Forecasting industry-level CPI and PPI inflation: Does exchange

rate pass-through matter?

Prasad S. Bhattacharya
a,

, Dimitrios D. Thomakos
b,1
a
School of Accounting, Economics and Finance, Deakin University, 221 Burwood Highway, Burwood, Melbourne, Victoria 3125, Australia
b
Department of Economics, University of Peloponnese, Tripolis Campus 22100, Greece
Abstract
We show that incorporating the effects of exchange rate pass-through into a model can help in obtaining superior forecasts of
domestic, industry-level inflation. Our analysis is based on a multivariate system of domestic inflation, import prices and
exchange rates that incorporates restrictions from economic theory. These are restrictions on the transmission channels of the
exchange rate pass-through to domestic prices, and are presented as testable hypotheses that lead to model reduction. We
provide the results of various tests, including causality and prior restrictions, which support the underlying economic arguments
and the model we use. The forecasting results for our model suggest that it has a superior performance overall, jointly producing
more accurate forecasts of domestic inflation.
2007 International Institute of Forecasters. Published by Elsevier B.V. All rights reserved.
Keywords: Causality; Direction of change; Econometric model; Exchange rates; Forecasting; Inflation; Model reduction; Pass-through; VAR
model; VARMA model
1. Introduction
We examine whether industry-level inflation fore-
casts of domestic consumer and producer prices can
be improved when we incorporate additional infor-
mation about potential exchange rate pass-through.
Our analysis is performed in a multivariate setting,
and we compare standard forecasting models, such
as linear multivariate ARMA and VARMA models,
with a structural system that incorporates informa-
tion about the transmission of exchange rate effects
to domestic prices. We cover several different indus-
tries in three major economies, Japan, the United
Kingdom and the United States.
The exchange rate pass-through effect is de-
fined as the percent change in local currency
import prices resulting from a 1% change in the
exchange rate between the exporting and importing
countries. Theoretically, this effect can be either full
Available online at www.sciencedirect.com
International Journal of Forecasting 24 (2008) 134150
www.elsevier.com/locate/ijforecast

Corresponding author. Tel.: +61 3 9244 6645; fax: +61 3 9244

6283.
E-mail addresses: prasbhat@deakin.edu.au (P.S. Bhattacharya),
thomakos@uop.gr (D.D. Thomakos).
1
Tel.: +30 2170 230132; fax: +30 2710 230139.
0169-2070/$ - see front matter 2007 International Institute of Forecasters. Published by Elsevier B.V. All rights reserved.
doi:10.1016/j.ijforecast.2007.06.002
or zero,
2
i.e., a one percent change in the exchange
rate can either lead to an exact and proportionate
(1%) change in local currency import prices, or there
may not be any effect (0%) on the local currency
import prices.
3
Thus, domestic prices may either be
affected significantly or remain unchanged due to an
exchange rate fluctuation. Obstfeld (2001, 2002),
however, proposes another form of pass-through
effect, arguing that the exchange rate pass-through
can be two-dimensional, affecting both import prices
(in local currency terms) and domestic prices. With
this two-dimensional approach, the net effect on
domestic inflation can be either significant or
insignificant, and thus becomes an issue for empirical
investigation. Following Obstfeld's (2002) argu-
ments, we build a structural system that separates
the exchange rate pass-through effects on local
currency import prices and domestic prices of
imported goods in the short-run. We use this system
to empirically test for the presence and extent of the
pass-through effect, and to see whether we can
provide better forecasts of industry-level inflation.
Our analysis adds to the related literature in a
number of ways. First, it links domestic inflation
forecasts with the exchange rate channel in a novel
way for three major OECD countries, using monthly
industry-level prices. Second, we augment our fore-
casting evaluation with a number of tests of the cau-
sality of the exchange rate. The results of these tests are
important in their own right (for checking the validity
of the underlying economic arguments) and are also
used later to determine the extent of the ability of the
pass-through effect to make inflation predictions.
Taylor (2000) argues that the low level of inflation in
the nineties in the US can be one potential explanation
of a lower pass-through effect or lower pricing power of
the firms. He therefore takes the exchange rate as being
endogenous in determining the optimal price level. We,
on the other hand, actually provide formal tests, which
do not necessarily corroborate Taylor's view. Third,
our study relies on a systemthat is built around testable
implications of economic theory. We then extensively
compare the results from this system with those from a
number of atheoretic forecasting methods. The main
novelty and contribution of our proposed system lies in
the way we treat and test for the presence of the
exchange rate pass-through effect. The two-dimen-
sional approach of Obstfeld (2002) is modeled via a
triangular specification of a reduced-form VAR
model, which is tested and reduced in turn, before
generating inflation forecasts. Spanos (1989), Clem-
ents and Mizon (1991), and Hendry and Mizon (1993)
show that, in this kind of a VAR setup, tests for
competing structural hypotheses are possible.
To preview our results, we find significant evidence
in favor of the economic arguments that guide our
approach for most of the industries examined. Speci-
fically, we find evidence in favor of non-causality from
domestic prices to exchange rates, and causality from
exchange rates to domestic prices. These findings
clearly corroborate both the underlying economic
argument and our use of a model where the exchange
rate is used as an explanatory variable rather than being
modeled jointly with domestic prices. After incorporat-
ing the above tested restrictions into our system, we
compute 1, 2 and 3 month ahead forecasts for domestic
inflation variables (consumer and producer inflation),
and compare them with forecasts computed from
atheoretic multivariate time series models, which
includes the parsimonious class of VARMAmodels. We
find that, overall, our model has a superior forecasting
performance when evaluated against standard forecast
evaluation criteria. In particular, our model is either best
or second best (based on the root mean-squared or mean
absolute error of the forecasts) for about 80% of the
cases examined, and is always the best model in
correctly predicting the direction of future domestic
inflation.
4
The ability of the proposed model to produce
accurate forecasts shows that it has higher informational
content than its competitors, and thus should be more
useful to forecasting practitioners engaged in industry-
2
A full effect arises due to a producer currency pricing (PCP)
type assumption, where the imported goods are priced in terms of
the sellers', exporters' or producers' currency (see, in particular,
Obstfeld & Rogoff, 2000; Obstfeld, 2002, and references therein).
On the other hand, a zero effect arises because of the local currency
pricing (LCP, see Devereux, 1997; Engel, 2002) or pricing to
market (PTM; see Krugman, 1987)-type assumptions, where pricing
is done in terms of the buyers', consumers' or importers' currency.
3
Empirical studies (see, for example, Goldberg & Knetter, 1997;
Campa & Goldberg, 2005), however, show that the pass-through
effect is partial, i.e., hovering around 50% in the long-run for
manufacturing traded goods in OECD countries.
4
The results on the directional performance of the generated
forecasts are not reported here but are available to the interested
reader from the corresponding author upon request.
135 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
level forecasting. Finally, our overall results support
Clements and Hendry's (1998, p. 16) claim that fore-
casts from econometric systems should outperform
forecasts from unrestricted VARs.
The rest of the paper is organized as follows. In
Section 2, we briefly summarize some of the previous
literature. In Section 3, we provide an overview of the
motivation and set-up (including reduction and testing)
of our system, and discuss the competing forecasting
models and the computation and evaluation of fore-
casts. In Section 4, we provide a brief description of
our data. In Section 5, we discuss our results. In
Section 6, we offer some concluding remarks.
2. Some related literature
We selectively discuss some previous studies related
to the issues of inflation prediction and the pass-
through effect. Ball (1999) incorporates the degree of
pass-through into the monetary policy rule to control
inflation. Kim (1998) employs a vector error correction
model to show that exchange rate appreciation has a
predictable negative long-run effect on the US PPI.
McCarthy (2000) uses an unrestricted VAR model and
impulse response analysis to examine the impact of
exchange rates and import prices on the domestic PPI
and CPI for nine industrial countries, the US, Japan,
Germany, France, the UK, Belgium, the Netherlands,
Sweden and Switzerland. His findings suggest that
import prices have a much stronger effect than ex-
change rates in explaining domestic price inflation.
This supports other studies like those of Boldin (1998)
and Koenig (1998), which also achieve forecast im-
provements after including import prices in a CPI
inflation forecasting model. Within the existing litera-
ture on the topic of exchange rate changes and their
related consequences for prices, Goldberg and Knetter
(1997) show that the pass-through effect is responsible
for price changes in around 50% of manufacturing
traded goods' prices in OECD countries. Therefore, an
effective monetary policy always remains helpful for
preventing future inflation coming from the exchange
rate channel. In that sense, our study provides a ready-
made analysis of the exchange rate pass-through effect
and its interaction with prices relative to a number of
alternative scenarios. Goldberg (2004) argues for an
industry-specific exchange rate in the US to track the
exchange rate channel affecting producer profit. Our
study can also throwsome light in this direction. Unlike
Goldberg's (2004) argument, we are able to show that
differences in the trade-weighted exchange rate
transmission channel do have differential impacts on
the traded goods' prices, which in turn affects the
producers' profit margins.
3. Methodology
3.1. Overview of the structural system
The structural system
5
idea we use in this paper
incorporates the two-dimensional approach of Obstfeld
(2002), and rests on the concept that there is no
feedback effect of the domestic prices on either import
prices or exchange rates. The exchange rate is taken to
be exogenously determined, and there is no contem-
poraneous feedback from any other price variables
(domestic prices, import prices) in the short-run.
6
This
is termed block causality and is a testable hypothesis.
If this assumption is correct, then an exogenous ex-
change rate change affects, in the short-run, the import
prices at the entry point (direct effect), and at a later
stage, the domestic prices of imported goods (indirect,
second stage effect). The second stage effect requires
there to be a mismatch between domestic prices of
imported goods and imported goods' prices at the point
of entry if domestic transport costs remain unchanged
and markup adjustments by domestic importers and
producers are sluggish.
This relative price difference between the point of
entry and the point of sale for the one good can be
captured well if there is no effect of past domestic
prices on current domestic prices of imported goods.
This is termed triangularity and is also testable. In
addition, there is another effect at work in our system,
termed the carry-over effect. The carry-over effect
basically states that if there are imported intermediate
factor inputs for domestic production, then as a result
5
The structure in our system refers to the use of prior information
from economic theory about the relative causal response of the
various price series; it does not refer to the standard notion of an
econometric structural model with contemporaneous values of the
endogenous variables on the right-hand side.
6
See Adolfson (2001) for a discussion regarding the treatment of
the exchange rate as exogenous and omitting controls for
disaggregated industry-level work.
136 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
of an exogenous exchange rate change, the price
difference between domestic prices of importables and
the import prices of goods at the entry point will
significantly affect domestic producer prices. The
relative price difference can generate more expendi-
ture-switching toward domestically produced goods,
which can be generically captured by the price dif-
ference between the point of entry and the point of sale.
In particular, if the imported goods at the point of entry
are invoiced in the currencies of the exporter or pro-
ducer countries, the exchange rate pass-through effect
will be very high, which is nothing but the direct effect
we pointed out earlier. On the other hand, as the
domestic prices of those imports are quoted in the
domestic or seller's currencies, the exchange rate shock
will have a minimal role to play in their increase. As a
result, the mismatch between industry-level prices for
goods will be higher, with producer currency pricing
evidence at the entry point and local currency pricing or
pricing to market evidence at the domestic level.
In our setup, we test and/or use the two components
discussed above: block causality and triangularity. We
build three different reduced-form systems to capture
the effect of changes in the exchange rate on import
prices, producer prices, and consumer prices. Below
we discuss system I in greater detail. What differen-
tiates the three systems is that the pass-through is
toward consumer prices in system I and toward pro-
ducer prices in systems II and III.
3.1.1. System I
Here we focus on the short-run price changes of
imported final goods. At the point of entry, retailers
pay the import price P
ri
, which includes a markup
m
i

