Enders4 - APPLIED ECONOMETRIC TIME SERIES

APPLIED ECONOMETRIC
TIME SERIES 4TH ED.

WALTER ENDERS
Chapter 4
WALTER ENDERS, UNIVERSITY OF ALABAMA
Copyright © 2015 John, Wiley & Sons, Inc. All rights reserved.
The Random Walk Model
yt = yt–1 + t (or yt t).
t
Hence yt  y0    i
i 1
Given the first t realizations of the {t} process, the conditional mean of yt+1 is
Etyt+1 = Et(yt + t+1) = yt
Similarly, the conditional mean of yt+s (for any s > 0) can be obtained from
s
Et yt  s  yt  Et   t i  yt
i 1
var(yt) = var(t + t–1 + ... + 1) = t2
var(yt–s) = var(t–s + t–s–1 + ... + 1) = (t – s2
Random Walk Plus Drift
yt = yt–1 + a0 + t
Given the initial condition y0, the general solution for yt is

t
y t  y 0  a0 t    i
i 1
ts
y t  s  y 0  a0 ( t  s )    i
i 1
Etyt+s = yt + a0s.
The autocorrelation coefficient
E[(yt – y0)(yt–s – y0)] = E[(t + t–1+...+ 1)(t–s+ t–s–1 +...+1)]
= E[(t–s)2+(t–s–1)2+...+(1)2]
= (t – s)2
 s  (t  s) / (t  s)t
= [(t – s)/t]0.5
Hence, in using sample data, the autocorrelation function for a

random walk process will show a slight tendency to decay.
Panel (a): Random Walk Panel (b): Random Walk Plus Drift
12 60
10 50
8 40
6 30
4 20
2 10
0 0
10 20 30 40 50 60 70 80 90 100 10 20 30 40 50 60 70 80 90 100
Panel (c): T rend Stationary Panel (d): Random Walk Plus Noise
60 14
12
50
10
40
8
30
6
20
4
10
2
0 0
10 20 30 40 50 60 70 80 90 100 10 20 30 40 50 60 70 80 90 100
Figure 4.2: Four Series With Trends
Figure 4.3: The Business Cycle?
200
150
100
50
0
0 10 20 30 40 50 60 70 80 90 100
60
40
20
-20
-40
-60
Table 4.1: Selected Autocorrelations From Nelson and Plosser
1 2 r(1) r(2) d(1) d(2)

Real GNP .95 .90 .34 .04 .87 .66
Nominal GNP .95 .89 .44 .08 .93 .79
Industrial Production .97 .94 .03 -.11 .84 .67
Unemployment .75 .47 .09 -.29 .75 .46
Rate
Worksheet 4.1
Consider the two random walk processes
yt = yt1 + yt zt = zt1 + zt

10 5.0
8
2.5
6
0.0
4
2
-2.5
0
-5.0
-2
-4 -7.5
20 40 60 80 100 20 40 60 80 100
Since both series are unit-root processes with uncorrelated error terms, the regression of
yt on zt is spurious. Given the realizations of {yt} and {zt}, it happens that yt tends to increase as
zt tends to decrease. The regression line shown in the scatter plot of yt on zt captures this
tendency. The correlation coefficient between yt and zt is 0.69 and a linear regression yields yt =
1.41  0.565zt. However, the residuals from the regression equation are nonstationary.
Scatter Plot of yt Against zt Regression Residuals

10 5
4
8
3
6
2
4
1
2 0
-1
0
-2
-2
-3
-4
-4
-7.5 -5.0 -2.5 0.0 2.5 5.0 10 20 30 40 50 60 70 80 90 100
Worksheet 4.2
Consider the two random walk plus drift processes
yt = 0.2 + yt1 + yt zt = 0.1 + zt1 + zt
25 2.5
0.0
20
-2.5
15
-5.0
10
-7.5
5
-10.0
0
-12.5
-5 -15.0
10 20 30 40 50 60 70 80 90 100 10 20 30 40 50 60 70 80 90 100
Here {yt} and {zt} series are unit-root processes with uncorrelated error terms so that the regression is
spurious. Although it is the deterministic drift terms that cause the sustained increase in yt and the overall
decline in zt, it appears that the two series are inversely related to each other. The residuals from the
regression yt = 6.38  0.10zt are nonstationary.
Scatter Plot of yt Against zt Regression Residuals

