Working Paper 02-27 Departamento de Economía

Economics Series 08 Universidad Carlos III de Madrid

June 2002 Calle Madrid, 126
28903 Getafe (Spain)
Fax (34) 91 624 98 75

MODELING ELECTRICITY PRICES: INTERNATIONAL EVIDENCE *

Álvaro Escribano1 , Juan Ignacio Peña2 and Pablo Villaplana 3

Abstract
This paper analyses the evolution of electricity prices in deregulated markets. We present a
general model that simultaneously takes into account the possibility of several factors:
seasonality, mean reversion, GARCH behaviour and time-dependent jumps. The model is applied
to equilibrium spot prices of electricity markets from Argentina, Australia (Victoria), New
Zealand (Hayward), NordPool (Scandinavia), Spain and U.S. (PJM) using daily data. Six different
nested models were estimated to compare the relative importance of each factor and their
interactions. We obtained that electricity prices are mean-reverting with strong volatility
(GARCH) and jumps of time-dependent intensity even after adjusting for seasonality. We also
provide a detailed unit root analysis of electricity prices against mean reversion, in the presence of
jumps and GARCH errors, and propose a new powerful procedure based on bootstrap techniques.

Keywords: electricity prices, seasonality, mean reversion, GARCH, jumps, unit root test,
bootstrap.

JEL Clasification: C22, L94, L9 and G10

1
Departamento de Economía, Universidad Carlos III de Madrid, Spain; E.mail:
[email protected]
2
Departamento de Economía de la Empresa, Universidad Carlos III de Madrid, Spain; E.mail:
[email protected]
3
Departamento Economía de la Empresa, Universidad Carlos III de Madrid, Spain; E.mail:
[email protected]

* The authors are grateful to the comments received on the first version of this paper from Angel
Leon, Craig Pirrong, Cristopher R. Knittel, Michael Roberts and the participants at the I
Workshop in Electricity Derivatives (Valencia, Spain), IX Foro Finanzas (Pamplona, Spain), EFA
(Berlin) and EARIE (Madrid). We acknowledge financial support provided by DGYCIT grant
PB98-0030. P. Villaplana also acknowledges financial support provided by Energy Economics
Laboratory, of the Universidad Carlos III de Madrid.
 1. INTRODUCTION
Until early 90’s the electricity sector has been a vertically integrated industry, where regulators fixed
prices as a function of generation, transmission and distribution costs and therefore there was little
uncertainty in prices. In last years electricity markets in many countries are experiencing a deregulation
process, with the aim of introducing competition in generation and supply activities (not in transmission and
distribution since they are considered natural monopolies). One of the main consequences of this reform is
that prices are determined by the interaction between supply (generators) and demand (suppliers, who are
agents that buy energy and sell it to the consumers) in what is usually called a “pool”. In this context
generators compete to sell electricity in the market pool while the suppliers to consumers purchase electricity
from the pool at equilibrium prices set by the intersection of aggregated demand and supply on an hourly (or
half-hourly) basis. These new deregulated prices have been characterized in all the markets by having an
extremely high volatility. Even when compared with financial markets (stock, bonds) or with other
commodities, the behavior of electricity prices is still regarded as quite complex and volatile. The
deregulation has introduced new elements of uncertainty in the sector and therefore usual financial aspects
like financial risk management, derivative contracts, or hedging are being introduced in the industry. In fact
the more experienced markets now include futures and options markets (for instance, electricity futures
contracts are traded in different markets, Sidney Futures Exchange, New Zealand Futures and Options
Exchange, Eltermin (Scandinavia), NYMEX and others). There is an extensive literature on the deregulation
effects of electricity markets from a regulatory and industrial organization point of view. For an introduction
to the analysis of competition in electricity markets, see for instance, Wolak(1997), Hogan (1998),
Borenstein (2001) and references therein.
The characterization and understanding of the behavior of electricity prices is a necessary task and is the
basis for the valuation and risk management of real assets and financial claims on the commodity. Some
initial recent contributions are Johnson and Barz (1999), Bhanot (2000), Lucia and Schwartz (2002) and
Knittel and Roberts (2001).
We extend this literature by proposing and estimating a general and flexible model and applying it to a
comprehensive set of markets, Argentina, NordPool, Australia (Victoria), New Zealand (Hayward), US
(Pennsylvania -New Jersey-Maryland, PJM hereafter) and Spain. This will allow us to compare the different
behavior observed in deregulated markets and quantify the role of different characteristics (importance of
seasonality, mean-reversion, volatility and/or jumps) in each individual market. Our goal is to propose a
general (benchmark) model that encompasses the main features present in all markets.
One of the main innovations of this paper is the estimation of a general and flexible model to a
comprehensive set of markets. That is, we take into account the interaction between jumps and GARCH
behavior, and among jumps, GARCH and mean reversion. Our results stress the importance of including
those three elements simultaneously in order to isolate the main elements of the behavior of electricity prices
in deregulated markets. The other main contribution is the proposal and application of a new unit root testing
strategy in the presence of jumps and volatility. Although we focus on equilibrium prices from electricity