m
i

(E
i
) 0 charged by the foreign exporters that
depends on the prevailing exchange rate E
i
. An exo-
genous change in the exchange rate leads to a change
in import prices given by:
dlogP
ri
dlogE
i
1
dlog 1 m

i
_ _
dlogE
i
; 1
where we assume that such a change has no effect on
the price charged by the foreign exporters, i.e.,
dlogP
i

/dlogE
i
=0. Depending on whether m
i

changes
or not, a change in the exchange rate may or may not
be reflected in P
ri
: if there is no change in the markup
then there is full pass-through to import prices; if
there is a reduction in the markup (e.g., to maintain
the exporters' competitiveness) then there can be no
change in the domestic import prices. As pointed out
earlier, this is the first channel of short-run exchange
rate pass-through. Here foreign exporters can dis-
criminate among destination markets by price.
Once in the home market, retailers have to bear the
transport and distribution costs of final goods before
selling them to the consumers. Denoting these costs for
the ith good as
i

i
(P
ri
) 0, the change in the total
marginal cost the retailers face from a change in the
exchange rate is given by:
dlogMC
ri
dlogE
i

dlogP
ri
dlogE
i

dlog 1 X
i

dlogE
i
; 2
and again, the effect on the marginal cost for the
retailer depends on the response of import prices, and
the corresponding response of distribution costs, to the
exchange rate change. Now, letting the domestic
markup charged by the retailer to final consumers be

i
(MC
ri
) 0, we find that the effect on the final
price of the ith good is given by:
dlogP
ci
dlogE
i

dlogMC
ri
dlogE
i

dlog 1 g
i

dlogE
i
; 3
or by combining Eqs. (1), (2) and (3):
dlogP
ci
dlogE
i
1
dlog 1 m

i
_ _
dlogE
i

dlog 1 X
i

dlogE
i

dlog 1 g
i

dlogE
i
: 4
Eq. (4) shows the link between the exchange rate
E
i
, domestic prices for retailers of imported goods P
ri
,
and domestic prices for consumers of imported goods
P
ci
. An import price increase driven by exchange rate
depreciation may or may not lead to a proportional
increase in consumer prices, depending on the changes
in the corresponding mark-ups. This is the second
channel of pass-through: the response of domestic
prices to changes in the prices of imports can be
explained by changes in the existing domestic
markups,
i
and
i
, in the way we described
previously. The foreign and domestic markup adjust-
ments may dampen the transmission of the changes in
the exchange rate to import prices and domestic prices.
These adjustments can be a reflection of sluggish
137 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
nominal wage adjustments in the foreign country as
well as in the home country.
The above approach identifies two different channels
of exchange rate pass-through. One channel is at the
point of entry, and is captured by fluctuations in import
prices at the point of entry. The other channel is one
whichtransmits changes in the exchange rate to domestic
prices (which can be either consumer or producer prices)
through markup adjustments by domestic and foreign
agents. To capture these effects empirically, we need
properly matched industry-level import prices, consumer
prices and producer prices. In addition, this conceptual
framework reflects the assumptions of block causality
and triangularity, as discussed before.
Finally, it is important to note a practical implica-
tion of the above formulation. If these assumptions
about the transmission of an exchange rate change are
correct, then one can trace the impact of such a change
sequentially through import prices to domestic prices.
This is not only testable as a hypothesis (the triangu-
larity mentioned above), it is also useful in making
forecasting scenarios: if one has a properly specified
model, then in principle, it can produce forecasts for
any desired path of the exchange rates.
3.2. Specification, reduction and testing of the
structural system
We convert the conceptual framework of the pre-
vious section into a dynamic econometric specification
with testable restrictions and implications. Following
the previous subsection, and because we are interested
in producing inflation forecasts later on, our analysis is
performed on log-changes of prices. Let us therefore
denote CPI inflation by y
t
1
, PPI inflation by y
t
2
, the
percentage change in import prices by y
t
3
, and the
percentage change in the exchange rate by x
t
, all of
which are expressed as deviations from their sample
means. Consider these variables as being the compo-
nents of the vector z
t
=(y
t
T
, x
t
)
T
, where y
t
(y
t
1
, y
t
2
, y
t
3
)
T
denotes the vector of price changes, and incorporate
them into an unrestricted VAR model of order p as:
z
t

p
j1
F
j
z
tj
u
t
; 5
where u
t
=(
t
T
,
t
)
T
is assumed to be a multivariate
white noise with covariance matrix . The coefficient
matrices
j
and the error covariance matrix can be
expressed in partitioned form as:
F
j

