Professional Documents
Culture Documents
Consequencesof Hodrick Prescott Filtering
Consequencesof Hodrick Prescott Filtering
Consequencesof Hodrick Prescott Filtering
net/publication/24075766
CITATIONS READS
10 2,288
1 author:
SEE PROFILE
All content following this page was uploaded by David John Doorn on 21 May 2014.
Consequences of Hodrick–Prescott
filtering for parameter estimation
in a structural model of
inventory behaviour
D. Doorn
Department of Economics, University of Minnesota Duluth,
112 Library Drive, 165 SBE, Duluth, MN 55812, USA
E-mail: ddoorn@d.umn.edu
1
Sen (2004) investigates this possibility for updated versions of the series’ examined in Nelson and Plosser (1982) and Doorn
(2003) finds trend breaks in aggregate inventories and sales at the two-digit SIC industry level.
Applied Economics ISSN 0003–6846 print/ISSN 1466–4283 online ß 2006 Taylor & Francis 1863
http://www.tandf.co.uk/journals
DOI: 10.1080/00036840500427254
1864 D. Doorn
rely upon pre-determination of the time-series prop- different criteria for detrending the data prior to
erties of the data, it is capable of removing both linear estimation, including removing a linear trend and HP
and stochastic trends. The HP filter has been much filtering with different values for the smoothing
applied in the Real Business Cycle (RBC) literature as parameter, discussed below. For comparison, the
a method of isolating business cycle frequencies from model is also estimated without prior detrending of
the long-run trend component in both actual and the data but instead estimating deterministic compo-
simulated data. The goal in that literature has been to nents along with the other parameters of the model.
study the business cycle behaviour of different The paper proceeds as follows: First the Hodrick–
macroeconomic variables and to determine the Prescott filter is presented and some of the previous
degree of any comovements between them over results mentioned above discussed. Next a structural
the course of the cycle. This generally involves a model of inventory behaviour is derived with which
correlation study of the filtered data.2 Unfortunately to simulate data. The model is then calibrated to
for this work, studies of the impact HP filtering can actual data on inventories and sales of non-durable
have on the second moments of a data series have goods. Once this is done, simulated data is used to
shown it to have the potential to introduce spurious estimate the parameters of the model several times
correlations in the filtered data and spurious cross- using different methods for dealing with the trend.
correlations between series. This may cause the A comparison will be made of the distributional
stylized facts gained through the study of HP filtered characteristics across the different detrending meth-
data to be questionable at best. There have been a ods. In addition, the effect of detrending method on
number of papers showing this potential for the HP different test statistics resulting from the estimation
filter to distort results from RBC models and will be considered.
empirical studies, most notably Harvey and Jaeger
(1993), King and Rebelo (1993), and Cogley and
Nason (1995).
Another application of the HP filter has been as an II. The Hodrick–Prescott Filter
ad hoc method of detrending data series which are
subsequently used in estimation of parameters from This derivation of the Hodrick–Prescott filter closely
structural econometric models. Most estimation follows that of King and Rebelo (1993). The HP filter
methods require the data used to be covariance is based on the assumption that a time-series process
stationary in order for the underlying asymptotic can be modelled as the sum of a growth component
theory to hold. While seemingly useful as a tool for and a cyclical component, that is yt ¼ ygt þ yct . In the
detrending and achieving stationarity, the above- real business cycle literature it is desirable to remove
mentioned problems have the potential to affect the growth component, whether it be a stochastic or
estimation using HP filtered data as well. If the cross- deterministic trend, in order to study the behaviour of
correlations between variables are affected by the the cyclical component and to compare that behav-
filtering process, then estimation of a model posited iour between different series. The HP filter achieves
as governing the relationship between those variables this by defining the cyclical component as
will likely be affected as well, along with any
inferences based on the estimated parameters. It is yct ¼ yt ygt ð1Þ
the goal of this paper to assess whether there is a where yct becomes the desired detrended series. The
significant impact on parameter estimation when HP filter minimizes the variance of Equation 1 while
using HP filtered data as opposed to other methods penalizing for excessive changes in the growth
of detrending. component. This can be expressed in terms of the
To effect this study of the impact HP filtering may following minimization problem
have on estimation a simulation study is conducted
T n
X 2 2 o
based on a widely-studied model of inventory
min yt ygt þ ygtþ1 ygt Þ ðygt ygt1
behaviour. The simulated data generated by the g
fyt gTt¼1 t¼1
model contain simple linear trends. The simulated
ð2Þ
data is then used to estimate the population
parameters of the model using the Generalized where is termed the ‘smoothing parameter’, since its
Method of Moments (GMM) estimator of Hansen value determines the penalty applied to excessive
(1982). The model is estimated several times using changes in the growth rate of the series. The value
2
A recent example of such work in this journal is Sensier (2003), in which wide use of the HP filter was made in the study of
asymmetry in the business cycle behaviour of inventories in the UK.
