9.1 introduction - rice universityecon446/hgl/ch09.pdfk ttk ttk ek ttk ttkte ee ee ee ee e −−...
TRANSCRIPT
9.1 Introduction
9.2 Lags in the Error Term: Autocorrelation
9.3 Estimating an AR(1) Error Model
9.4 Testing for Autocorrelation
9.5 An Introduction to Forecasting: Autoregressive Models
9.6 Finite Distributed Lags
9.7 Autoregressive Distributed Lag Models
Figure 9.1
1 2( , , ,...)t t t ty f x x x− −=
1( , )t t ty f y x−=
1( ) ( )t t t t ty f x e e f e −= + =
Figure 9.2(a) Time Series of a Stationary Variable
Figure 9.2(b) Time Series of a Nonstationary Variable that is ‘Slow Turning’ or ‘Wandering’
Figure 9.2(c) Time Series of a Nonstationary Variable that ‘Trends’
9.2.1 Area Response Model for Sugar Cane
( ) ( )1 2ln lnA P= β +β
( ) ( )1 2ln lnt t tA P e= β +β +
1 2t t ty x e= β +β +
1t t te e v−= ρ +
1 2t t ty x e= β +β +
1t t te e v−= ρ +
2( ) 0 var( ) cov( , ) 0 fort t v t sE v v v v t s= = σ = ≠
1 1− < ρ <
( ) 0tE e =
22
2var( )1
vt ee σ= σ =
−ρ
( ) 2cov , 0kt t k ee e k− = σ ρ >
( )
2
2
cov( , ) cov( , )corr( , )var( )var( ) var
kkt t k t t k e
t t kt et t k
e e e ee eee e
− −−
−
σ ρ= = = = ρ
σ
1corr( , )t te e − = ρ
ˆ 3.893 .776 (se) (.061) (.277)
t ty x= +
Figure 9.3 Least Squares Residuals Plotted Against Time
1
2 2
1 1
( )( )cov( , )
var( )var( ) ( ) ( )
T
t tt t t
xy T Tt t t t
t t
x x y yx yrx y x x y y
=
= =
− −= =
− −
∑
∑ ∑
11 2
12
12
垐cov( , )
var( ) ˆ
T
t tt t t
T
t tt
e ee ere e
−− =
−=
= =∑
∑
The existence of AR(1) errors implies:
The least squares estimator is still a linear and unbiased estimator, but
it is no longer best. There is another estimator with a smaller
variance.
The standard errors usually computed for the least squares estimator
are incorrect. Confidence intervals and hypothesis tests that use these
standard errors may be misleading.
Sugar cane example
The two sets of standard errors, along with the estimated equation are:
The 95% confidence intervals for β2 are:
ˆ 3.893 .776(.061) (.277) 'incorrect' se's(.062) (.378) 'correct' se's
t ty x= +
(.211,1.340) (incorrect)
(.006,1.546) (correct)
1 2t t ty x e= β +β +
1t t te e v−= ρ +
1 2 1t t t ty x e v−= β +β +ρ +
1 1 1 2 1t t te y x− − −= −β −β
1 1 1 2 1t t te y x− − −ρ = ρ −ρβ −ρβ
1 2 1 2 1(1 )t t t t ty x y x v− −= β −ρ +β +ρ −ρβ +
1ln( ) 3.899 .888ln( ) .422 (se) (.092) (.259) (.166)
t t t t tA P e e v−= + = +
It can be shown that nonlinear least squares estimation of (9.24) is
equivalent to using an iterative generalized least squares estimator
called the Cochrane-Orcutt procedure. Details are provided in
Appendix 9A.