F
yyj
j
xyj
j
T
yxj
u
xxj
_ _
;

S
e
s
eg
s
T
eg
r
g
_ _
: 6
This allows us to easily express several hypotheses and
sub-models that we will consider. The hypothesis of no
block causality from prices to the exchange rate is
given by:
Hypothesis set # 1. H
0
BC
:
yxj
=0 for all j =1, 2, , p,
for the absence of block causality.
Note that the above test, as well as the other
hypothesis tests that follow, are Wald-type tests.
If the hypothesis of no block causality is correct,
then the generic VAR model of Eq. (5) is reduced to a
VARX (VAR with exogenous variables) model that
can be written as:
y
t

p
j1
F
yyj
y
tj
j
xyj
x
tdj
_ _
e
t
; 7
where we allow for the possibility of a delayed
response of d periods for prices from a change in the
exchange rates (note that this is compatible with the
idea of sluggish adjustments mentioned before). We
can, as in Eq. (6), partition the relevant coefficient
matrices as:
F
yyj

11j

12j

13j

21j

22j

23j

31j

32j

33j
_
_
_
_
; j
xyj

xy1j

xy2j

xy3j
_
_
_
_
:
8
The VARX model of Eq. (7) can now incorporate
the two-dimensional approach of Obstfeld (2002), the
dual transmission of exchange rate changes through
import and domestic prices. The model can be further
refined by imposing and testing additional hypotheses.
For example, note that triangularity is given as a set of
restrictions on the dynamics of the model, and that it
requires the absence of short-term feedback from con-
sumer and producer prices to import prices, and si-
milarly from consumer prices to producer prices.
138 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
Therefore, triangularity can be expressed as a set of
restrictions as:
Hypothesis set # 2. H
0
TR
: /
klj
=0 for all kNl and
every j =1, 2, , p.
In addition, within the context of the VARX model
and the triangularity restrictions, we can test for the
validity of the unidirectional feedback, i.e., we can per-
form causality-type tests within the triangular structure
as:
Hypothesis set # 3. H
0
TRC,1
: /
12j
=/
13j
=0, H
0
TRC,2
:
/
23j
=0, H
0
TRC,3
: /
xy3j
=0 for all j =1, 2, , p.
The first hypothesis above tests whether domestic
consumer prices are indeed affected by producer and
import prices; the second hypothesis tests whether pro-
ducer prices are affected by import prices, given that
the triangularity assumption is satisfied; and the third
hypothesis tests whether import prices are affected by
the exchange rate, again given that the triangularity
assumption is satisfied.
The sequence of steps that we take in specifying
and forecasting using our structural system can now
be summarized as follows:
Note that we do not compute forecasts from the
estimates of the model in step (b). This step is performed
to generate the additional causality assumptions.
We compute forecasts from the unrestricted model of
Eq. (5) in step (a), since the no causality assumptions that
lead to the structural system need not be incorrect. As
we explain in the next section, we also use a more
parsimonious VARMAmodel for computing unrestricted
forecasts. However, we do test the triangularity assump-
tion, as it rests on prior economic motivations, and always
generate forecasts from the VARX model, as in step (c).
7
In the discussion of our results, as well as in the
tables, we use the notationSYSto denote the structural
system as described in this section, and the notation
VAR1 to denote the unrestricted VAR model of Eq. (5).
3.3. Competing forecasting models and forecast
evaluation
We compare the forecasts we generate from either
the SYS or VAR1 models with forecasts that are
computed from a different VAR model and from a
VARMA model. We denote these two models VAR2
and VARMA, respectively. The second VAR model
(VAR2) is an unrestricted VAR that excludes import
prices and the exchange rate, but includes consumer
prices and producer prices, and is further augmented
using interest rates and the unemployment rate. Letting
w
t
=(y
t1
, y
t2
, r
t
, u
t
)
T
denote the vector of variables
entering the second VAR model, we have a similar
representation to that in Eq. (5), i.e.:
w
t

k
j1
P
j
w
tj
v
t
; 9
where v
t
is assumed to be multivariate white noise. Both
unrestricted VAR models of Eqs. (5) and (9) are esti-
mated using nine lags.
8
7
An issue raised by the editor was the treatment of the exogenous
variable, the exchange rate, when generating our inflation forecasts
from the VARX model. Clearly, using the true, out-of-sample values
for the exchange rate would not be legitimate, and another
forecasting model would be needed to generate forecasts of the
exchange rate as well. However, in all of our specifications, the
exchange rate was entered with a lag of order d3, and therefore
we could use, in a proper way, the past values of the exchange rate
when we generated inflation forecasts.
8
Nine lags are chosen, keeping in mind that the existing literature
on the exchange rate pass-through effect (see, for example,
Goldberg & Knetter, 1997; and Campa & Goldberg, 2005) points
out that the long-run timeframe starts with the third quarter, where
the pass-through to local currency import prices seems to be
complete. In that case, there will be more inflationary pressure on
domestic industrial prices coming from the exchange rate channel.
(a) Estimate the unrestricted VAR model of Eq. (5),
perform and report the tests in Hypothesis set
#1, and generate the corresponding forecasts.
(b)Impose the block causality hypothesis for the
exchange rate, and reduce the model to the
VARX of Eq. (7). Perform and report the tests in
Hypothesis set #3, under the triangularity
assumption.
(c) Estimate the VARX model of Eq. (7) and
perform the tests in Hypothesis set #2:
1. If the triangularity assumption is not re-
jected, impose it and re-estimate the model
by seemingly unrelated regression (SUR)
then generate forecasts from the restricted
VARX model.
2. If the triangularity assumption is rejected,
then proceed with the unrestricted VARX
model in generating forecasts.
139 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
In addition to these unrestricted VARmodels, we also
employ a more parsimonious VARMA(1,1) model.
9
The class of VARMA models is considerably more
flexible in modeling and forecasting linear multiva-
riate time series, but is also considerably more time-
consuming to estimate. However, a VARMA model
seems to be a very appropriate benchmark for fore-
casting comparisons in this context. The model is given
by:
z
t
A
1
z
t1
x
t
B
1
x
t1
; 10
where
t
is again assumed to be a multivariate white
noise. Since our forecasting evaluation requires multiple
nonlinear estimations for this model, we use the fast,
regression-based method of Spliid (1983) for estimating
the parameter matrices and generatingthe corresponding
forecasts.
Our forecasts are for horizons of h=1, 2, 3 months
and are computed using a rolling window of T
0
observations; they are initially evaluated using their
root mean-squared and mean absolute errors. Denoting
the h step-ahead forecast for the ith price variable (CPI
inflation y
t1
or PPI inflation y
t2
) from the mth
forecasting model by
t+h|t,i
, we compare:
R
i
m

1
T
1

T
tT
0
1
y
thjt;i
m y
th;i
_ _
2
;