Impact of Hodrick–Prescott filtering on parameter estimation 1865
chosen for will differ depending on the sampling 1.0
frequency of the data and represents the trade-off
between smoothness and goodness of fit in the 0.8
resulting series.3
0.6
Making use of lag operators, the first-order
condition from the minimization problem results in 0.4
yt ygt 2
¼ ð1 LÞ ð1 L1 Þ2 ygt 0.2
or 0.0
2
yt ¼ ½1 þ ð1 LÞ ð1 L Þ 1 2
ygt – 0.1 0.1 0.3 0.5 0.7 0.9 1.1
Frequency
By inversion this can be put in terms of a low
frequency filter applied to yt, which yields the growth Fig. 1. Frequency response of HP cyclical filter: ( )
lambda ^ 1600, ( ) lambda ^ 14 400, ( ) lambda ^
component ygt ¼ Hg ðLÞyt , where 86 400, ( ) lambda ¼ 129 600, ( ) Ideal-monthly, ( )
1 Ideal-Quarterly. This plot depicts the squared gain of the
Hg ðLÞ ¼ 1 þ ð1 LÞ2 ð1 L1 Þ2 ð3Þ filter HP(u) for j ^ 1600, j ^ 14 400, j ^ 86 400, and
j ^ 129 600. Also shown are the ideal highpass filters for
The cyclical component of the series is then given by monthly and quarterly data. See text for details
yct ¼ yt ygt ¼ ð1 Hg ðLÞÞyt ¼ Hc ðLÞyt , where
½1 L2 ½1 L1 2 L2 ð1 LÞ4
Hc ðLÞ ¼ ¼
1 þ ½1 L2 ½1 L1 2 1 þ L2 ð1 LÞ4
differencing the data with (1 L)4 and then applying
L2 ð1 LÞ4 the filter L2/(1/ þ L2)(1 L)4 to the result.
¼ ð4Þ
ð1=Þ þ L2 ð1 LÞ4 Figure 1 plots the frequency response of the filter
In the frequency domain, the squared gain, or for different values of , chosen to reflect values used
frequency response, of this filter is in the literature for quarterly data ( ¼ 1600) and
monthly data ( ¼ 14 400, 86 400, 129 600). Also
½1 ei! 2 ½1 ei! 2 2 depicted are the ideal filters for both monthly and
HPð!Þ ¼ quarterly data, which only pass frequencies above a
1 þ ½1 ei! 2 ½1 ei! 2
period of eight years, often chosen to be the cutoff
4½1 cosð!Þ2 2 period for business cycle research. On the vertical axis
¼ are the weights applied by the filter to different
1 þ 4½1 cosð!Þ2
2 frequencies in the data. Notice that very low
4½1 cosð!Þ2 frequencies are completely attenuated by the filter
¼ ð5Þ while high frequencies are passed without alteration.
