Professional Documents
Culture Documents
Econometrics
Econometrics
Econometrics
Econometrics
(2.4)
Econometrics
Chapter 02
f(y)
x1
E(y|x) = 0 + 1x
.
u4 {
y3
y2
.} u1
y1
(B.27)
x2
x3
x4
Econometrics
x
10
Econometrics
.} u3
u {.
Cont.
y
y4
E(u) = 0
E(xu) = 0
Econometrics
x1
Econometrics
x2
. E(y|x) = + x
11
12
Chapter 02
Cont.
y 0 1 x (2.16) or 0 y 1 x (2.17)
So the OLS estimated slope is
n 1 yi 0 1 xi 0 (2.14)
i 1
n
n 1 xi yi 0 1 xi 0 (2.15)
i 1
Econometrics
y1
Econometrics
u y
n
i 1
i 1
0 1 xi
(2.22)
y
n
.} 1
i 1
x1
16
.} 3
14
y 0 1 x
2 {
Econometrics
15
4 {
(2.19)
2
xi x
y4
More OLS
13
y3
y2
i 1
i 1
Econometrics
x x y
x2
Econometrics
x3
x4
0 1 xi 0,
xi yi 0 1 xi 0
i 1
x
17
Econometrics
18
Chapter 02
Cont.
x u
u
i 1
0 and thus,
1
n
u
i 1
Econometrics
Cont.
i 1
19
Econometrics
20
Goodness-of-Fit
y y SST (2.33)
y y SSE (2.34)
u SSR (2.35)
2
2
i
1
x y
x
(2.38).
R2
1
SST
SST
R2 indicates the fraction of the sample
variation in yi that is explained by the
model.
Econometrics
22
Unbiasedness of OLS
Unbiased estimator: An estimator whose expected
value (or mean of its sampling distribution) equals
the population value (regardless of the population
value).
where y* = ln y and x* = ln x.
0 ( 2.31)
y 0 1 x
Econometrics
1*
(2.30)
Algebraic Properties
Econometrics
Algebraic Properties
23
Econometrics
24
Chapter 02
Cont.
Unbiasedness of OLS
Cont.
(x x)
i
Unbiasedness of OLS
xi x yi
(x x)
then E 1 1
x x u
(x x)
i
i
2
(2.49), (2.52)
x x E (u
(x x)
i
| x ) 1
(2.53)
25
Unbiasedness Summary
Cont.
26
Econometrics
5. Var(u|x) = 2 (Homoskedasticity)
27
Econometrics
28
Homoskedastic Case
Variance of OLSE
f(y|x)
. E(y|x) = + x
x1
29
x2
Econometrics
30
Chapter 02
Heteroskedastic Case
Cont.
Variance of OLSE
f(y|x)
Var ( 1 )
.
x1
x2
x3
E(y|x) = 0 + 1x
Econometrics
33
Estimate
32
Estimate
ui yi 0 1 xi
0 1 xi ui 0 1 xi
u x
i
(2.61)
Econometrics
34
(
x
i x )2
2
Econometrics
Econometrics
( 2 . 57 )
x )2
se 1
(x
31
Econometrics
36