_
A
i
m
1
T
1

T
tT
0
1
j y
thjt;i
m y
th;i
j;
11
for the root mean-squared and mean absolute errors
respectively, where T
0
+T
1
=T, with T
0
being the
training sample and T
1
being the evaluation sample.
We then use the Diebold and Mariano (1995) test to
more formally compare the forecasting performances
of the competing models, based on the difference of
their forecasting errors. We employ both the squared
loss function and the absolute value loss function in
computing the DieboldMariano test statistics. Our
discussion of the results is based on the root mean-
squared statistic and the DieboldMariano test using
the squared loss function. The results based on the
mean absolute error statistic and the corresponding
DieboldMariano tests are qualitatively similar and
are available on request.
4. Data
An appropriate empirical analysis based on the above
discussion can be performed using suitably disaggre-
gated data. While we do not have access to industry-
level domestic prices of the imported goods, the data we
have include (1) consumer prices (CPI) (which reflect
the prices of final products or final consumer goods), (2)
import prices (IMP) for final goods, intermediate goods
and crude materials, and (3) prices for domestic pro-
ducers (PPI), again for final goods, intermediate goods
and crude materials. With these data, we should be able
to distinguish in terms of end uses, and this allows us to
gain a better understanding of the channels of pass-
through under investigation.
Our choice of data is guided by two considerations.
First, we need to have industry-level price data for
imported goods, as well as matching industry-level
price data for intermediate goods (if available, as in
system II) and matching price data for final goods (can
be for producers goods, as in system III, or for final
consumers goods, as pointed out in system I). Second,
we concentrate on three of the largest active global
economies, Japan, the United Kingdom and the United
States, which are involved in heavy trading across three
different regions. It is important to note that these
countries do have the required data. We have access to
perfectly matching industry-level price data for four-
teen US industries, thirteen UK industries and seven
Japanese industries (and not for all SITC industries).
The monthly data frequency we use is guided by the
question we try to answer in this study: whether we can
improve the forecast performance in the presence of
short-run pass through at the SITC level of industrial
manufacturing goods data. Additional details about the
raw data can be obtained from the authors on request.
For Japan, we have data for import prices, producer
prices, wholesale prices (WPI), trade-weighted ex-
change rates, and short-term interest rates from the
Bank of Japan's website. The seven industries we use
9
We thank the referee for suggesting benchmarking on a
VARMA(1,1) model and a VAR model with endogenous exchange
rates. We have cross-checked the forecast results from the VARMA
(1,1) model with models of orders (1, 2), (2, 1) and (2, 2), and VAR
models with lags 6, 10, 12, and 15. The findings remain
qualitatively similar, and are therefore not reported.
140 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
Table 1
Tests for causality: United Kingdom (PPI-based models)
Industry/Lags Block causality for exchange rate Causality in the triangular structure
(ppi, imp)wfx wfx (ppi, imp) Block causality from imp to ppi Block causality from wfx to imp
ppi imp impppi impwfx wfximp
Tobacco
3 0.579 0.003 0.227 0.067 0.495 0.002
6 0.262 0.002 0.004 0.085 0.365 0.011
9 0.184 0.000 0.215 0.290 0.538 0.001
12 0.026 0.000 0.233 0.018 0.552 0.000
Pulp
3 0.858 0.534 0.000 0.494 0.725 0.664
6 0.532 0.329 0.000 0.482 0.520 0.236
9 0.390 0.426 0.000 0.493 0.266 0.392
12 0.043 0.086 0.000 0.208 0.105 0.128
Wood
3 0.546 0.032 0.000 0.146 0.275 0.048
6 0.615 0.012 0.003 0.813 0.225 0.024
9 0.082 0.053 0.006 0.437 0.033 0.049
12 0.032 0.042 0.020 0.329 0.043 0.050
Metal
3 0.815 0.137 0.002 0.361 0.887 0.790
6 0.952 0.473 0.004 0.278 0.961 0.768
9 0.288 0.338 0.016 0.172 0.576 0.791
12 0.235 0.182 0.014 0.270 0.397 0.074
Chemical
3 0.876 0.000 0.003 0.005 0.661 0.000
6 0.972 0.000 0.001 0.016 0.883 0.001
9 0.902 0.000 0.012 0.040 0.842 0.004
12 0.835 0.000 0.043 0.006 0.732 0.013
Org-chem
3 0.285 0.014 0.000 0.300 0.201 0.001
6 0.277 0.001 0.000 0.362 0.365 0.002
9 0.152 0.000 0.004 0.568 0.168 0.004
12 0.037 0.002 0.012 0.362 0.069 0.007
Medi.
3 0.440 0.002 0.521 0.334 0.385 0.731
6 0.301 0.008 0.387 0.740 0.716 0.433
9 0.033 0.000 0.391 0.478 0.408 0.232
12 0.053 0.010 0.048 0.590 0.336 0.360
Plastics
3 0.967 0.019 0.000 0.726 0.898 0.120
6 0.943 0.028 0.001 0.279 0.959 0.023
9 0.917 0.040 0.033 0.303 0.855 0.037
12 0.479 0.011 0.001 0.049 0.431 0.050
Tex-fabs
3 0.421 0.014 0.014 0.337 0.458 0.009
6 0.866 0.037 0.032 0.188 0.784 0.085
9 0.824 0.207 0.072 0.061 0.659 0.293
12 0.752 0.227 0.044 0.052 0.343 0.526
Iron
3 0.536 0.345 0.001 0.237 0.936 0.991
6 0.630 0.102 0.009 0.216 0.812 0.986
9 0.209 0.088 0.056 0.064 0.865 0.960
12 0.276 0.014 0.254 0.207 0.898 0.600
(continued on next page)
141 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
are chemicals; foodstuffs and feedstuff; machinery and
equipment; metals and related products; petroleum,
coal and natural gas; textiles and wood; and lumber and
related products. The sample period is from 01/1971 to
12/2002, which contains T=384 observations. The
trade-weighted exchange rate is defined as the Japanese
Yen vis--vis weighted index of Japan's major trading
partners' currencies. The civilian unemployment rate
series, obtained from the International Labor Organi-
zation's (ILO) website, starts from 01/1976 and ends at
12/2002, reducing the sample to T=324 observations.
For the United Kingdom, we have data on import
prices, producer prices and the civilian unemployment
rate from National Statistics Online. The thirteen indus-
tries we use are tobacco; pulp and waste paper; wood
and cork; metal ores; chemicals; organic chemicals;
medicinal products; plastics; textile fabrics; iron and
steel; non-ferrous metals; machinery and transport
equipment; and electrical machinery. The trade-weight-
ed exchange rate and average discount rates for Treasury
bills are downloaded from the Bank of England's
website. For all UK data series, the sample period is
from 01/1991 to 12/2002, giving a total of T=144
observations.
For the United States, we have data on import prices,
producer prices and corresponding consumer prices. In
addition, we again use a trade-weighted exchange rate,
defined as the US dollar/weighted average of 27
countries' currencies, plus the overall civilian unem-
ployment rate, the federal funds rate and the 3-month
Treasury bill rate. All data series are from the Bureau of
Labor Statistics and the Federal Reserve Bank of Saint
Louis online databases. The fourteen industries we use
are meat and meat preparations; vegetables, fruit and
nuts, fresh or dried; beverages and tobacco; beverages;
mineral fuels; lubricants and related materials; chemi-
cals and related products, n.e.s. (not essentially
specified); organic chemicals; inorganic chemicals;
rubber manufactures, n.e.s.; non-metallic mineral man-
ufactures; metalworking machinery; electrical machin-
ery and equipment; furniture and parts thereof; and
articles of apparel and clothing accessories. The sample
period varies across industries and data series, with the
earliest monthly series starting at 01/1989. The number
of available observations thus varies between T=108
and T=168 observations by the series and model used.
For our forecast evaluations, we set the evaluation
sample to T=48 months for thirty industries across all
Table 1 (continued)
Industry/Lags Block causality for exchange rate Causality in the triangular structure
(ppi, imp)wfx wfx (ppi, imp) Block causality from imp to ppi Block causality from wfx to imp
ppi imp impppi impwfx wfximp
Nonfme
3 0.457 0.631 0.000 0.398 0.455 0.973
6 0.487 0.393 0.001 0.662 0.442 0.867
9 0.051 0.010 0.000 0.314 0.399 0.306
12 0.006 0.010 0.008 0.205 0.127 0.361
Mach
3 0.457 0.000 0.463 0.224 0.231 0.000
6 0.373 0.000 0.895 0.248 0.119 0.000
9 0.517 0.000 0.672 0.093 0.190 0.000
12 0.222 0.001 0.916 0.461 0.147 0.000
El-mach
3 0.575 0.125 0.003 0.426 0.731 0.049
6 0.555 0.007 0.001 0.013 0.412 0.011
9 0.066 0.009 0.004 0.018 0.194 0.006