25 7.5
20 5.0
15 2.5
10 0.0
5 -2.5
0
-5.0
-5
-7.5
-15.0 -12.5 -10.0 -7.5 -5.0 -2.5 0.0 2.5 10 20 30 40 50 60 70 80 90 100
Panel (a): Detrended RGDP
1.00
0.75
0.50
0.25
0.00
-0.25
-0.50
0 1 2 3 4 5 6 7 8 9 10 11 12
Panel (b): Logarithm ic Change in RGDP

1.00
0.50
0.00
-0.50
0 1 2 3 4 5 6 7 8 9 10 11 12
Autocorrelations PACF
Figure 4.4 ACF and PACF
3. UNIT ROOTS AND REGRESSION RESIDUALS
• yt = a0 + a1zt + et
• Assumptions of the classical model:
– both the {yt} and {zt} sequences be stationary
– the errors have a zero mean and a finite variance.
– In the presence of nonstationary variables, there might be
what Granger and Newbold (1974) call a spurious
regression
• A spurious regression has a high R2 and t-statistics that
appear to be significant, but the results are without any
economic meaning.
• The regression output “looks good” because the least-
squares estimates are not consistent and the customary
tests of statistical inference do not hold.
Four cases
• CASE 1: Both {yt} and {zt} are stationary.
– the classical regression model is appropriate.
• CASE 2: The {yt} and {zt} sequences are integrated of different orders.
– Regression equations using such variables are meaningless
• CASE 3: The nonstationary {yt} and {zt} sequences are integrated of
the same order and the residual sequence contains a stochastic trend.
– This is the case in which the regression is spurious.
– In this case, it is often recommended that the regression equation be estimated in
first differences.
• CASE 4: The nonstationary {yt} and {zt} sequences are integrated of
the same order and the residual sequence is stationary.
– In this circumstance, {yt} and {zt} are cointegrated.
The Dickey-Fuller tests
p
Δyt   yt 1    i yt i 1   t
i 2
p
Δyt  a0   yt 1    i yt i 1   t
i2
p
Δyt  a0   yt 1  a2 t    i yt i 1   t
i2
The 1, 2, and 3 statistics are constructed in exactly the same way
as ordinary F-tests:
i 
 SSR ( restricted )  SSR (unrestricted ) / r
SSR (unrestricted ) /(T  k )
Figure 4.6: The Dickey-Fuller Distribution
0.09
0.08
0.07
0.06
0.05
percentile
0.04
0.03
0.02
0.01
0
-5 -4 -3 -2 -1 0 1 2 3
t-statistic
Table 4.2: Summary of the Dickey-Fuller
Tests
Model Hypothesis Test Critical values for
Statistic 95% and 99%
Confidence Intervals
yt = a0 + yt-1 + a2t + t =0  -3.45 and -4.04
 = a2 = 0 3 6.49 and 8.73
a0 =  = a2 = 0 2 4.88 and 6.50
yt = a0 + yt-1 + t =0  -2.89 and -3.51
a0 =  = 0 1 4.71 and 6.70
yt = yt-1 + t =0  -1.95 and -2.60
Table 4.3: Nelson and Plosser's Tests For
Unit Roots
p a0 a2  +1
Real GNP 2 0.819 0.006 -0.175 0.825

(3.03) (3.03) (-2.99)
Nominal GNP 2 1.06 0.006 -0.101 0.899

(2.37) (2.34) (-2.32)
Industrial Production 6 0.103 0.007 -0.165 0.835

(4.32) (2.44) (-2.53)
Unemployment Rate 4 0.513 -0.000 -0.294* 0.706

(2.81) (-0.23) (-3.55)
p is the chosen lag length. Entries in parentheses represent the t-test for
the null hypothesis that a coefficient is equal to zero. Under the null of
nonstationarity, it is necessary to use the Dickey-Fuller critical values. At the
.05 significance level, the critical value for the t-statistic is -3.45.
Quarterly Real U.S. GDP
lrgdpt = 0.1248 + 0.0001t  0.0156lrgdpt–1 + 0.3663lrgdpt–1
(1.58) (1.31) (1.49) (6.26)
The t-statistic on the coefficient for lrgdpt–1 is 1.49. Table A

indicates that, with 244 usable observations, the 10% and 5% critical
value of  are about 3.13 and 3.43, respectively. As such, we cannot
reject the null hypothesis of a unit root.
The sample value of 3 for the null hypothesis a2 =  = 0 is 2.97. As