1 2 2 1 1(1 )t t t t ty x x y v− −= β −ρ +β −ρβ +ρ +
0 1 1 1 1t t t t ty x x y v− −= δ + δ + δ + θ +
1 0 2 1 2 1(1 )δ = β −ρ δ = β δ = −ρβ θ = ρ
1 1ˆ 2.366 .777 .611 .404
(se) (.656) (.280) (.297) (.167)t t t ty x x y− −= + − +
9.4.1 Residual Correlogram
0 1: 0 : 0H Hρ = ρ ≠
1 (0,1)z T r N=
34 .404 2.36 1.96z = × = ≥
9.4.1 Residual Correlogram
1 11.96 1.96 or r r
T T≥ ≤ −
1.96 1.96 or k kr rT T
≥ ≤ −
2cov( , ) ( )
var( ) ( )t t k t t k
kt t
e e E e ee E e
− −ρ = =
Figure 9.4 Correlogram for Least Squares Residuals fromSugar Cane Example
1 2t t ty x e= β +β +
1 2 1 2 1(1 )t t t t ty x y x v− −= β −ρ +β +ρ −ρβ +
Figure 9.5 Correlogram for Nonlinear Least Squares Residualsfrom Sugar Cane Example
1 2 1t t t ty x e v−= β +β +ρ +
= 2.439 = 5.949 -value = .021t F p
1 2 1垐t t t ty x e v−= β +β +ρ +
1 2 1 2 1垐 ?t t t t tb b x e x e v−+ + = β +β +ρ +
1 1 2 2 1
1 2 1
垐 ?( ) ( )
垐
t t t t
t t t
e b b x e v
x e v
−
−
= β − + β − +ρ +
= γ + γ +ρ +
2 34 .16101 5.474LM T R= × = × =
1 1 2 2t t t p t p ty y y y v− − −= δ + θ + θ + + θ +L
( ) 11
1
ln( ) ln( ) 100 100t tt t t
t
CPI CPIy CPI CPICPI
−−
−
⎛ ⎞−= − × ≈ ×⎜ ⎟
⎝ ⎠
1 2 3.1883 .3733 .2179 .1013 (se) (.0253) (.0615) (.0645) (.0613)
t t t tINFLN INFLN INFLN INFLN− − −= + − +
Figure 9.6 Correlogram for Least Squares Residuals fromAR(3) Model for Inflation
1 1 2 2 3 3t t t t ty y y y v− − −= δ + θ + θ + θ +
1 1 2 1 3 2 1T T T T Ty y y y v+ − − += δ + θ + θ + θ +
1 1 2 1 3 2垐 垐ˆ.1883 .3733 .4468 .2179 .5988 .1013 .3510.2602
T T T Ty y y y+ − −= δ + θ + θ + θ
= + × − × + ×=
2 1 1 2 3 1垐 垐垐
.1883 .3733 .2602 .2179 .4468 .1013 .5988
.2487
T T T Ty y y y+ + −= δ + θ + θ + θ= + × − × + ×=
1 1 1 1 1 2 2 1 3 3 2 1垐 垐ˆ ( ) ( ) ( ) ( )T T T T T Tu y y y y y v+ + − − += − = δ − δ + θ −θ + θ −θ + θ −θ +
1 1Tu v +=
2 1 1 1 2 1 1 2 1 1 2ˆ( )T T T T T Tu y y v u v v v+ + + + + += θ − + = θ + = θ +
23 1 2 2 1 3 1 2 1 1 2 3( )T T T Tu u u v v v v+ + + += θ + θ + = θ + θ + θ +
2 21 1
2 2 22 2 1
2 2 2 2 23 3 1 2 1
var( )
var( ) (1 )
var( ) [( ) 1]
v
v
v
u
u
u
σ = = σ
σ = = σ + θ
σ = = σ θ + θ + θ +
( )垐 垐1.96 , 1.96T j j T j jy y+ +− ×σ + ×σ
0 1 1 2 2 , 1, ,t t t t q t q ty x x x x v t q T− − −= α +β +β +β + +β + = +L K
( )ts
t s
E yx −
∂= β
∂
( ) 11
1
ln( ) ln( ) 100 100t tt t t
t
WAGE WAGEx WAGE WAGEWAGE
−−
−
⎛ ⎞−= − × ≈ ×⎜ ⎟
⎝ ⎠
0 1 1 1 1t t t q t q t p t p ty x x x y y v− − − −= δ + δ + δ + + δ + θ + + θ +L L