3
markets, this modeling strategy could also be applied to other commodity prices like for instance, natural
gas.
The paper is organized as follows. Section 2 describes the main characteristic factors of electricity prices and
discuss some related literature. Section 3 presents the model and the econometric methodology. Section 4
describes our data sets and presents some descriptive statistics. Section 5 presents the empirical results from
the estimated models. Section 6 applies a variety of unit root tests for the null hypothesis of a unit root
against the alternative of mean reversion. Finally, section 7 includes some conclusions and provides some
insights for future risk management research based on our empirical findings.

2. ELECTRICITY PRICE BEHAVIOR AND RELATED LITERATURE

2.1. Why are electricity prices so volatile?
There are several elements that explain the observed high volatility of electricity prices. Probably the
most important one is the non-storability of electricity. Electricity cannot be physically stored in a direct way
(electricity can be indirectly stored via hydroelectric schemes or via storage of generator fuel), and
production and consumption have to be continuously balanced. Therefore, supply and demand shocks cannot
easily be smoothed out and they will have a direct effect on equilibrium prices.
The characteristics of demand and supply play also an important role in the observed volatility. Electricity
demand is highly inelastic because it is a necessary commodity and also highly weather-dependent. The
characteristics of the supply stack of each market can also contribute to the volatility of a particular demand.
Pool’s prices are determined by the intersection between demand and supply. For low levels of demand,
generators supply electricity by using base-load units with low marginal costs, as higher quantities are
needed new generators with higher marginal costs enter into the system. The relative insensitivity of demand
to price fluctuations and the binding constraints supply can face at peak times, makes short-term prices for
electricit y extremely volatile. Therefore, in markets where both the demand and supply curves are steep we
could observe sharp increases in prices as the quantity demanded is increased. Moreover, depending on the
structure of the market and the market power of the generators, for high levels of demand only few
generators could satisfy the residual demand and therefore market power could come into play through
monopolistic or oligopolistic behaviors of generators.
2.2. Characteristics of electricity prices
The model we propose is very flexible and allow us to simultaneously include seasonality, mean
reversion, volatility and jumps. The main goal of this paper is to show that this general model captures the
salient idiosyncratic features of electricity prices. As we will see later on in sections 4 and 5, there is enough
empirical evidence in the data to include the four characteristics simultaneously.
2.2.1. Seasonality
Electricity demand is heavily influenced by economic and business activities and by the weather
conditions. These two factors explain the main seasonal behavior of electricity prices. Different kinds of
seasonality appear in the data; intra-daily, weekly and monthly seasonality. As it is usual in this literature, we
assume that seasonality is generated by deterministic factors and since we use the average daily prices, we