12 0.001 0.005 0.004 0.013 0.086 0.028
xy denotes x does not cause y; the numbers in the cells are p-values of the corresponding test; wpi stands for the wholesale price index;
wfx stands for the trade-weighted exchange rate; imp stands for the import price; and ppi denotes the producer price. In the table, Pulp
denotes pulp and waste paper, Wood denotes wood and cork, Metal stands for metal ores, Chemical stands for chemicals, Org-chem
denotes organic chemicals, Medi. denotes medicinal products, Tex-fabs denotes textile fabrics, Iron stands for iron and steel, Nonfme
stands for non-ferrous metals, Mach denotes machinery and transport equipment, and El-mach denotes electrical machinery.
142 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
Table 2
Tests for causality: United States (PPI-based models)
Industry/Lags Block causality for exchange rate Causality in the triangular structure
(ppi, imp)wfx wfx(ppi, imp) Block causality from imp to ppi Block causality from wfx to imp
ppi imp impppi impwfx wfximp
Meat
3 0.929 0.914 0.032 0.690 0.845 0.894
6 0.929 0.908 0.167 0.834 0.851 0.934
9 0.751 0.793 0.036 0.962 0.798 0.967
12 0.656 0.474 0.026 0.312 0.700 0.989
Fruit
3 0.611 0.294 0.010 0.068 0.296 0.247
6 0.352 0.760 0.074 0.387 0.111 0.743
9 0.354 0.718 0.113 0.140 0.213 0.658
12 0.516 0.787 0.170 0.163 0.352 0.687
Beve
3 0.019 0.745 0.833 0.902 0.064 0.933
6 0.070 0.208 0.178 0.923 0.104 0.863
9 0.013 0.075 0.521 0.209 0.061 0.959
12 0.000 0.015 0.880 0.472 0.006 0.873
Chemical
3 0.204 0.000 0.000 0.807 0.238 0.000
6 0.221 0.008 0.004 0.348 0.391 0.001
9 0.288 0.033 0.003 0.058 0.398 0.013
12 0.141 0.004 0.000 0.012 0.260 0.015
Org-chem
3 0.047 0.196 0.259 0.047 0.035 0.081
6 0.023 0.104 0.216 0.122 0.060 0.038
9 0.059 0.024 0.415 0.070 0.150 0.054
12 0.061 0.001 0.207 0.010 0.148 0.029
Inor-chem
3 0.038 0.073 0.418 0.123 0.012 0.044
6 0.015 0.471 0.023 0.064 0.022 0.199
9 0.002 0.439 0.036 0.147 0.026 0.423
12 0.001 0.406 0.076 0.060 0.006 0.535
Rubber
3 0.807 0.006 0.005 0.713 0.785 0.005
6 0.228 0.019 0.023 0.638 0.815 0.021
9 0.158 0.088 0.067 0.634 0.617 0.058
12 0.246 0.087 0.044 0.394 0.682 0.075
Nm-min
3 0.502 0.011 0.476 0.388 0.584 0.004
6 0.202 0.273 0.194 0.377 0.503 0.049
9 0.006 0.484 0.465 0.530 0.375 0.134
12 0.003 0.166 0.039 0.696 0.141 0.313
Me-mach
3 0.845 0.000 0.222 0.821 0.864 0.000
6 0.101 0.000 0.352 0.766 0.817 0.000
9 0.001 0.000 0.209 0.333 0.285 0.000
12 0.001 0.000 0.280 0.063 0.446 0.000
El-mach
3 0.015 0.023 0.216 0.425 0.026 0.018
6 0.010 0.072 0.805 0.248 0.005 0.033
9 0.030 0.053 0.899 0.027 0.022 0.056
12 0.003 0.012 0.123 0.024 0.004 0.063
(continued on next page)
143 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
three countries, and to T
1
=44 months for four indus-
tries in the United States. Our choice of estimation and
evaluation samples is such that, for the monthly data we
use, it allows a reasonable sample for both estimating
the parameters and excluding outliers (which could
not be accurately forecasted anyhow) from the
evaluation periods.
10
5. Discussion of results
5.1. Causality tests and model reduction
An important premise in our set-up is the assump-
tion of non-causality of the exchange rate with respect
to the other variables in our system, as well as the
assumption of the triangular structure (based on the
two-dimensional approach of Obstfeld, 2002). In this
section, we discuss some results from the corres-
ponding tests for the United Kingdom and the United
States for PPI-based models; the full set of test results,
including those for Japan, is available on request. These
results are presented in Tables 1 and 2. As all of the tests
are based on a VAR model, we present the results using
four different lags, 3, 6, 9 and 12 months. Each of the
tables has 6 columns; of particular interest are columns
1 and 2 (tests of no block causality) and columns 5 and
6 (tests of no pairwise causality between exchange rates
and import prices within the triangular structure). The
other columns of the tables provide additional tests for
the triangular structure.
Our results can be summarized as follows. For most
of the industries in all three countries, we simulta-
neously find evidence of causality from the exchange
rate to the price variables (column 2), and no significant
evidence of causality from the price variables to the
exchange rate (column 1). There is either a feedback or
a mutual absence of causality in very few industries. We
can claim that, overall, the hypothesis of no block
causality, H
0
BC
:
yxj
=0, for all j =1, 2, , p, is mostly
accepted. This is an important finding, as it allows us to
move on from the unrestricted VAR model of Eq. (5) to
the restricted VARX model of Eq. (7). For a large
proportion of industries (about 70%), we have evidence
of no block causality from the price variables to the
exchange rate, and the tests suggest that our use of the
VARX model appears to be appropriate.
The results from the tests within the triangular
structure for the domestic price and import variables
are mixed (columns 3 and 4), while the results about
the causality between import prices and exchange rates
(columns 5 and 6) are more informative and robust.
For about 40% of all industries, we simultaneously
find evidence of no causality from import prices to the
exchange rate, but causality from the exchange rate to
import prices.
Table 2 (continued)
Industry/Lags Block causality for exchange rate Causality in the triangular structure
(ppi, imp)wfx wfx(ppi, imp) Block causality from imp to ppi Block causality from wfx to imp
ppi imp impppi impwfx wfximp
Furni.
3 0.408 0.939 0.534 0.913 0.207 0.875
6 0.428 0.001 0.337 0.977 0.285 0.004
9 0.386 0.004 0.783 0.928 0.171 0.003
12 0.658 0.000 0.716 0.739 0.348 0.000
xy denotes x does not cause y; the numbers in the cells are p-values of the corresponding test; cpi stands for the consumer price index; wfx
stands for the trade-weighted exchange rate; imp stands for the import price; and ppi denotes the producer price. In the table, Meat stands
for meat and meat preparations, Fruit stands for vegetables, fruit and nuts, fresh or dried, Beve stands for beverages, Chemical denotes
chemicals and related products, not essentially specified, Org-chem stands for organic chemicals, Inor-chem stands for inorganic chemicals,
Rubber stands for rubber manufactures, not essentially specified, Nm-min stands for non-metallic mineral manufactures, Me-mach denotes
metalworking machinery, El-mach stands for electrical machinery and equipment, and Furni denotes furniture and parts thereof.
10
Here we consider outliers as those observations that are about
three sample standard deviations away from the corresponding
sample mean. We do note in passing that, based on this definition,
the selected evaluation samples show suggestive evidence of
underlying normality for the series. A complete list of descriptive
statistics is available on request.
144 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
Overall, the results of the causality analysis are
supportive of our use of prior economic information in
our system and of the corresponding model reduction
we obtain from turning the unrestricted VAR into the
triangular, restricted VARX model.
5.2. Comparison of forecasting performance
While the results on causality testing and model
reduction are supportive of our proposed approach, we
still need to see how our structural system fares out-
of-sample. Tables 310 contain all of the out-of-sample
evaluation results. We have grouped them by country:
Tables 3 and 4 for Japan, Tables 5 and 6 for the United
Kingdom, and Tables 710 for the United States. We
consider our findings quite interesting, both from an
economic perspective and from a purely forecasting
perspective.
If we compare the models based on their RMSE
values, then our system is either the best or second best
forecasting model in almost all cases considered. In
addition, it is more frequently the best model as the
forecasting horizon increases. This could potentially be
attributed to the appropriate or efficient use of the
economic structure we impose on our system. For the
1 month ahead forecasts, our system is the best (second
Table 4
DieboldMariano tests using a squared loss function for Japan
Industry Monthly rolling forecasts
VARMA VAR1 VAR2 VARMA VAR1 VAR2 VARMA VAR1 VAR2
One month ahead Two months ahead Three months ahead
Chemical 0.55 1.24 0.18 0.81 2.17