Table B indicates that the 10% critical value is 5.39, we cannot reject
the joint hypothesis of a unit root and no deterministic time trend. The
sample value of 2 is 20.20. Since the sample value of 2 (equal to
17.61) far exceeds the 5% critical value of 4.75, we do not want to
exclude the drift term. We can conclude that the growth rate of the real
GDP series acts as a random walk plus drift plus the irregular term
0.3663lrgdpt–1.
Table 4.4: Real Exchange Rate Estimation
 H0:  = 0 Lags Mean / F SD/
DW SEE
1973-1986
Canada 0.022 t = 1.42 0 1.05 0.059 0.194 5.47
(0.016) 1.88 1.16
Japan 0.047 t = 0.64 2 1.01 0.007 0.226 10.44
(0.074) 2.01 2.81
Germany 0.027 t = 0.28 2 1.11 0.014 0.858 20.68
(0.076) 2.04 3.71
1960-1971
Canada 0.031 t = 1.59 0 1.02 0.107 0.434 .014
(0.019) 2.21 .004
Japan 0.030 t = 1.04 0 0.98 0.046 0.330 .017
(0.028) 1.98 .005
Germany 0.016 t = 1.23 0 1.01 0.038 0.097 .026
(0.012) 1.93 .004
EXTENSIONS OF THE DICKEY–FULLER TEST
yt = a0 + a1yt–1 + a2yt–2 + a3yt–3 + ... + ap–2yt–p+2 + ap–1yt–p+1 + apyt–p + t
add and subtract apyt–p+1 to obtain
yt = a0 + a1yt–1 + a2yt–2 + ...+ ap–2yt–p+2 + (ap–1 + ap)yt–p+1 – apyt–p+1 + t
Next, add and subtract (ap–1 + ap)yt–p+2 to obtain:
yt = a0 + a1yt–1 + a2yt–2 + a3yt–3 + ... – (ap–1 + ap)yt–p+2 – apyt–p+1 + t
Continuing in this fashion, we obtain

p
 y t = a0   yt 1   i yt  i 1   t
i= 2
 p
 p
   1   ai  and  i    a j
 i 1  ji
Rule 1:
• Consider a regression equation containing a mixture of I(1)

and I(0) variables such that the residuals are white noise. If
the model is such that the coefficient of interest can be
written as a coefficient on zero-mean stationary variables,
then asymptotically, the OLS estimator converges to a
normal distribution. As such, a t-test is appropriate.
• Rule 1 indicates that you can conduct lag length tests using t-
tests and/or F-tests on
yt = yt–1 + 2yt–1 + 3yt–2 + … + pyt–p+1 + t
Selection of the Lag Length
• general-to-specific methodology
– Start using a lag length of p*. If the t-statistic on lag p*
is insignificant at some specified critical value, re-
estimate the regression using a lag length of p*–1.
Repeat the process until the last lag is significantly
different from zero.
– Once a tentative lag length has been determined,
diagnostic checking should be conducted.
• Model Selection Criteria (AIC ,SBC)
• Residual-based LM tests
The Test with MA Components
• A(L)yt = C(L)t so that A(L)/C(L)yt = t

• So that D(L)yt = t
– Even though D(L) will generally be an infinite-
order polynomialwe can use the same technique
as used above to form the infinite-order
autoregressive model
– However, unit root tests generally work poorly
if the error process has a strongly negative MA
component.
Example of a Negative MA term
yt = yt-1 + εt – β1εt-1; 0 < β1 < 1.
The ACF is:
γ0 = E[(yt – y0)2] = σ2 + (1 – β1)2E[(εt-1)2 + (εt-2)2 + … + (ε1)2]
= [1 + (1 – β1)2(t – 1)]σ2
γs = E[(yt – y0)(yt-s – y0)]
= E[(εt +(1–β1)εt-1 + … + (1–β1)ε1)(εt-s + (1–β1)εt-s-1 + … + (1–β1)ε1)
= (1 – β1) [1 + (1 – β1) (t – s – 1)] σ2
The ρi approach unity as the sample size t becomes infinitely large.