4
will only consider weekly and monthly seasonality. In particular, the seasonality is captured by means of two
deterministic seasonal functions: a) weekly seasonality, captured by means of daily dummies and b) monthly
seasonality, captured by either monthly dummies or by a sinusoidal functions.
The importance of deterministic regular patterns in the behavior of electricity prices has been analyzed by
Lucia and Schwartz (2002) and by Bhanot (2000). Lucia and Schwartz (2002) propose and estimate a one
and two-factor mean reverting models with deterministic seasonality for the Scandinavian market
(NordPool), showing that the seasonal pattern in spot electricity prices could explain part of the shape of the
observed term structure of futures prices. Bhanot (2000) analyses electric power prices using data from 12
regional markets from the US focusing in the mean-reverting and seasonal behavior of the series and on the
possible regional differences among them.
2.2.2. Mean-reversion
Since shifts in demand will push prices up, increasing the economic incentives of more expensive
generators to enter in the supply side (shift in supply) of the system, it seems natural to expect some degree
of mean reversion in the evolution of electricity prices. On the other hand, it could also be argued that prices
are mean-reverting because weather is a dominant factor which influences equilibrium prices through
changes in demand. Since the evolution of weather is a cyclical and mean-reverting process, this tendency to
revert to its mean level (maybe time-varying) will affect demand and therefore also equilibrium prices
(Knittel and Roberts 2001). Although the great majority of models have been proposed up to now are mean-
reverting models, for instance, Bhanot (2000), Karesen and Husby (2000), Lucia and Schwartz (2002) and
Knittel and Roberts (2001) there are also some recent papers that characterize electricity prices as non-mean
reverting, see for example De Vany and Walls (1999) and Leon and Rubia (2001). Furthermore, Johnson and
Barz (1999) analyzed the fit of mean-reverting and non-mean reverting models with and without jumps to a
set of deregulated markets. They found that the best fit was obtained by a mean-reverting model with jumps.
However they did not provide any formal test (unit roots, etc.) nor considered the possibility of non-constant
volatility (GARCH, etc.). In this paper we solve those limitations in two ways: a) extending the analysis to
electric ity markets for other countries and b) suggesting a new formal procedure to tests for the unit root
hypothesis against the alternative of mean-reversion in the presence of GARCH and Jumps in the data.
2.2.3. Jumps and volatility
By simple eye inspection (a formal econometric analysis will be done in Section 5) of the graphs
presented in Figures 1 to 6 of the appendix, it is clear the existence of important jumps in the behavior of
electricity prices.
One of the characteristics of evolution of these jumps is that the price does not stay in the new level, to
which it jumps, but reverts to the previous level rapidly. This behavior can be captured by introducing a
Poisson process as in a jump-diffusion model. There are already some applications of jump-diffusions to
electricity prices. Johnson and Barz (1999) estimate various jump-diffusion process to several electricity
price series, Knittel and Roberts (2001) also estimate a jump diffusion model (with time dependent jump
intensity) to California prices. In spite of the advantages of introducing jumps in the model there are some
limitations in modelling electricity prices by jump-diffusion processes (see e.g. Pirrong and Jermakyan 1999