ð1=Þ þ 4½1 cosð!Þ2
Also note that regardless of the value of , more low
where ! is frequency measured in radians. This frequency content is passed by the HP filter than may
representation allows the effect the filter has on cycles be ideal if the goal is to study behaviour of a series at
of different frequencies in the data to be seen. business cycle frequencies. In addition, some higher
Note that HP(0) ¼ 0, indicating attenuation of low frequency content is attenuated to the right of the
frequencies, and also that HP () ¼ (16/(1/ þ 16)), cutoff points of the ideal filters. This attenuation
which is approximately equal to one for large .4 This tends to decrease as is increased, although more
implies close to unit gain on high frequencies. In fact, undesirable low-frequency content is then left as well.
as goes to infinity, the filter passes all but the zero Regardless of the value of , the HP filter always
frequency, meaning it removes a deterministic linear removes a linear trend, but operates further on
trend only. In addition, the four differences in the deviations from this trend. Singleton (1988) shows
numerator of Equation 4 indicate it is capable of that when applied to stationary data, the HP filter is a
rendering stationary integrated processes of up to very good approximation to an ideal high pass filter,
fourth order.5 This would be the equivalent of which only allows cycles of greater frequency than
3
The smoothing parameter can be viewed as the ratio of the variance of the cyclical component to that of the change in the
growth component, although alternative interpretations are available. See, for example, Harvey and Jaeger (1993), Hodrick
and Prescott (1997), and Ravn and Uhlig (1997).
4
is typically set to 1600 for quarterly data and 14 400 for monthly. See Hodrick and Prescott (1997).
5
See King and Rebelo (1993).
1866 D. Doorn
some prespecified value to pass. This implies that if Under certain conditions, the HP filter can be
the data is linear trend stationary, the HP filter acts as shown to be the optimal linear filter, minimizing the
a high pass filter on the residuals from the mean square error between the actual cyclical
deterministic trend.6 This property makes the filter component and its estimate.8 However, these condi-
potentially useful in business cycle research by tions are fairly restrictive, with the strongest being
allowing the isolation of business cycle frequencies that the growth component and the cyclical compo-
from the data. However, if the goal of filtering is nent are uncorrelated. This would indicate that these
primarily to render data stationary prior to use in are generated by completely separate economic
estimation of econometric models, without regard to events. In addition, the particular trend specification
business cycle behaviour, applying such a high pass required for optimality causes the overall process to
filter may be removing more low-frequency content be I(2).For many economic time series this is unlikely
than is perhaps desirable. This may be especially to be the case. Finally, optimality requires a priori
harmful if most of the power of the series lies in the knowledge of the variances of the disturbance terms
low frequencies, as tends to be the case with many for the separate cyclical and growth components in
macroeconomic series. An example of this is given in order to set the smoothness parameter, , at its
Fig. 2, which plots the spectral density of monthly optimal value. Since the purpose of applying the filter
aggregate inventories of non-durable goods in the top to begin with is to isolate the trend and cyclical
panel, and then the same series detrended using the components, it is unlikely that these will be known
HP-filter with different values for . Also included is ahead of time.9 In practice is generally set based
the spectral density of the linearly detrended series. upon common practice and the sampling frequency of
The dashed line in the figure indicates a period of the data. These conditions make it unlikely that the
eight years, which is generally considered to be the HP filter is an optimal filter in most applications.
maximum length of the business cycle. The HP-filter However, even when optimal the filter tends to cause
is designed to attenuate any frequencies with period distortions in the auto-correlations of filtered series.
above eight years, which the figure indicates it does Ehlgen (1998) finds that the autocorrelations and the
fairly well. Again, this seems to be a good procedure variances of HP filtered data tend to be too small.
if the goal is to study the behaviour of a series at Further, he states that this can be a normal
business cycle frequencies and to compare that characteristic of optimal signal extraction filters and
behaviour across series. However, as a general
not just a problem with the HP filter.