For the sample sizes usually found in applied work, the autocorrelations
can be small.
Let β1 be close to unity so that terms containing (1 – β1)2 can be safely
ignored. The ACF can be approximated by ρ1 = ρ2 = … = (1 – β1)0.5.
For example, if β1 = 0.95, all of the autocorrelations should be 0.22.
Multiple Roots
• Consider
2yt = a0 + 1yt–1 + t
If 1 does differ from zero, estimate

2yt = a0 + 1yt–1 + 2yt–1 + t
If you reject the null hypothesis, 2 = 0,conclude that {yt} is
stationary.
Panel (a) yt = 0.5yt−1 + t + DL
10.0
7.5
5.0
2.5
0.0
-2.5
10 20 30 40 50 60 70 80 90 100
Panel (b) yt = yt−1 + t + DP

10.0
7.5
5.0
2.5
0.0
-2.5
-5.0
10 20 30 40 50 60 70 80 90 100
Perron’s Test
• Let the null be yt = a0 + yt–1 + 1DP + 2DL + t
– where DP and DL are the pulse and level dummies
• Estimate the regression (the alternative):
yt = a0 + a2t +m1DP + m2DL + m3DT + t
– Let DT be a trend shift dummy such that DT = t –  for t >  and zero
otherwise.
• Now consider a regression of the residuals
yˆ t  a 1 yˆ t  1   1 t
If the errors do not appear to be white noise, estimate the equation in the
form of an augmented Dickey–Fuller test.
The t-statistic for the null hypothesis a1 = 1 can be compared to the critical
values calculated by Perron (1989). For  = 0.5, Perron reports the
critical value of the t-statistic at the 5 percent significance level to be
–3.96 for H2 and –4.24 for H3.
Table 4.6: Retesting Nelson and Plosser's Data For
Structural Change
T  k a0 1 2 a2 a1
Real GNP 62 0.33 8 3.44 ‐0.189 ‐0.018 0.027 0.282

(5.07) (‐4.28) (‐0.30) (5.05) (‐5.03)
Nominal 62 0.33 8 5.69 ‐3.60 0.100 0.036 0.471

GNP (5.44) (‐4.77) (1.09) (5.44) (‐5.42)
Industrial 111 0.66 8 0.120 ‐0.298 ‐0.095 0.032 0.322

Prod. (4.37) (‐4.56) (‐.095) (5.42) (‐5.47)
The appropriate t-statistics are in parenthesis. For a0, 1, 2, and a2, the
null is that the coefficient is equal to zero. For a1, the null hypothesis is a1
= 1. Note that all estimated values of a1 are significantly different from unity
at the 1% level.
Power
• Formally, the power of a test is equal to the probability of

rejecting a false null hypothesis (i.e., one minus the
probability of a type II error). The power for tau‐mu is
a1 10% 5% 1%
0.80 95.9 87.4 51.4
0.90 52.1 33.1 9.0
0.95 23.4 12.7 2.6
0.99 10.5 5.8 1.3
Nonlinear Unit Root Tests
• Enders-Granger Test
yt = It1(yt–1 – ) + (1 – It)2(yt–1 – ) + t
 1 if yt 1  
It  
 0 if yt 1  
• LSTAR and ESTAR Tests

• Nonlinear Breaks—Endogenous Breaks
Schmidt and Phillips (1992) LM Test
• The overly-wide confidence intervals for  means that you are less
likely to reject the null hypothesis of a unit root even when the true
value of  is not zero. A number of authors have devised clever
methods to improve the estimates of the intercept and trend
coefficients.
t
y t  a0  a 2 t    t
i 1
yt = a2 + t
• The idea is to estimate the trend coefficient, a2, using the regression
yt = a2 + t. As such, the presence of the stochastic trend i does not
interfere with the estimation of a2.
LM Test Continued
• Use this estimate to form the detrended series as
ytd  yt ( y1 aˆ2) aˆ2t
• Then use the detrended series to estimate
p
y t  a 0   y d
t 1   ci ytdi   t
i 1
• Schmidt and Phillips (1992) show that it is preferable to estimate