5
and Clewlow and Strickland 2000). The main criticism is the assumption that all the shocks affecting the
series die out at the same rate. Simple economic intuition would argue that this is not a likely case. For larger
shocks it seems evident that forces of demand and supply will push back electricity prices quite fast. On the
other hand, when shocks are smaller it is more likely that prices will revert slowly to the previous level due
to the existence of adjustment costs. In statistical terms, modeling the series by a jump diffusion process has
its own limitations. When estimating the jump-diffusion process by (Quasi) Maximum Likelihood the
estimated model tend to capture the smallest and more frequents jumps in the data. Furthermore, the jump-
diffusion modeling approach does not capture the fact that jumps will probably appear in those periods
where the difference between the maximum supply and the demand is not very big (small excess capacity). If
the supply stack is convex (increasing marginal costs) during periods of high demand, the effect on prices,
for a given increase in demand (shift of the demand curve to right), will be greater the smaller is the excess
capacity. Our flexible modeling approach solves those limitations.
Another important aspects of electricity prices is the existence of high volatility and volatility clustering.
One of the most popular approaches for modeling conditional volatility is the GARCH model and its
extensions. Although there is some work on applying models of the ARCH family to electricity prices there
are problems with the usual modeling approach. For an application of different types of ARCH or GARCH
models to energy prices see Duffie et al. (1998) and Knittel and Roberts (2001). Duffie et al. (1998) showed
that the application of these kind of models to electricity prices has its limitations, because one can end with
an integrated volatility process, which is not a very appealing result. One of the reasons for the possibility of
explosive volatility is the presence of outliers (spikes) in the data, biasing the estimation of the GARCH
process. This bias of GARCH coefficients in the presence of jumps has also been obtained in other financial
applications, see for instance the application of jump-diffusions to exchange rates belonging to the ERM,
Neely (1999). Other papers that analyze the effects of outliers (jumps) on GARCH models with applications
to stock data are Carnero, Peña and Ruiz (2001), Hotta and Tsay (1998) and Verhoeven and McAleer (2000).
Our results show that one can improve both jump-diffusion models and GARCH models by working with a
model that simultaneously takes into account both characteristics. We show that both modeling approaches
are complementary and not substitutes. It is remarkable that once we allow for jumps in the GARCH models
we recover the desired stationarity of the volatility process. On the other hand, by allowing a GARCH
behavior in the jump-diffusion process we find a decreasing probability of observing a jump since part of the
smaller jumps that were previously captured by the pure jump model are now part of the GARCH
component.
Furthermore, we allow for non-constant jump intensities. We have seen that the technological characteristics
of electricity markets, like increasing marginal costs in the supply stack, increase the probability of observing
higher jumps when demand is high (high rate of capacity utilization), see for instance Birnbaum et al. (2002).
However, we also observe jumps in electricity prices even when demand is not very high. This is in general
due to transmission problems or because certain plants cannot generate electricity. In those situations, the
decrease (shift to the left) in supply and not the increase in demand, is the alternative main source of jumps
of equilibrium prices. For illustrative purposes and data limitations, we have decided to model the time

6
varying specification of the jump intensity by introducing different dummies per season. These dummies are
proxies for the demand variable that is one of the main sources of observed jumps. It is worth noting the
flexibility of our model allowing for simultaneous modeling of intensity of the jump process and volatility
(GARCH).

3. MODEL SPECIFICATION AND ESTIMATION

We have seen in previous section that a reasonable model for electricity prices should allow for the
existence of deterministic seasonality, the possibility of mean-reversion, jumps and (stochastic) volatility.
Therefore we propose a model that simultaneously incorporates all these factors in an flexible way. In
particular, our general model takes into account the possibility of seasonality (deterministic), mean-
reversion, volatility (GARCH behavior) and jumps (with the possibility of time-dependent intensity).
Moreover we can test for the significance of each of these factors, estimating six different nested models for
each of the analyzed markets.
We present the model in continuous and discrete time. Since this paper is devoted to the analysis of the data
generating process of equilibrium spot electricity prices, we work with the discrete time version of the
model. But since most financial questions (for instance valuation and hedging) are usually addressed in
continuous time we first present the model in its continuous time version.
The model in continuous time is 1 :
Pt = f(t) + Xt (1)
dXt = -κ Xt dt + vt 1/2 dZ + J(µJ ,σJ) d∏(λt ) (2)
dvt = k v (θv – vt )dt + v t1/2 σ dZv (3)
where Pt is the equilibrium spot electricity price of electricity markets, f(t) is a deterministic seasonal
function that captures the seasonality observed in electricity prices (captured either by monthly dummy
variables or by sinusoidal functions), dZ and dZv are independent Wiener processes, d∏(λt ) is a Poisson
distributed random variable with (time-dependent) intensity λt , and J(µJ ,σJ) is a random variable normally
distributed with mean µJ and standard deviation σJ. vt captures the evolution of the stochastic volatility. We
assume that the Wiener processes, the Poisson process and the jump size are mutually independent
processes.
Continuous-time models are the basis for a wide range of proble ms in finance and are usually hard to
estimate. The estimation methods for continuous-time models are computationally intensive in practice and
they are specially difficult to estimate in the context of time dependent intensities. A popular approach has
been discretization (for instance using the Euler approximation). It is well known that discretization of
continuous-time stochastic differential equations does introduce an estimation bias. However, the bias is
smaller the shorter the sampling interval. Wit h daily data this bias is negligible (see Bergstrom 1988, Melino
1994 and Das 2001).