0 1 1 2 2 3 3
0
t t t t t t
s t s ts
y x x x x e
x e
− − −
∞
−=
= α +β +β +β +β + +
= α + β +∑
L
Figure 9.7 Correlogram for Least Squares Residuals fromFinite Distributed Lag Model
1 2
3 1 2
.0989 .1149 .0377 .0593 (se) (.0288) (.0761) (.0812) (.0812)
.2361 .3536 .1976(.0829) (.0604) (.0604)
t t t t
t t t
INFLN PCWAGE PCWAGE PCWAGE
PCWAGE INFLN INFLN
− −
− − −
= + + +
+ + −
Figure 9.8 Correlogram for Least Squares Residuals from Autoregressive Distributed Lag Model
0 1 1 2 2 3 3 1 1 2 2t t t t t t t ty x x x x y y v− − − − −= δ + δ + δ + δ + δ + θ + θ +
0 0
1 1 0 1
2 1 1 2 0 2
3 1 2 2 1 3
4 1 3 2 2
垐 .1149
垐 垐 .3536 .1149 .0377 .0784
垐 垐 垐 .0643
垐 垐 垐 .2434
垐 垐 ? .0734
β = δ =
β = θ β + δ = × + =
β = θ β + θ β + δ =
β = θ β + θ β + δ =
β = θ β + θ β =
Figure 9.9 Distributed Lag Weights for Autoregressive Distributed Lag Model
Slide 9-44Principles of Econometrics, 3rd Edition
Slide 9-45Principles of Econometrics, 3rd Edition
Slide 9-46Principles of Econometrics, 3rd Edition
(9A.2)
1 2 1 t t t t t ty x e e e v−= β +β + = ρ +
(9A.1)1 2 1 1 2 1t t t t ty x y x v− −= β +β +ρ −ρβ −ρβ +
( ) ( )1 1 2 11t t t t ty y x x v− −−ρ = β −ρ +β −ρ +
1 2 1 1 1t t t t t t ty y y x x x x∗ ∗ ∗− −= −ρ = −ρ = −ρ
Slide 9-47Principles of Econometrics, 3rd Edition
(9A.4)
(9A.3)1 1 2 2t t t ty x x v∗ ∗ ∗= β + β +
1 2 1 1 2 1( )t t t t ty x y x v− −−β −β = ρ −β −β +
Slide 9-48Principles of Econometrics, 3rd Edition
(9A.5)
1 1 1 2 1y x e= β + β +
2 2 2 21 1 1 2 11 1 1 1y x e−ρ = −ρ β + −ρ β + −ρ
1 11 1 12 2 1y x x e∗ ∗ ∗ ∗= β + β +
(9A.6)
2 21 1 11
2 212 1 1 1
1 1
1 1
y y x
x x e e
∗ ∗
∗ ∗
= −ρ = −ρ
= −ρ = −ρ
Slide 9-49Principles of Econometrics, 3rd Edition
22 2 2
1 1 2var( ) (1 ) var( ) (1 )1
vve e∗ σ
= −ρ = −ρ = σ−ρ
Slide 9-50Principles of Econometrics, 3rd Edition
(9B.1)
0 1: 0 : 0H Hρ = ρ >
( )21
2
2
1
垐
ˆ
T
t tt
T
tt
e ed
e
−=
=
−=∑
∑
Slide 9-51Principles of Econometrics, 3rd Edition
(9B.2)
2 21 1
2 2 2
2
1
2 21 1
2 2 2
2 2 2
1 1 1
1
垐 垐2
ˆ
垐 垐
2垐 ?
1 1 2
T T T
t t t tt t t
T
tt
T T T
t t t tt t tT T T
t t tt t t
e e e ed
e
e e e e
e e e
r
− −= = =
=
− −= = =
= = =
+ −=
= + −
≈ + −
∑ ∑ ∑
∑
∑ ∑ ∑
∑ ∑ ∑
Slide 9-52Principles of Econometrics, 3rd Edition
(9B.3)( )12 1d r≈ −
cd d≤
Figure 9A.1:
Principles of Econometrics, 3rd Edition Slide 9-53
Figure 9A.2:
Principles of Econometrics, 3rd Edition Slide 9-54
The Durbin-Watson bounds test.
if the test is inconclusive.