the parameters of the trend using a model without the persistent
variable yt-1.
• Elliott, Rothenberg and Stock (1996) show that it is possible to
further enhance the power of the test by estimating the model
using something close to first-differences.
The Elliott, Rothenberg, and Stock Test
Instead of creating the first difference of yt, Elliott, Rothenberg and
Stock (ERS) preselect a constant close to unity, say , and subtract
yt1 from yt to obtain:
yt = a0 + a2t  a0  a2(t  1) + et, for t = 2, …,
= (1  )a0 + a2[(1)t + )] + et.
= a0z1t + a2z2t + et
z1t = (1  ) ; z2t =  + (1)t.
The important point is that the estimates a0 and a2 can be used to detrend
the {yt} series
p
y   y
d
t
d
t 1   ci ytdi   t
i 1
Panel Unit Root Tests
pi
• 
yit = ai0 + iyit–1 + ai2t +
 y
j1
ij it  j + it
• One way to obtain a more powerful test is to pool the estimates from a
number separate series and then test the pooled value. The theory
underlying the test is very simple: if you have n independent and
unbiased estimates of a parameter, the mean of the estimates is also
unbiased. More importantly, so long as the estimates are independent,
the central limit theory suggests that the sample mean will be normally
distributed around the true mean.
– The difficult issue is to correct for cross equation correlation
• Because the lag lengths can differ across equations, you should perform
separate lag length tests for each equation. Moreover, you may choose
to exclude the deterministic time trend. However, if the trend is
included in one equation, it should be included in all
Table 4.8: The Panel Unit Root Tests for Real Exchange Rates
Lags Estimated i t‐statistic Estimated i t‐statistic
Log of the Real Rate Minus the Common Time Effect

Australia 5 ‐0.049 ‐1.678 ‐0.043 ‐1.434
Canada 7 ‐0.036 ‐1.896 ‐0.035 ‐1.820
France 1 ‐0.079 ‐2.999 ‐0.102 ‐3.433
Germany 1 ‐0.068 ‐2.669 ‐0.067 ‐2.669
Japan 3 ‐0.054 ‐2.277 ‐0.048 ‐2.137
Netherlands 1 ‐0.110 ‐3.473 ‐0.137 ‐3.953
U.K. 1 ‐0.081 ‐2.759 ‐0.069 ‐2.504
U.S. 1 ‐0.037 ‐1.764 ‐0.045 ‐2.008
Limitations
• The null hypothesis for the IPS test is i = 2 = … = n = 0. Rejection of the null
hypothesis means that at least one of the i’s differs from zero.
• At this point, there is substantial disagreement about the asymptotic theory
underlying the test. Sample size can approach infinity by increasing n for a given T,
increasing T for a given n, or by simultaneously increasing n and T.
– For small T and large n, the critical values are dependent on the magnitudes of
the various ij.
• The test requires that that the error terms be serially uncorrelated and
contemporaneously uncorrelated.
– You can determine the values of pi to ensure that the autocorrelations of {it}
are zero. Nevertheless, the errors may be contemporaneously correlated in that
Eitjt  0
– The example above illustrates a common technique to correct for correlation
across equations. As in the example, you can subtract a common time effect
from each observation. However, there is no assurance that this correction will
completely eliminate the correlation. Moreover, it is quite possible that is
nonstationary. Subtracting a nonstationary component from each sequence is
clearly at odds with the notion that the variables are stationary.
The Beveridge-Nelson Decomposition
• The trend is defined to be the conditional expectation of the

limiting value of the forecast function. In lay terms, the
trend is the “long-term” forecast. This forecast will differ at
each period t as additional realizations of {et} become
available. At any period t, the stationary component of the
series is the difference between yt and the trend t.
BN 2
• Estimate the {yt} series using the Box–Jenkins technique.

– After differencing the data, an appropriately identified
and estimated ARMA model will yield high-quality
estimates of the coefficients.
• Obtain the one-step-ahead forecast errors of Etyt+s for large
s. Repeating for each value of t yields the entire set of
premanent components
• The irregular component is yt minus the value of the trend.
The HP Filter
Let the trend of a nonstationary series be the {t} sequence so
that yt – t the stationary component
1 T  T 1
 ( yt   t) +  t+1 t
   