detrending method it is clear that HP filtering Cogley and Nason (1995) look at the effects of HP
removes much of the information in the data
filtering on difference stationary data and the
contained in the lower frequencies. In addition,
implications of this for business cycle research.
even at frequencies above eight years, the filter
They posit that, if the series is difference stationary
removes more of the variability from the series than
then applying the HP filter will likely result in
does linearly detrending, which is due to the
problems akin to linearly detrending a random
frequency response of the filter as depicted in
walk, which has been studied by Nelson and Kang
Fig. 1. Note, however, that as is increased more
(1981).10 This implies that application of the HP filter
of the low frequency information is retained, which
to difference stationary data will likely cause pro-
makes sense since the filter becomes equivalent to
blems of filter induced cyclicality in the resulting
linear detrending as goes to infinity.
filtered series. Application of the HP filter to an I(1)
Application of the HP filter to a time series results
process is equivalent to applying the filter
in a trend that very closely follows the time path of
the data. While visually appealing, this may not L2 ð1 LÞ3
necessarily be desirable.7 Figure 3 indicates the SðLÞ ¼ ð6Þ
ð1=Þ þ L2 ð1 LÞ4
resulting differences in the residuals between remov-
ing a linear trend and applying the HP filter to the to the stationary differenced series. In this case, S(L)
aggregate inventory data. Clearly the HP filter results is not a high pass filter. In investigating its properties
in a very different detrended series. Cogley and Nason (1995) find that the filter S(L)
6
See Cogley and Nason (1995).
7
As an example, McCallum (2000) contains an application of the HP filter to US real GDP over the 1920s and 1930s. The
resulting detrended series gives little evidence of the Great Depression.
8
See Harvey and Jaeger (1993) and King and Rebelo (1993).
9
Harvey and Jaeger (1993) discuss estimating using maximum likelihood methods. Pedersen (1999) proposes other methods
to determine the optimal value of .
10
They found that such detrending caused cycles to appear in the detrended data that were not present in the original series.
Impact of Hodrick–Prescott filtering on parameter estimation 1867
35000000000.00
20000000000.00
5000000000.00
473 157.67 94.6 67.57 52.56 43 36.38 31.53 27.82 24.89 22.52 20.57 18.92 17.52 16.31 15.26 14.33 13.51 12.78 12.13
236.5 118.25 78.83 59.13 47.3 39.42 33.79 29.56 26.28 23.65 21.5 19.71 18.19 16.89 15.77 14.78 13.91 13.14 12.45
800000000
500000000
200000000
473 157.67 94.6 67.57 52.56 43 36.38 31.53 27.82 24.89 22.52 20.57 18.92 17.52 16.31 15.26 14.33 13.51 12.78 12.13
236.5 118.25 78.83 59.13 47.3 39.42 33.79 29.56 26.28 23.65 21.5 19.71 18.19 16.89 15.77 14.78 13.91 13.14 12.45
Fig. 2. Spectral density of total aggregate inventories of non-durables: ( ) LDT, ( ) HP1, ( ) HP2, ( ) HP3. The
top panel is the spectral density of the series in levels. The bottom panel shows the spectral densities of the detrended series from
the different methods, with LDT indicating linear detrending and HP indicating HP filtering with j ^ 14 400 for HP1, j ^ 86
400 for HP2, and j ^ 129 600 for HP3. The dashed line indicates the cutoff period of eight years, which is generally considered to
be the maximum length of the business cycle
will result in spurious cyclicality when applied to applied to an ARIMA(p, d, q) process. They found
stationary data. Furthermore, HP filtering of two that there is a non-zero probability of inducing
independent random walk processes was found to spurious cross-correlations between two independent
induce cross-correlations between the series that were series that have been HP filtered.
