Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
(a) The 95% confidence interval for 1 is {5.82 1.96 2.21}, that is 10.152 1 1.4884.
(b) Calculate the t-statistic:
t act =
1 0 5.82
=
= 2.6335.
SE( 1) 2.21
1 (5.6) 0.22
=
= 0.10
SE( 1)
2.21
1 0 2.12
=
= 5.89,
SE ( 1) 0.36
(c) The 95% confidence interval for the gender gap 1 is {2.12 1.96 0.36}, that is,
1.41 1 2.83.
(d) The sample average wage of women is 0 = $12.52/hour. The sample average wage of men is
0 + 1 = $12.52 + $2.12 = $14.64/hour.
(e) The binary variable regression model relating wages to gender can be written as either
Wage = 0 + 1 Male + ui ,
or
Wage = 0 + 1Female + vi .
In the first regression equation, Male equals 1 for men and 0 for women; 0 is the population
mean of wages for women and 0 + 1 is the population mean of wages for men. In the second
regression equation, Female equals 1 for women and 0 for men; 0 is the population mean of
wages for men and 0 + 1 is the population mean of wages for women. We have the following
relationship for the coefficients in the two regression equations:
0 = 0 + 1 ,
0 + 1 = 0 .
Given the coefficient estimates 0 and 1 , we have
0 = 0 + 1 = 14.64,
1 = 0 0 = 1 = 2.12.
Due to the relationship among coefficient estimates, for each individual observation, the OLS
residual is the same under the two regression equations: u i = v i. Thus the sum of squared
residuals, SSR = i =1 u i2, is the same under the two regressions. This implies that both
n
2
SER = ( SSR
and R 2 = 1 SSR
are unchanged.
TSS
n 1 )
1
3.
The 99% confidence interval is 1.5 {3.94 2.58 0.31) or 4.71 lbs WeightGain 7.11 lbs.
4.
29
30
(a) The estimated gain from being in a small class is 13.9 points. This is equal to approximately 1/5
of the standard deviation in test scores, a moderate increase.
(b) The t-statistic is t act = 13.9
= 5.56, which has a p-value of 0.00. Thus the null hypothesis is
2.5
rejected at the 5% (and 1%) level.
(c) 13.9 2.58 2.5 = 13.9 6.45.
6.
(a) The question asks whether the variability in test scores in large classes is the same as the
variability in small classes. It is hard to say. On the one hand, teachers in small classes might able
so spend more time bringing all of the students along, reducing the poor performance of
particularly unprepared students. On the other hand, most of the variability in test scores might be
beyond the control of the teacher.
(b) The formula in 5.3 is valid for heteroskesdasticity or homoskedasticity; thus inferences are valid
in either case.
7.
3.2
= 2.13 with a p-value of 0.03; since the p-value is less than 0.05, the null
(a) The t-statistic is 1.5
hypothesis is rejected at the 5% level.
(b) 3.2 1.96 1.5 = 3.2 2.94
(c) Yes. If Y and X are independent, then 1 = 0; but this null hypothesis was rejected at the 5% level
in part (a).
(d) 1 would be rejected at the 5% level in 5% of the samples; 95% of the confidence intervals would
contain the value 1 = 0.
8.
(a) 43.2 2.05 10.2 or 43.2 20.91, where 2.05 is the 5% two-sided critical value from the t28
distribution.
(b) The t-statistic is t act = 61.57.4 55 = 0.88, which is less (in absolute value) than the critical value of
20.5. Thus, the null hypothesis is not rejected at the 5% level.
(c) The one sided 5% critical value is 1.70; tact is less than this critical value, so that the null
hypothesis is not rejected at the 5% level.
9.
(a) =
1 1
X n
(Y1 + Y2 +
K, X ) = E X1 1n (Y + Y + L + Y )|X , K, X )
11
=
(X + L + X ) =
Xn
n
10. Let n0 denote the number of observation with X = 0 and n1 denote the number of observations with
X = 1; note that
n
i =1
( X i X )2
Y = n1 Y1 +
n
n0
n
Y0
=
n
i =1
X i = n1 ; X = n1| n;
n
i =1
X i2 nX 2 = n1
1
n1
n12
n
n
i =1
X iYi = Y1 ;
= n1 1
n1
n
)=
n1n0
n
n
n
n
n
(Y1 Y ) = Y 1 Y1 0 Y0 = Y1 Y0
n0
n0
n
n
n
n n + n0
n
and 0 = Y 1 X = 0 Y0 + 1 Y1 (Y1 Y0 ) 1 = 1
Y0 = Y0
n
11. Using the results from 5.10, 0 = Ym and 1 = Yw Ym . From Chapter 3, SE(Ym ) =
SE(Yw Ym ) =
sm2
nm
Sm
nm
and
s2
+ nww . Plugging in the numbers 0 = 523.1 and SE ( 0 ) = 6.22; 1 = 38.0 and
SE( 1 ) = 7.65.
12. Equation (4.22) gives
2 =
0
var (H i ui )
( )
n E H
2
i
, where H i = 1
( )
E X i2
Xi .
Using the facts that E (ui | X i ) = 0 and var (ui | X i ) = u2 (homoskedasticity), we have
E (Hi ui ) = E u
=0
( )
2
i
E X
i i
X u = E (ui )
( )
E Xi2
E [ Xi E (ui |Xi )]
x
0 = 0,
E ( Xi2 )
and
E [(Hi ui ) ] = E u
2
x
E Xi2
2
i i
Xu
2
i
x
2
2 2
x
= E u 2 2 Xiui + 2 Xi ui
E Xi
E Xi
2 2
x
= E u 2 x E Xi E ui2|Xi +
E Xi E ui |Xi
2
2
E Xi
E Xi
2
i
x
= u2 2 x 2 x u2 +
E Xi u2
E Xi
E Xi2
2
= 1 x 2 u2 .
E Xi
31
32
x2
var (H i ui ) = E[( H i ui )2 ] = 1
E X i2
( )
u2 .
( )= E
E H
2
i
( )
E Xi2
2
i
= E 1 2
( )
E Xi2
x
Xi +
E Xi2
( )
Xi2
2
2
x
=1 2 x 2 +
E Xi2 = 1 x 2 .
E ( Xi ) E ( Xi2 )
E ( Xi )
( )
Thus
2 =
0
=
13. (a)
(b)
(c)
(d)
14. (a)
var (Hiui )
nE H 2 2
i
( )
E ( Xi2 ) u2
x2 2
1
E Xi2 u
u2
=
=
2
x2
x2
n 1
n 1
E Xi2
E Xi2
( )
( )
( )
E ( X )
=
.
2
i
2
u
n X2
n[E Xi2 x2 ]
Yes
Yes
They would be unchanged
(a) is unchanged; (b) is no longer true as the errors are not conditionally homosckesdastic.
X
From Exercise (4.11), = aiYi where ai = n i 2 . Since the weights depend only on Xi but
j=1 X j
not on Y , is a linear function of Y.
i
E( | X1,
(b)
K, X ) = +
n
Var ( |X1,
(c)
n
i=1
K, X ) =
Xi E(ui | X1,
in=1 X 2j
n
i=1
K, X ) = since E(u |X , K, X ) = 0
n
in=1 X 2j
K, X ) =
n
2
in=1 X 2j
w ,1
m ,1
w ,1
by [SE ( m,1 )] + [SE ( w,1 )] , and the result follows by noting the SE is the square root of the
estimated variance.
2