1
Notice that we are dealing with equilibrium electricity prices. The data we use is the average price. We have decided
not to take logarithms since this transformation would tend to eliminate right skewness and outliers. In our case right
skewness and outliers are explicitly modelled as part of the main sources of uncertainty.

7
The goal of this paper is to disentangle the possible components that are present in electricity prices series
and therefore, we have decided to work with a discrete time version of model (1)-(3) for two reasons: a) the
estimation bias with daily data is negligible and b) we have greater flexibility with discrete time models.
The general discrete time model we estimate is:

Pt = f(t) + Xt (4)

φ· Xt-1 +ht ½ε1t ; prob. 1- λt

Xt = (5)
φ· Xt-1 +ht ½ε1t +µJ+σJ· ε2t ; prob. λt

h t =ω + α· ε2t-1 + β· ht-1 (6)

λt =L1· wintert +L2· fallt +L3· springt +L4· summert (7)

where ε1t and, ε2t ~ i.i.d. N(0,1). The parameter φ describes the degree of mean-reversion, if |φ| <1, then Pt
reverts back to its (non-constant) mean. The parameter φ in (5) stands for (1-κ) in (2), so a low mean
reversion, low κ is equivalent to φ ≈ 1. The (nonnegative) parameters ω, α and β characterize the dynamics
of the volatility following a GARCH(1,1) process (ω > 0; α , β ≥0). The nonegativity restrictions are needed
to guarantee that the conditional variance is positive and also ω has to be strictly positive for the process not
to degenerate. If α + β <1, then the variance reverts back to its unconditional mean σ 2 = ω / (1- α - β).
The equation (7) models the time-dependent intensity process for the jumps by means of three dummies;
wintert is a dummy variable that takes value 1 if the observation is in December, January and February and
zero otherwise; fallt takes value 1 if the observation is in September, October or November and zero
otherwise; spring t takes value 1 if the observation is in March, April or May and zero otherwise and finally
summert takes value 1 if the observation is in June, July or August and zero otherwise.
The deterministic seasonality is specified either by monthly dummy variables or by sinusoidal functions.
However, for space reasons and to avoid a tedious reading, we only provide the results of the sinusoidal
specification since the results are very similar with both specifications. In particular, with sinusoidal
functions the seasonal factor is specified as:

f(t) = B0 + B2· t + C1· sin(t+C2)· (2π/365)) + C3· sin((t+C4)· (4π/365)) + D1· wkdt (8)

where wkdt is a dummy variable that takes value 1 if the observation is in weekday and zero otherwise
(weekend). With this general formulation for the sinusoidal function we allow for the possibility of having
two cycles per year (two local maximum per year). In the case of one annual cycle we should have C3 = C4
= 0.