previously non-existent. Harvey and Jaeger (1993) The implication of these findings is that the cyclical
also show that the HP filter can induce spurious properties of HP filtered data cannot be relied upon
cycles that are non-existent in the original series when for inference about the business cycle behaviour of
1868 D. Doorn
function that accounts for production costs, costs of
4000 changing production, inventory holding costs, and
2000 backlog costs that arise when sales cannot be met out
of inventories.11 This particular model also includes
0
an unobservable cost shock, that may be observable
– 2000 to the firm but not the econometrician. The
optimization problem becomes
– 4000
– 6000 X
T
max lim Et bj ðptþj Stþj Ctþj Þ
ðHtþj Þ T!1
0.00 100.00 200.00 300.00 400.00 500.00 j¼0
Date
s.t.
Fig. 3. Residuals: ( ) Linear trend ( ) HP1. A
comparison of residuals from detrending monthly aggregate a0 a1 a2
inventories of non-turables with a linear trend as well as with Ctþj ¼ Q2tþj þ Q2tþj þ ðHtþj1 a3 Stþj Þ2
2 2 2
the HP filter using j ^ 14 400
þ Htþj utþj þ deterministic terms ð7Þ
11
See Sensier (2003) for a review and discussion of these properties of the inventory holding cost function.
Impact of Hodrick–Prescott filtering on parameter estimation 1869
Table 1. Specification of simulation parameters innovations. Since the parameters in Equation 13
are functions of the ai’s they can be determined given
Sales process and cost shock
some choice for the cost parameters. West and
KS 1 2 "2S u2 "S , u Wilcox (1996) use several sets of values for these
531 0.001211 0.75 0.20 0.11625 3.5 0.5 based on other work. Here it is chosen to instead
Implied inventory process determine values for the cost parameters that fit the
particular data set being calibrated to. In order to do
KH 1 2 1 2
1050 0.002685 1.06 0.12 0.006 0.065 this it was necessary to jointly estimate the exogenous
sales process, Equation 12, and the reduced form for
inventories, Equation 13. From the parameter
estimates for Equation 13 estimates can be obtained
for combinations of the cost parameters using13
derivative of the objective function must be non- a1 =a0 ¼ 1 ðb 1
2 Þ 2b 2 ð14Þ
negative.12 This yields the requirement that
2
a0 ð1 þ 4b þ b2 Þ þ a1 ð1 þ bÞ þ ba2 0 ð11Þ a2 =a0 ¼ b1 1
2 ð1 þ b1 Þ
In order to use the model to simulate data it is þ b2 2 þ ð1 þ bÞa1 =a0 þ ð1 þ 4b þ b2 Þ ð15Þ
necessary to solve for a reduced form equation in
inventories. This requires a specification of the sales and from estimates of the sales process a3 can also be
process. Here it is assumed for sales to be exogenous derived.
and described by an AR(2) process: In calibrating the model, estimates from BEA data
on total aggregated inventories and sales of non-
St ¼ KS þ t þ 1 St1 þ 2 St2 þ "St ð12Þ durable goods are roughly matched. In fixing the ai’s
where KS and t are constant plus trend terms and "St for the simulation Blanchard (1983) is followed
is assumed I.I.D. Normal. and a0 is normalized to one. Based on the estimates,
With the sales process specified and assuming this results in a0 ¼ 1, a1 ¼ 5.898, a2 ¼ 0.032, and
uncorrelated cost shocks the model can be solved for a3 ¼ 7.191.
a reduced form equation for inventories. The solution With estimates for the cost parameters in hand
methods used are described in Blanchard (1983) and data for inventories and sales can be simulated by
West (1992) and also are available in the form of a specifying the parameters of the exogenous sales
technical appendix to this paper, which may be process along with the distributions of the sales and
obtained from the author upon request. The derived cost innovations. The autoregressive parameters of
equation for inventories is the sales process are set to approximately match those
of the present data. These are given in Table 1.