0.14 0.67 2.13

0.03
Food 0.64 1.77

0.66 0.06 1.10 2.45

0.01 0.99 2.52

Mach 0.82 0.24 1.36 0.02 1.02 0.60 0.11 0.80 1.26
Metal 1.06 1.69

1.26 0.74 2.22

0.20 0.29 1.98

0.57
Petrol 0.22 0.43 0.21 0.24 1.36 1.75

0.66 1.91

1.68

Textiles 0.02 0.58 1.62

0.15 1.17 1.14 0.09 1.60

0.41
Wood 0.26 0.47 0.29 0.41 1.50

1.17 1.21 1.61

1.60

Cell entries are the values of the test statistic;

,

and

denote the 99%, 95% and 90% levels of significance, respectively; and the squared
loss function is used to calculate the DieboldMariano test statistic. All results are reported in comparison with the SYS results: a negative number
indicates superior performance of the SYS, a positive number indicates superior performance of the competing model. For industry and model
details, see the notes of Table 3.
Table 3
Root mean-squared errors (RMSEs) for Japan
Industry Monthly rolling forecasts
VARMA SYS VAR1 VAR2 VARMA SYS VAR1 VAR2 VARMA SYS VAR1 VAR2
One month ahead Two months ahead Three months ahead
Chemical 5.33 5.56 6.25 5.84 5.23 5.01 7.09 5.68 5.02 5.14 7.03 5.46
Food 3.31 3.21 3.44 3.02 3.30 3.07 3.65 3.06 3.31 3.08 3.56 3.04
Mach 5.63 5.57 5.10 5.80 5.27 5.18 5.18 5.59 5.31 5.21 5.30 5.18
Metal 2.42 2.07 2.71 2.47 2.48 2.01 3.17 2.19 2.53 1.98 3.27 2.28
Petrol 18.95 19.61 19.19 19.39 20.63 19.62 22.18 21.02 21.01 19.15 23.81 21.37
Textiles 6.59 6.67 6.45 7.79 6.62 6.63 6.33 7.37 6.51 6.52 6.20 6.76
Wood 5.92 6.15 6.00 6.01 6.81 6.39 7.84 7.23 7.43 6.41 8.18 7.52
Cell entries are values of the RMSE; VARMA stands for a VARMA(1,1) model with exchange rate as an endogenous variable; SYS stands for
the structural triangular system; VAR1 stands for an unrestricted VAR with exchange rate as an endogenous variable; and VAR2 stands for an
unrestricted VAR without import prices and exchange rates, including only inflation rates, interest rates and unemployment. Chemical stands
for chemicals, Food stands for foodstuffs and feedstuff, Mach stands for machinery and equipment, Metal stands for metals and related
products, Petrol stands for petroleum, coal and natural gas, Textiles stands for textiles and Wood stands for wood, lumber and related
products.
145 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
best) in 1(4) out of the 7 industries in Japan, 5(6) out of
the 13 industries in the United Kingdomand 4(8) out of
the 14 industries in the United States. For the 3 months
ahead forecasts, the systemis the best (second best) in 4
(3) out of the 7 industries in Japan, 7(4) out of the 13
industries in the United Kingdom and 4(5) the
industries in the United States. Therefore, based on
RMSE values, our system is the best model for 29% of
all industries for one step-ahead forecasts, and is the
best model for 44% of all industries for three steps-
ahead forecasts. The corresponding numbers for the
second best model are 53% and 35%, respectively.
The closest competitor to the system is the VARMA
model.
Table 6
DieboldMariano tests using a squared loss function for the United Kingdom
Industry Monthly rolling forecasts
VARMA VAR1 VAR2 VARMA VAR1 VAR2 VARMA VAR1 VAR2
One month ahead Two months ahead Three months ahead
Tobacco 0.44 1.01 1.68