8
By comparing different restricted versions of model (4)-(8) we are able to check which kind of model better
explains the evolutio n of electricity prices. Since the proposed model is quite flexible we should be able to
explain equilibrium electricity prices with higher or lower levels of kurtosis, greater or smaller relative
importance of spikes, etc.
The simultaneous modeling of GARCH and jump components in electricity markets is an important
extension. The question of whether jump processes or stochastic volatility better describe the evolution of
prices giving the observed kurtosis has produced and ongoing debate in financial modeling (Das and
Sundaram 1997, Das 2001). The sampling interval used in empirical applications also has its role in
deciding which approach must be followed. See the discussion and the test statistic proposed by Das (2001)
to decide between stochastic volatility and jumps. Our results show that both sources of uncertainty are
complementary rather than substitutes, although the relative contribution of each component is different in
each market.
The set of parameters is Θ = {f(t), φ, σ 2 ,ω, α, β, µ J,σJ 2, λt } is estimated by Maximum Likelihood
(ML). Estimation of Θ involves the following maximization:

Max Θ Σ Tt=1 ( log ( f [p t | p t –1 ] ) ) (9)

Contingent on the particular nested specification considered some parameters from equation (10) will be set
equal to zero. Now, consider that the transition probabilities for electricity equilibrium prices follows a
Poisson-Gaussian process. That is,

 − ( p t − f (t ) − φ ⋅ p t −1 − µJ )2 
f [ pt | p t −1 ] = λt ⋅ exp 
1
 (
2 ht + σJ2 ) 
 2π (ht + σ J2 )
(10)
 − ( pt − f (t ) − φ ⋅ pt −1 )  1
2
+ (1 − λt ) ⋅ exp   .
 2 ht  2πht
Equation (10) approximates the true Poisson-Gaussia n density with a mixture of normal distributions. Other
Poisson-Gaussian models could have been considered as was done in the context of exchange rates and
interest rates. However, previous evidence shows that the mixture approximation leads to similar results and
is much easier to estimate. For some applications to exchange rates see, Vlaar and Palm (1993), Nieuwland,
Verschoor and Wolff (1994) and Neely (1999), and Das (2001) for interest rates.
In order to compare different processes for electricity prices we estimate six nested models on our
international data set. For expository reasons, we have included the explicit formula of each model in
Appendix B. The six models we estimate are: a pure-Gaussian model with constant variance and without
jumps (Model 1); a GARCH(1,1)-Gaussian model without jumps (Model 2), a Poisson-Gaussian models
with constant variance (Model 3), a Poisson-Gaussian models with time-varying intensity for jumps (Model
3b), a GARCH(1,1)-Poisson-Gaussian model with constant intensity (Model 4) and the most general model
is a GARCH(1,1)-Poisson-Gaussian model with time-varying intensity for jumps (Model 4b). All of the
models have been estimated by maximum likelihood using RATS 2.5. The parameters estimates were

9
obtained using Berndt, Hall, Hall and Hausman (1974) algorithm. Reported results are robust to different
starting values.

4. DATA AND DESCRIPTIVE ANALYSIS

4.1 Data
The electricity markets analyzed in this paper are: NordPool (Scandinavia), Argentina, Australia
(Victoria), New Zeala nd (Hayward), PJM and Spain. We work with daily averages of electricity spot prices
(on-peak and off-peak hours), so we have one price for each day. All the series are expressed in the local
currency of the market. Data has been obtained from each of the pools. The sample period available is
different in each international market2 .
4.2 Descriptive statistics.
We present in Appendix A, a table (Table 1) with descriptive statistics for each of the five series. We
may observe that price series are quite volatile, have positive skewness and high kurtosis. We may also see
that although all of them share these characteristics there exist some differences among them. As was pointed
out by Wolak (1997), the generation mix (supply stack) of each market will translate into the behavior of
observed spot prices. In particular in Argentina and in Australia electricity is mainly generated by fossil fuel
technology, while in New Zealand and NordPool electricity is mainly generated by hydroelectric sources.
Therefore as seen in Table 1, the prices in the NordPool and New Zealand markets are less volatile than
prices in Australia, Argentina and PJM. In fact we observe from the graphs of Victoria, Argentina and PJM
equilibrium prices that spikes are quite important.
Wolak (1997) also pointed out the effect that regulation and market microstructure rules have on the
behavior of electricity prices. Those effects are also crucial to understand the behavior of equilibrium
electricity prices in Spain, see Federico and Whitmore (1999) and Fabra and Toro (2001). The differences
between markets should, and in fact do, translate to the estimation results. For instance, as we have
commented previously, those series with higher coefficient of kurtosis, tend to have in the GARCH(1,1)
model a higher estimated persistence. As we said above, GARCH models usually tend to introduce high
persistence in the estimation in order to be able to generate a high degree of kurtosis. On the other hand, the
degree of skewness translates in the estimated mean jump size. It can be shown that the mixture model
generates higher skewness the bigger the mean jump size.
From the summary statistics of Table 1 and from the graphs of the price series we may see that the
behavior of electricity prices in each market is quite different. This fact provides evidence on the high degree
of regionalism of deregulated electricity markets. The existence of differences among market (for instance
because differences in the type of generation, proportion of electricity generated by hydro, coal, gas or
nuclear plants) supports the idea that we should approach the analysis of each market with a general flexible
model, and that we should let data determine which are the most important idiosyncratic features of a given
market.