Ht ¼ 1 Ht1 þ 2 Ht2 þ 1 St1 Following West and Wilcox (1996), the sales innova-
tion variance is set to normalize the unconditional
þ 2 St2 þ t þ KH þ "Ht ð13Þ
variance of the sales process to one. In addition
where the same cost shock variance and correlation with
2 2 sales are used given in that paper, as these values
"Ht ¼ ut þ "St conveniently result in the variance ratio and the
a0 2
correlation between inventories and sales closely
with 1and 2 being functions of the marginal cost matching that of the data. The sales innovation
parameters, 1 and 2 functions of 1, 2 and the variance and the variance of the cost shock also
parameters from the sales process, and t þ KH being are given in Table 1, along with the correlation
trend plus constant terms. The error term, "Ht, between the two. With the ai’s fixed and the sales
indicates the correlation between the inventory and process specified implied values for 1, 2, 1, and
sales processes. 2 can be determined.14 These also are reported in
In order to simulate the data it is necessary to Table 1.
specify values for the parameters of the exogenous To determine coefficients on trend terms West and
sales process, the reduced form inventory equation, Wilcox (1996) is again followed and these are set so
and also the distribution of the sales and cost that the implied coefficients of variation for St
12
See Ramey (1991) for a discussion of this optimality condition.
13
See Blanchard (1983).
14
See technical appendix, available upon request.
1870 D. Doorn
and Ht matches that of the present data, which is Legendre–Clebsch condition of Equation 11. The
found to be approximately 14.6 for sales and 9.7 for first-order condition can now be expressed as
inventories. The coefficient of variation is 1/2/
Et Ht X1tþ2 2 X2tþ1 3 Stþ1 ut ¼ 0 ð16Þ
where is the variance of the process and the mean,
which will involve the trend terms for the process in where
levels. The exact solution for the trend coefficient, as
well as constant terms, is available in the technical X1tþ2 ¼ b2 Htþ2 þ ð2b2 þ 2bÞHtþ1
appendix and yields the values given in Table 1. þ ð2b þ 2ÞHt1 Ht2
The sales and inventory processes specified in
Equations 12 and 13 are used to generate simulated b2 Stþ2 þ ðb2 þ 2bÞStþ1
data for sales and inventories. One thousand samples
ð2b þ 1ÞSt þ St1
were generated by first obtaining starting values for
St1, St2, Ht1 and Ht1 by generating series of X2tþ1 ¼ bHtþ1 þ Ht1 þ bStþ1 St
length T ¼ 1000 from each process while omitting the
a0
trend terms. The last two observations from each of 1 ¼
c
these series are then used as the starting values in
generating an additional 1000 observations from both a1
2 ¼
the inventory and sales processes, this time including c
the trend terms. The final 500 observations from each ba2 a3
3 ¼
series is then chosen as the sample.15 c
c ¼ a0 ð1 þ 4b þ b2 Þ þ a1 ð1 þ bÞ þ ba2
Given the values of the cost parameters above, the
implied population values of the regression coeffi-
IV. Estimation Technique
cients are 1 ¼ 0.056, 2 ¼ 0.332, and 3 ¼ 0.013.
Replacing expectations with realized values in
In estimating the model using the simulated data the
Equation 16 and solving for current period inven-
goal is to retrieve estimates of the population values
tories gives a linear equation which can then be used
of the cost parameters. However, it may be noted
in estimation.
from Equation 9 that these are not fully identified by
the Euler equation, as any simultaneous scaling of a0, Ht ¼ 1 X1tþ2 þ 2 X2tþ1 þ 3 Stþ1 þ vtþ2 ð17Þ
a1, or a2 would have no effect on the Euler condition.
where vt þ 2 includes the unobservable cost shock
Because of this the process is reduced to estimating
along with expectational errors, or
combinations of parameters rather than the individ-
uals. This requires some sort of normalization in vtþ2 ¼ ut 1 ðX1tþ2 Et X1tþ2 Þ 2 ðX2tþ1 Et X2tþ1 Þ
order to estimate the Euler equation, which amounts 3 ðStþ1 Et Stþ1 Þ ð18Þ
to choosing a left-hand-side variable in Equation 9
and solving for that variable. Choice of which Although Equation 17 is linear in the parameters,
variable to solve for has often varied in previous the correlation structure of the regressors rules out
studies, and although it should not affect the Euler ordinary least squares estimation as inconsistent.