0.71 0.06 1.44 0.81 0.23 1.28

Pulp 0.17 0.39 0.43 0.09 0.34 0.40 0.60 0.24 0.11
Wood 0.54 0.76 0.58 0.12 1.56

1.66

0.07 0.57 0.43

Metal 0.05 0.75 0.81 0.22 0.79 0.50 0.10 2.00

0.00
Chemical 0.34 0.14 0.95 0.99 0.53 0.84 0.31 0.30 0.38
Org-chem 0.25 0.63 1.28 0.25 0.71 0.41 0.36 1.49

0.87
Medi. 0.14 1.06 2.72

0.17 1.39 1.10 0.17 1.40 0.97

Plastics 1.11 0.48 1.74

1.44 0.13 2.44

0.15 1.59

0.93
Tex-fabs 0.21 0.32 1.49

0.04 0.17 0.65 0.72 0.69 0.23

Iron 0.27 1.47

0.65 0.23 0.30 0.92 0.07 1.33 1.29

Nonfme 0.02 1.26 0.37 0.33 1.97

1.13 0.44 1.75

0.88
Mach 0.39 0.61 0.69 0.44 1.16 0.74 0.89 0.58 0.01
El-mach 0.38 0.77 2.75

0.18 1.20 1.85

0.43 1.75

0.94
Cell entries are the values of the test statistic;

,

and

denote the 99%, 95% and 90% levels of significance, respectively; and the squared
loss function is used to calculate the DieboldMariano test statistic. All results are reported in comparison with the SYS results: a negative number
indicates superior performance of the SYS, a positive number indicates superior performance of the competing model. For model and industry
details, see the notes of Tables 1 and 3, respectively.
Table 5
Root mean-squared errors (RMSEs) for United Kingdom
Industry Monthly rolling forecasts
VARMA SYS VAR1 VAR2 VARMA SYS VAR1 VAR2 VARMA SYS VAR1 VAR2
One month ahead Two months ahead Three months ahead
Tobacco 14.03 13.56 16.57 18.66 13.44 13.59 15.30 18.14 13.24 13.61 15.45 18.01
Pulp 29.34 28.56 29.89 30.09 29.21 29.61 30.34 30.55 30.27 32.45 32.02 32.74
Wood 7.10 8.34 9.06 8.96 8.08 7.96 9.21 9.12 8.28 7.97 8.76 8.64
Metal 17.94 18.07 19.62 19.63 17.80 18.32 19.42 18.88 18.15 18.37 20.27 18.26
Chemical 2.87 2.79 3.08 3.58 2.82 2.84 3.06 2.94 3.23 2.89 3.24 3.20
Org-chem 13.05 13.60 14.21 14.72 14.33 13.82 14.50 14.09 13.15 13.93 15.67 14.66
Medi. 13.29 14.43 15.19 16.48 13.29 14.48 15.97 15.23 13.34 14.51 16.08 15.10
Plastics 17.67 20.04 19.47 17.15 19.59 21.91 22.22 18.26 21.82 21.43 24.25 19.65
Tex-fabs 2.26 2.31 2.34 2.68 2.33 2.18 2.37 2.55 2.20 2.18 2.45 2.60
Iron 12.91 13.00 12.17 14.09 13.80 13.78 14.50 15.08 14.16 13.83 15.31 15.47
Nonfme 25.81 25.94 28.01 26.57 25.98 24.99 28.47 26.96 26.23 24.88 28.20 26.37
Mach 1.77 1.67 2.10 2.12 1.78 1.67 2.20 2.12 1.69 1.67 2.09 1.99
El-mach 2.82 2.55 2.59 3.27 2.72 2.39 2.55 3.19 2.48 2.41 2.49 2.96
For model and industry details, see the notes of Tables 1 and 3, respectively.
146 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
The use of the DieboldMariano test for comparing the
forecasting models is appropriate in our context, but the
small evaluation sample we use may not provide
trusted inferences. A casual look at the corresponding
tables reveals that our system mostly performs
significantly better than the competing VAR models,
while it is on a par with the competing VARMA model.
There is no doubt that we would have preferred to have
had our system also outperform the VARMA model in
terms of the DieboldMariano test results, and it is
quite possible that a larger evaluation sample could
have produced such a favorable outcome for our
system. Be that as it may, the weight of evidence still
favors us: the test does not indicate that the VARMA
model is better than our system (the two models are
equivalent), while our system is better in forecasting
the direction of inflation (results not reported here) and
very frequently has smaller RMSE values.
What do these results say about the usefulness of our
approach? From a purely forecasting point of view, we
find that our restricted VARX model does provide
RMSE forecasting improvements over the unrestricted
VARmodels of, either Eq. (5) or Eq. (9), while it is on a
par with the VARMA model of Eq. (10). This result on
its own would be additional evidence on the ability of
low-order, parsimoniously specified time series models
to forecast well. However, taking the economic
arguments and the choice of evaluation measure into
account provides us with a different result. A properly
specified system that incorporates restrictions from
economic theory produces RMSE forecasts that are as
good as or better than those of a properly specified,
atheoretic time series model; such a system should be
of use to any practitioner that works in forecasting
industry-level inflation. Also, as noted at the end of
Section 3.1, one can use our system for preparing
Table 8
DieboldMariano tests using squared loss function for the United States (CPI-based models)
Industry Monthly rolling forecasts
VARMA VAR1 VAR2 VARMA VAR1 VAR2 VARMA VAR1 VAR2
One month ahead Two months ahead Three months ahead
Mfl 1.12 0.65 1.51

0.06 1.35 1.98

0.58 1.76

2.23

Food 0.94 2.79

3.76

0.18 2.53

4.81

1.81

2.47

4.67

Appa 2.51

3.29

4.19

4.65

3.15

3.74

0.83 4.58

6.20

Cell entries are the values of the test statistic;

,

and

denote the 99%, 95% and 90% levels of significance, respectively; and the squared
loss function is used to calculate the DieboldMariano test statistic. All results are reported in comparison with the SYS results: a negative number
indicates superior performance of the SYS, a positive number indicates superior performance of the competing model. For industry and model
details, see the notes of Table 7.
Table 7
Root mean-squared errors (RMSEs) for the United States (CPI-based models)
Industry Monthly rolling forecasts
VARMA SYS VAR1 VAR2 VARMA SYS VAR1 VAR2 VARMA SYS VAR1 VAR2
One month ahead Two months ahead Three months ahead
Mfl 38.96 58.41 54.38 74.35 46.19 56.14 62.67 78.43 45.10 56.01 63.58 81.93
Food 1.05 1.92 2.71 3.29 1.21 2.06 2.72 3.25 1.30 2.09 2.72 3.15
Appa 21.92 15.04 10.23 11.62 21.45 14.94 9.92 10.87 22.17 22.27 12.49 10.93
Cell entries are values of the RMSE; VARMA stands for a VARMA(1,1) model with the exchange rate as an endogenous variable; SYS
stands for the structural triangular system; VAR1 stands for an unrestricted VAR with the exchange rate as an endogenous variable; and VAR2
stands for an unrestricted VAR without import prices and exchange rates, including only inflation rates, interest rates and unemployment. In the
table, Mfl stands for mineral fuels, lubricants and related materials, Food stands for beverages and tobacco, and Appa stands for articles of
apparel and clothing accessories.
147 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
different forecasting scenarios based on different
assumed paths for the exchange rate. This is clearly not
possible with either the VARMA or the restricted VAR
models, where the exchange rate enters endogenously.
6. Concluding remarks
In this paper, we explore whether exchange rate pass-
through can be used to improve the forecasting
performance of models for industry-level inflation. Our
approach is based on the ideas of Obstfeld (2001, 2002)
about a two-dimensional mechanism of exchange rate
transmission to domestic prices, and requires industry-
level data and analysis. Our modeling framework is
based on the use of a generic, reduced formVARmodel,
which we test and subsequently reduce to a VARX
model, thus successfully validating and incorporating
information from economic theory. We perform various
Table 10
DieboldMariano tests using squared loss function for the United States (PPI-based models)
Industry Monthly rolling forecasts
VARMA VAR1 VAR2 VARMA VAR1 VAR2 VARMA VAR1 VAR2
One month ahead Two months ahead Three months ahead
Meat 0.19 1.75

2.13

0.79 1.54

2.11

0.36 1.37 1.52

Fruit 0.10 3.27

1.81

0.38 2.81

2.03

2.53

1.93

1.90

Beve 0.43 2.37

3.70

0.23 2.16

3.27

0.65 1.81

2.16

Chemical 1.30 0.60 0.52 0.16 1.53

0.20 1.22 0.85 0.01

Org-chem 0.95 2.07

0.23 0.45 1.74

1.01 0.17 1.53

1.40
Inor-chem 0.35 1.05 0.10 0.17 1.25 0.49 1.65

1.15 0.15
Rubber 0.26 1.89

1.86

0.41 1.96

2.21

1.10 1.72

1.66

Nm-min 1.55

2.43

4.11

1.68

1.89

3.55

0.66 1.92

3.01

Me-mach 0.58 0.68 2.28

0.42 0.30 1.77

1.29 0.03 0.67

El-mach 0.46 0.35 2.07

0.96 0.21 1.43

1.78

0.15 1.14
Furni 1.06 2.94

3.65

1.20 1.37 1.84

0.72 1.24 2.28

Cell entries are the values of the test statistic;