2
However, the bests models were re-estimated during common periods with similar results obtained. For consistency
and efficiency reasons of the estimates we report the results obtained from the longest possible samples of each
international market.

10
 5. RESULTS
In this section we highlight the main empirical results obtained, see Appendix B (Tables B.1 to B.6).
Six models were estimated to each of the average daily prices of the five international markets in order to
estimate the relative contribution of each of the main four temporal characteristics of electricity prices:
seasonality, mean-reversion, non-constant volatility (GARCH) and jumps.
The selection between the two ways we model seasonality in electricity prices, monthly dummies or
sinusoidal functions, is less relevant the more regular the seasonal pattern is. Dummy variables are more
sensitive to the presence of jumps and they could in principle provide a higher modeling flexibility.
However, since our empirical results are very similar with both pr ocedures, we only report the results
obtained with the sinusoidal function.
The mean-reverting property of electricity prices seems clear from the plots, see Figures 1 to 6, or from the
estimated models, see Appendix B. In all the models estimated, the autoregressive coefficient φ is positive
and smaller than 1. Only in the NordPool the estimated coefficient is close to 1 indicating a slow mean-
reversion. For example in Model 1 of Table B.1, φ = 0.93.
The low degree of mean-reversion observed in NordPool can be explained by the fact that in the
Scandinavian market, electricity is mainly generated by hydro resources. Hydro reservoirs play the role of
indirect storage of electricity, therefore in these type of markets we could expect more inter-temporal
substitution between inputs than in markets with a low proportion of electricity generated by water. In
markets with no inter-temporal substitution we should observe a higher degree of mean-reversion since
generators cannot use inventories to smooth out shocks , and the degree of mean-reversion in electricity
prices is mainly driven by the mean-reversion in demand or in temperature. On the contrary, New Zealand
power generation is also driven by hydro resources and it has a high degree of mean-reversion. Wolak (1997)
pointed out the fact that in markets dominated by hydroelectric power, average prices are less stable. This
instability of mean prices is clearly observed in the NordPool case. For example, the fact that 1996 was a dry
year, created a high mean level of prices during that year, see also Lucia and Schwartz (2002).
This kind of weather instability reduces the estimated degree of mean-reversion in prices, generating a
dynamic behavior in prices that is approximated by a unit root process with autoregressive conditional
heteroskedastic errors. By comparing the estimated autoregressive coefficient (φ) of model 1 with models 2
to 4 we provide direct evidence on the effects of outliers and GARCH behavior on the unit root hypothesis.
In particular, in the NordPool case when we include GARCH and jumps in the model, we clearly see that the
mean reversion property becomes more apparent reducing the estimated value of φ from 0.93 to 0.8. A
formal unit root analysis against mean-reversion alternatives will be considered in section 6.
The summary statistics of Appendix A and also the price plots of Figure 1 to 6 provide clear evidence on the
volatility of electricity prices and in particular the non-constant and the clustering of the volatility. A well-
known cause of leptokurtosis in the unconditional distribution is conditional heterocedasticity, which
supports the need to move beyond a simple constant variance Gaussian model. As expected, we obtain that
Model 2 (that incorporates a GARCH(1,1) component) gives an important improvement in goodness of fit

