercept in this equation mean?
. reg sleep totwrk
Source

SS

df

MS

Model
Residual

14381717.2
124858119

1
704

Total

139239836

705

Number of obs
F( 1,
704)
Prob > F
R-squared
Adj R-squared
Root MSE

14381717.2
177355.282
197503.313

sleep

Coef.

totwrk
_cons

-.1507458
3586.377

(ii)

Std. Err.
.0167403
38.91243

t
-9.00
92.17

P>|t|
0.000
0.000

=
=
=
=
=
=

706
81.09
0.0000
0.1033
0.1020
421.14

[95% Conf. Interval]
-.1836126
3509.979

-.117879
3662.775

If totwrk increases by 2 hours, by how much is sleep estimated to fall? Do you find this to be a large effect?

1

(iii)

Let totwrk_hr be the total hours worked during the week. Without using the computer, what will be the coefficient of this variable in a regression of sleep on totwrk_hr? totwrk_hr=totwrk/60 We can re-write the model equation using this new variable: sleep  0  1 (totwork _ hr * 60)  u

sleep  0  601totwork _ hr  u sleep  0  1 ' totwork _ hr  u where 1 '  601 .
ˆ
ˆ
So  '  60  0.15 * 60  9 .
1

1

Increasing the number of total hours worked per week by one leads to a decrease of 9 minutes of sleep per week.
2) A more realistic version of this model is: sleep  0  1totwork  2educ  3age  u , where sleep and totwrk (total work) are measured in minutes