2
[(  )  ( t  t -1 ) ]
2
T t=1 T t= 2
For a given value of  the goal is to select the {t} sequence so as to

minimize this sum of squares. In the minimization problem  is an arbitrary
constant reflecting the “cost” or penalty of incorporating fluctuations into the
trend.
In applications with quarterly data, including Hodrick and Prescott (1984)  is

usually set equal to 1,600.
Large values of  acts to “smooth out” the trend.
Panel (a) The BN Cycle Pane l (b) The HP Cycle
0.03 0.04
0.03
0.02
0.02
0.01
0.01
0.00 0.00
-0.01 -0.01
-0.02
-0.02
-0.03
-0.03
-0.04
-0.04 -0.05
1960 1970 1980 1990 2000 2010 1960 1970 1980 1990 2000 2010
Figure 4.11: Two Decompositions of GDP
14
RGDP
12
10
trllions of 2005 dollars
Consumption
6
Investment
2
0
1950 1960 1970 1980 1990 2000 2010
Figure 4.12: Real GDP, Consumption and Investment

Enders4 - APPLIED ECONOMETRIC TIME SERIES

Uploaded by

Copyright:

Available Formats

Enders4 - APPLIED ECONOMETRIC TIME SERIES

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Enders4 - APPLIED ECONOMETRIC TIME SERIES

Uploaded by

Copyright:

Available Formats

APPLIED ECONOMETRIC

TIME SERIES 4TH ED.

WALTER ENDERS, UNIVERSITY OF ALABAMA

Etyt+1 = Et(yt + t+1) = yt

var(yt) = var(t + t–1 + ... + 1) = t2

var(yt–s) = var(t–s + t–s–1 + ... + 1) = (t – s2

Given the initial condition y0, the general solution for yt is

Hence, in using sample data, the autocorrelation function for a

Figure 4.2: Four Series With Trends

1 2 r(1) r(2) d(1) d(2)

yt = yt1 + yt zt = zt1 + zt

Scatter Plot of yt Against zt Regression Residuals

Scatter Plot of yt Against zt Regression Residuals

Panel (b): Logarithm ic Change in RGDP

Figure 4.4 ACF and PACF

Real GNP 2 0.819 0.006 -0.175 0.825

Nominal GNP 2 1.06 0.006 -0.101 0.899

Industrial Production 6 0.103 0.007 -0.165 0.835

Unemployment Rate 4 0.513 -0.000 -0.294* 0.706

The t-statistic on the coefficient for lrgdpt–1 is 1.49. Table A

The sample value of 3 for the null hypothesis a2 =  = 0 is 2.97. As

add and subtract apyt–p+1 to obtain

yt = a0 + a1yt–1 + a2yt–2 + ...+ ap–2yt–p+2 + (ap–1 + ap)yt–p+1 – apyt–p+1 + t

Next, add and subtract (ap–1 + ap)yt–p+2 to obtain:

yt = a0 + a1yt–1 + a2yt–2 + a3yt–3 + ... – (ap–1 + ap)yt–p+2 – apyt–p+1 + t

Continuing in this fashion, we obtain

• Consider a regression equation containing a mixture of I(1)

yt = yt–1 + 2yt–1 + 3yt–2 + … + pyt–p+1 + t

• A(L)yt = C(L)t so that A(L)/C(L)yt = t

The ρi approach unity as the sample size t becomes infinitely large.

If 1 does differ from zero, estimate

Panel (b) yt = yt−1 + t + DP

Real GNP 62 0.33 8 3.44 ‐0.189 ‐0.018 0.027 0.282

Nominal 62 0.33 8 5.69 ‐3.60 0.100 0.036 0.471

Industrial 111 0.66 8 0.120 ‐0.298 ‐0.095 0.032 0.322

• Formally, the power of a test is equal to the probability of

yt = It1(yt–1 – ) + (1 – It)2(yt–1 – ) + t

• LSTAR and ESTAR Tests

• Schmidt and Phillips (1992) show that it is preferable to estimate

yt = a0 + a2t  a0  a2(t  1) + et, for t = 2, …,

= (1  )a0 + a2[(1)t + )] + et.

z1t = (1  ) ; z2t =  + (1)t.

Lags Estimated i t‐statistic Estimated i t‐statistic

Log of the Real Rate Minus the Common Time Effect

• The trend is defined to be the conditional expectation of the

• Estimate the {yt} series using the Box–Jenkins technique.

For a given value of  the goal is to select the {t} sequence so as to

In applications with quarterly data, including Hodrick and Prescott (1984)  is

Large values of  acts to “smooth out” the trend.

Figure 4.11: Two Decompositions of GDP

You might also like