equation identities, it does often result in different Instead, an instrumental variables procedure is used
estimates for the parameter values.16 to obtain consistent estimates of the regression
However, the goal here is to construct a valid coefficients. The procedure is implemented using an
model with which to analyse the effects of filtering iterated version of the Generalized Method of
techniques, rather than to make any particular Moments (GMM) estimator of Hansen (1982),
observations on the empirical behaviour of inven- which is equivalent to classical instrumental variables
tories. With this in mind, normalization issues are estimation when the equation is linear in the
ignored, and it is continued to follow West and parameters. Instruments used are a constant and
Wilcox (1996) in choosing to solve for current period two lags each of inventories and sales. Because vtþ2 in
inventories. This is a convenient choice in that it Equation 18 is MA(2), the GMM weighting matrix
amounts to dividing Equation 10 through by the used in estimation is the inverse of the Newey and
15
A sample size of 500 is chosen because this is close to the number of observations available in Bureau of Economic Analysis
data for monthly inventories and sales at this point.
16
See Fuhrer et al. (1995) for a discussion of different normalizations for the linear-quadratic inventory model.
Impact of Hodrick–Prescott filtering on parameter estimation 1871
West (1987) heteroscedasticity and autocorrelation 10
consistent covariance matrix. Additional details of
the estimation procedure are given in the technical 8
appendix, available upon request.
The above model is estimated five times for each of 6
the 1000 samples, using a different procedure for
handling the trend each time. The first method, 4
labelled LDT, just removes a linear trend from the
data by regressing the series on a constant and time 2
and retaining the residuals. The next three methods
use the HP filter for detrending, but with different 0
– 0.10 – 0.05 0.00 0.05 0.10 0.15 0.20 0.25
values for the smoothing parameter , the choices of
which have been used or suggested in various studies Fig. 4. Density of b1 estimates: ( ) LDT, ( ) HP1,
( ) HP2, ( )HP3, ( ) NDT. The vertical line indicates
with monthly data. These will be denoted HP1, HP2, the population value of 0.056
and HP3. HP1 uses the standard value of ¼ 14 400
generally applied in the literature to monthly data.
HP2 uses a value of ¼ 86 400, used by Bils and
Kahn (2000) in their study of inventory behaviour.
HP3 uses a value of ¼ 129 600, suggested as optimal 3
for monthly data in Ravn and Uhlig (1997). The final
procedure, denoted NDT, does not detrend the data
prior to estimation, but instead estimates constant 2
and trend terms along with Equation 17 and adds
time to the instrument set.
1
0
V. Simulation Results – 0.3 – 0.1 0.1 0.3 0.5 0.7 0.9
17
This is due to West and Wilcox (1996), who devise such an interval in their simulation study of instrumental variables
estimators.
Impact of Hodrick–Prescott filtering on parameter estimation 1873
Table 3. Simulation results
19
See, for example, Eichenbaum (1989) and Doorn (2003).
Impact of Hodrick–Prescott filtering on parameter estimation 1875
Sensier, M. (2003) Inventories and asymmetric business West, K. D. (1992) Inventory models, Unpublished
cycle fluctuations in the UK: a structural approach, Manuscript, University of Wisconsin.
Applied Economics, 35, 387–403. West, K. D. and Wilcox, D. W. (1996) A comparison of
Singleton, K. (1988) Econometric issues in the analysis of alternative instrumental variables estimators of a
equilibrium business cycle models, Journal of dynamic linear model, Journal of Business and
Monetary Economics, 21, 361–86. Economic Statistics, 14, 281–93.