Applied econometrics and implications for energy economics research
Russell Smyth
a,  , Paresh Kumar Narayan b,1
a
Department ofEconomics, Monash University 3800, Australia
b
School ofAccounting, Economics and Finance, Deakin University, 221 Burwood Highway, Burwood, Victoria 3125, Australia
a b s t r a c t a r t i c l e i n f o
Article history:
Received 7 April 2014
Received in revised form 18 June 2014
Accepted 29 July 2014
Available online 15 August 2014
JEL classif i cation:
Q40
Q41
Q42
Q48
Q49
Unit root
Cointegration
Granger causality
Developments inappliedeconometrics, particularlywithregard to unitroottests and cointegrationtests, have mo-
tivated a rich empirical literature on energy economics over the last decade. This study reviews recent develop-
ments in time series econometrics applications in the energy economics literature. We f i rst consider the
literature on the integration properties ofenergy variables. We begin with a discussion ofthe implications of
whether energy variables contain a unit root and proceed to examine how results differ according to the specif i c
unit root or stationarity test employed. We then proceed to examine recent developments in the literature on
cointegration, Granger causality and long-run estimates between (disaggregated) energy consumption and eco-
nomic growth. We review both single country and panel studies and pay particular attention to studies which
have expanded the literature through adding variables such as f i nancial development and trade, in addition to en-
ergy consumption to the augmented production function, as well as studies which have extended the literature
through examining disaggregated energy consumption by type. In each case we highlight best practice in the lit-
erature, point to limitations in the literature, including econometric modeling challenges, and suggest recommen-
dations for future research. A key message ofour survey is that the profession needs to guard against ‘overload’ of
research in these areas as most applied studies are no longer adding anything more to what is already known.
(c) 2014 Elsevier B.V. All rights reserved.
1. Introduction
Developments in applied econometric estimation methods have
been the catalyst for a rich body ofapplied energy economics research.
Judgingbypapers accepted, and published, in leadingenergyeconomics
journals, this trend is gaining momentum. There is a need to take stock
ofthis literature. There is a need to review whether, at least in the most
popular strands ofthe energy economics literature, greater volume of
applied work is adding anything new. If it is making new
contributions—this is welcomed, but ifit is not, then future directions
of research need to be reconsidered. This paper is a response to the
growing energy economics literature motivated by new developments
in applied econometrics. This paper not only addresses whether addi-
tional applied research is adding new insights to what is already
known in two ofthe most popular f i elds in the energy economics liter-
ature, but also offers several directions for future research, allowing the
profession to develop, and expand, upon the rich body ofliterature that
it has so successfully developed.
We focus on two specif i c strands ofthe energy economics literature
that have theirorigins in applied econometric methods. Specif i cally, our
focus is on (a) integration properties of energy variables and
(b) cointegration and Grangercausality analysis. So much growth in en-
ergy economics research has documented that a need to undertake a
stock take ofthis literature is not only timely but, hopefully, will also
guide future research in energy economics. In certain strands ofthe en-
ergy economics literature, it seems as ifapplied work is no longer mak-
ing any new contributions and throwing any new light to what is
already known (see also Karanf i l, 2009). It is this ‘overload’ ofresearch
in certain f i elds against which the literature needs to guard.
Our review ofthe literature suggests two messages, which have im-
portant implications for existing and future research in energy econom-
ics based on new developments in applied econometrics. First, there is
largelya consensus in the unit root literature that mostenergytype var-
iables are stationary if tests utilize suff i ciently large time-series data.
This is conf i rmed by panel data models that examine the same unit
root null hypothesis. Because panel data models have the advantage of
having more power to reject the null hypothesis—a power gain that re-
sults from pooling oftime-series components ofa panel with its cross-
section—almost all panel data unit root models with structural breaks
reveal clear evidence that energy variables are stationary. It is impera-
tive to assign greater weight to panel data models ofunit root tests, as
opposed to time-series models, because unit root models function par-
simoniously when they are imposed on large sample sizes. Typically
most energy type variables will have 30–40 years of annual data,
which, particularly when the literature uses the relatively more popular
structural break unit root models, is insuff i cient for unit root models to
function precisely. Panel data models are a perfect response to this
Energy Economics 50 (2015) 351–358
Corresponding author. Tel.: +61 3 99051560; fax: +61 3 9905 5476.
E-mail addresses: russell.smyth@monash.edu (R. Smyth),
paresh.narayan@deakin.edu.au (P.K. Narayan).
1
Tel.: +61 3 9244 6180; fax: +61 3 9244 6034.
Keywords:
http://dx.doi.org/10.1016/j.eneco.2014.07.023
0140-9883/(c) 2014 Elsevier B.V. All rights reserved.
Contents lists available at ScienceDirect
Energy Economics
journ al homepage: www. el sevier. com/l ocate/eneco