,

,

denote 99%, 95% and 90% levels of significance; and the squared loss function is used to
calculate the DieboldMariano test statistic. All results are reported in comparison with the SYS results: a negative number indicates superior
performance of the SYS, a positive number indicates superior performance of the competing model. For model and industry details, see the notes
of Tables 2 and 3, respectively.
Table 9
Root mean-squared errors (RMSEs) for the United States (PPI-based models)
Industry Monthly rolling forecasts
VARMA SYS VAR1 VAR2 VARMA SYS VAR1 VAR2 VARMA SYS VAR1 VAR2
One month ahead Two months ahead Three months ahead
Meat 11.86 14.54 17.13 22.54 8.39 14.55 16.79 21.14 12.33 14.54 16.10 22.70
Fruit 1.62 1.98 2.72 2.62 1.72 1.90 2.72 2.55 1.37 2.00 2.52 2.48
Beve 2.44 3.84 5.41 5.42 3.21 3.83 4.91 5.21 2.90 3.88 4.68 4.97
Chemical 5.74 5.81 6.08 5.99 4.83 5.97 6.65 5.94 5.01 6.12 6.49 5.96
Org-chem 15.93 16.14 19.68 16.67 18.02 15.72 18.05 17.65 21.70 15.97 17.84 18.23
Inor-chem 5.87 11.55 12.58 11.71 5.72 11.18 12.37 11.78 5.86 11.20 12.33 10.89
Rubber 3.69 3.23 4.07 3.32 4.34 3.25 4.00 4.10 4.00 3.14 3.93 3.84
Nm-min 2.52 2.30 3.11 2.26 2.64 2.32 2.94 3.14 2.48 2.28 2.79 2.94
Me-mach 1.16 1.96 1.94 1.74 1.38 1.88 1.94 2.28 1.17 1.90 1.86 2.11
El-mach 1.69 1.47 1.51 1.60 1.71 1.48 1.47 2.04 1.63 1.50 1.46 2.02
Furni 1.38 1.31 1.65 1.33 1.77 1.32 1.58 1.66 2.03 1.28 1.55 1.75
For model and industry details, see the notes of Tables 2 and 3, respectively.
148 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
causality and model reduction tests that support both the
underlying economic arguments and our approach. We
then proceed to compare the forecasting ability of our
proposed system with that of different competing
models, including a reduced form VAR, a VAR
augmented with other economic variables, and finally,
a VARMA model. Our comparison of forecasting
performance is based on the use of the RMSE and the
Diebold and Mariano (1995) test.
Using monthly data from three major economies
(Japan, the United Kingdom and the United States)
and thirty-four industries, we find substantive
evidence in favor of our approach. Our tests of
causality and model reduction suggest that exchange
rates are unidirectional causal for the domestic price
variables, with no feedback from them. Our compar-
ison of forecasting performance shows that our
structural system provides the best overall fore-
casting performance: based on RMSE evaluation, it
is the best or second best forecasting model for 80%
of the cases examined; based on the evaluation of the
DieboldMariano tests our system performs on a par
with the VARMA model, and very frequently
outperforms the VAR models. Specific as they are
to our dataset and context, our results suggest the
following:
Exchange rate pass-through, with its different
dynamic channels towards import and producer/
consumer prices, does improve the out-of-sample
forecasting performance of industry-level inflation.
The use of prior economic information in the
context of an appropriate model can improve the
model's forecasting performance.
Tests of causality and model reduction need not just
be descriptive in-sample devices; they can both
offer substantial support for the underlying eco-
nomic arguments and help construct a more
parsimonious and better forecasting model.
Using multiple forecast evaluation criteria should
be preferred over any single criterion for distin-
guishing between competing models, especially
when any two models are ranked close together
using a single criterion.
In a (linear) multiple time series context, one should
not neglect to benchmark one's forecasts against the
parsimonious class of VARMA models. The use of
the easier to estimate class of VAR models cannot
always capture the underlying dynamics of the time
series.
Potential extensions of our work include testing for
and using models with nonlinear features, or specify-
ing and forecasting industry-level inflation using
nonparametric transfer function models. We leave
these to future research.
Acknowledgments
An earlier version of this paper was presented at the
2004 Australasian Econometric Society Meeting in
Melbourne, Australia, and at the 23rd International
Symposium on Forecasting in Merida, Mexico, 2003.
We would like to thank the conference and symposium
participants, as well as Prasad Bidarkota, Jonathan Hill
and Luis Bernal, for useful comments and suggestions
on earlier versions of the paper. We would also like to
thank the editor, Michael Clements, an associate editor
and an anonymous referee for useful comments that
improved the content and presentation of the paper. All
remaining errors are ours.
References
Adolfson, M. (2001). Export price responses to exogenous exchange
rate movements. Economics Letters, 71, 9196.
Ball, L. (1999). Efficient rules for monetary policy. International
Finance, 2, 6383.
Boldin, M. D. (1998). A New Era for Inflation or Will Inflation Pick Up
Before This ExpansionEnds?Unpublishedpaper, Conference Board.
Campa, J. M., & Goldberg, L. S. (2005). Exchange rate pass-through
into import prices. Review of Economics and Statistics, 87,
679690.
Clements, M. P., & Hendry, D. F. (1998). Forecasting economic time
series. Cambridge, UK: Cambridge University Press.
Clements, M. P., & Mizon, G. E. (1991). Empirical analysis of
macroeconomic time series: VARand structural models. European
Economic Review, 35, 887932.
Devereux, M. B. (1997). Real exchange rates and macroecono-
mics: Evidence and theory. Canadian Journal of Economics, 30,
773808.
Diebold, F. X., & Mariano, R. S. (1995). Comparing predictive accu-
racy. Journal of Business and Economic Statistics, 13, 253263.
Engel, C. (2002). The responsiveness of consumer prices to
exchange rates and the implication for exchange-rate policy: A
survey of a few recent new open-economy macro models.
Working Paper of The National Bureau of Economic Research,
Vol. 8725.
Goldberg, L. (2004). Industry-specific exchange rates for the United
States. Federal Reserve Bank of New York Economic Policy
Review, 10, 116.
149 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150
Goldberg, P. K., & Knetter, M. M. (1997). Goods prices and
exchange rates: What have we learned? Journal of Economic
Literature, 35, 12431272.
Hendry, D. F., & Mizon, G. E. (1993). Evaluating dynamic
econometric models by encompassing the VAR. In P. C. B.
Phillips (Ed.), Models, methods and applications of economet-
rics (pp. 272300). Oxford, UK: Basil Blackwell.
Kim, K. (1998). US inflation and the dollar exchange rate: Avector
error correction model. Applied Economics, 30, 613619.
Koenig, E. F. (1998, July/August). What's new about the new
economy? Some lessons from the current expansion. Southern
Economy, Federal Reserve Bank of Dallas (pp. 711).
Krugman, P. K. (1987). Pricing to market when the exchange rate
changes. In Sven W. Arndt & J. David Richardson (Eds.), Real
financial linkages among open economies. Cambridge, Massa-
chusetts: MIT Press.
McCarthy, J. (2000). Pass-through of exchange rates and import
prices to domestic inflation in some industrialized economies. Staff
Reports of Federal Reserve Bank of New York, Vol. 111.
Obstfeld, M. (2001). International macroeconomics: Beyond the
MundellFleming model. IMF Staff Papers: Special Issue, 47,
139.
Obstfeld, M., (2002). Exchange rates and adjustment: Perspectives
from the new open economy macroeconomics. Mimeo.
Obstfeld, M., & Rogoff, K. (2000). New directions for stochastic
open economy models. Journal of International Economics, 50,
117153.
Spanos, A. (1989). Early empirical findings on the consumption,
stylized facts or fiction: A retrospective view. Oxford Economic
Papers, 41, 150169.
Spliid, H. (1983). A fast estimation method for the vector
autoregressive moving average model with exogenous va-
riables. Journal of the American Statistical Association, 78,
843849.
Taylor, J. B. (2000). Low inflation, pass-through and the pricing
power of firms. European Economic Review, 44, 13891408.
150 P.S. Bhattacharya, D.D. Thomakos / International Journal of Forecasting 24 (2008) 134150