Principles of Econometrics, 3rd Edition
0 1if , re
Slide 9-55
ject : 0 and accept : 0;Lcd d H H< ρ = ρ >
0if , do not reject : 0;Ucd d H> ρ =
,Lc Ucd d d< <
Slide 9-56Principles of Econometrics, 3rd Edition
0 1 1 2 2 3 30
t t t t t t s t s ts
y x x x x e x e∞
− − − −=
= α +β +β +β +β + + = α + β +∑L
0 1 1 1 1t t t q t q t p t p ty x x x y y v− − − −= δ + δ + δ + + δ + θ + + θ +L L
Slide 9-57Principles of Econometrics, 3rd Edition
(9C.2)
(9C.1)0 1 1t t t ty x y v−= δ + δ + θ +
1 0 1 1 2t t ty x y− − −= δ + δ + θ
0 1 1 0 1 0 1 1 2
21 0 1 0 1 1 2
( )t t t t t t
t t t
y x y x x y
x x y
− − −
− −
= δ + δ + θ = δ + δ + θ δ + δ + θ
= δ + θ δ + δ + θ δ + θ
Slide 9-58Principles of Econometrics, 3rd Edition
(9C.3)
21 0 1 0 1 1 0 2 1 3
2 2 31 1 0 1 0 1 1 0 2 1 3
( )t t t t t
t t t t
y x x x y
x x x y
− − −
− − −
= δ + θ δ + δ + θ δ + θ δ + δ + θ
= δ + θ δ + θ δ + δ + θ δ + θ δ + θ
21 1 1
2 10 1 0 1 1 0 2 1 0 1 ( 1)
2 11 1 1 0 1 1 ( 1)
0
(1 )
jt
j jt t t t j t j
jj s j
t s t js
y
x x x x y
x y
+− − − − +
+− − +
=
= δ + θ δ + θ δ + + θ δ
+ δ + θ δ + θ δ + + θ δ + θ
= δ + θ + θ + + θ + δ θ + θ∑
L
L
L
Slide 9-59Principles of Econometrics, 3rd Edition
(9C.4)0 10
st t s
sy x
∞
−=
= α + δ θ∑
21 1
1
(1 )1δ
α = δ + θ + θ + =−θ
L
0t s t s t
sy x e
∞
−=
= α + β +∑
Slide 9-60Principles of Econometrics, 3rd Edition
0 1s
sβ = δ θ
2 00 1 1
0 1
(1 )1s
s
∞
=
δβ = δ + θ + θ + =
−θ∑ L
Slide 9-61Principles of Econometrics, 3rd Edition
(9C.6)
(9C.5)0 1 1 2 2 3 3 1 1 2 2t t t t t t ty x x x x y y− − − − − tv= δ + δ + δ + δ + δ + θ + θ +
0 0
1 1 0 1
2 1 1 2 0 2
3 1 2 2 1 3
4 1 3 2 2
1 1 2 2 for 4s s s s− −
β = δ
β = θ β + δβ = θ β + θ β + δ
β = θ β + θ β + δβ = θ β + θ β
β = θ β + θ β ≥M
Slide 9-62Principles of Econometrics, 3rd Edition
(9D.2)
(9D.1)
1 21ˆ
3T T T
Ty y yy − −
++ +
=
1 21 1 2ˆ (1 ) (1 )T T T Ty y y y+ − −= α +α −α +α −α +L
2 31 2 3ˆ(1 ) (1 ) (1 ) (1 ) .....T T T Ty y y y− − −−α = α −α +α −α +α −α +
1垐 (1 )T T Ty y y+ = α + −α
Figure 9A.3: Exponential Smoothing Forecasts for two alternative values of α
Principles of Econometrics, 3rd Edition Slide 9-63