11
with respect to the constant variance of Model 1 in all of the five international markets analyzed. One
important aspect of most electricity markets is that the empirical parameter estimates of the GARCH(1,1)
models imply that the volatility process is explosive, i.e. α + β > 1, Bollerslev (1986). A common finding is
that GARCH models tend to impute a high degree of persistence (quantified by α + β) to the conditional
volatility, generating a conditional variance process which is not covariance-stationary. Furthermore, since
the jth period ahead forecast of the conditional variance is given by:

( )
E (ht + j ) = σ 2 + (α + β) ht − σ 2 , for j ≥ 1
j
(11)

when α + β = 1, shocks to the conditional variance accumulate and therefore are highly persistent, in the

sense that E (ht + j | ht ) → ∞ as j → ∞ see Nelson (1990), and when α + β > 1the volatility forecast is

explosive. It is clear that the explosive volatility forecast characteristic of electricity markets is not an
appealing result since the predictions of the model are meaningless and create difficulties to do any possible
risk management analysis based on prices from electricity markets.
In particular, this empirical result is obtained in Argentina, Australia and PJM electricity markets
where the estimated GARCH have α + β > 1. This property could have been anticipated since there is a high
degree of kurtosis of electricity prices. The close relationship between the degree of kurtosis generated by a
GARCH(1,1) process and the value of α + β is well known, see for instance Carnero, et al. (2002). In the
GARCH(1,1) processes the measure of persistence of volatility shocks is also given by the sum of the
coefficients α and β. The high degree of persistence in empirical applications could therefore be due to the
existence of a GARCH(1,1) process with high degree of kurtosis, which forces the sum of GARCH
coefficients to be close to one.
Two factors have been pointed out to explain the high persistence estimated in GARCH process: the
existence of outliers (Carnero et al., 2001; Hotta and Tsay, 1998; Verhoeven and McAleer, 2000) or the
existence of level shifts in the variance process (Lamoreaux and Lastrapes, 1993).
For our purpose, the main factor is the existence of important price spikes in electricity markets (outliers)
that could affect the parameter estimates of the volatility process. Observe for example, that the estimated
value of the parameter α in Model 2 is always larger than that estimated value in Model 4 that allows for
both GARCH(1,1) and jumps. This difference is even bigger for the cases of Argentina, Australia and PJM.
Notice that the parameter α may increase due to the existence of occasional periods of high volatility but
with low persistence. As we may see from Figures 1 to 6, the huge increases in prices that exist during a
short period of time (few days) clearly appear in the electricity price series of Argentina, Australia and PJM
markets.
Another alternative specification, when moving beyond the simple constant variance model, is to allow for
jumps, see Model 3 of Appendix B. Observe that in the six electricity markets, there is an improvement in
goodness of fit when moving from Model 1 to Model 3. The parameters corresponding to the jump process
(λ, µJ, σ J) are all statistically significant in all the markets. Only in the New Zealand market, µJ is not
statistically different from zero, which means that the AVERAGE jump size is nearly zero. However, this
does not imply jump process is not important to understand behavior of electricity prices. We can check the

12
improvement when modeling jumps with either the value of the log-likelihood function (Schwarz
Information Criterion) or by a Likelihood Ratio tests which are provided in Table B.7 of Appendix B.
Furthermore, we also have estimated Model 3b, in order to take into account for probability of observing a
jump not to be constant through time. In particular in Model 3b, λ is a function of seasonal dummies (one per
season), see Appendix B for the particular parameterization used.
Our results confirm our intuition that the probability of observing jumps is not constant. From this result we
should expect to have a time varying jump risk premium in futures prices. An interesting topic for future
research is to analyze which of the following variables: demand, hydro reservoir, etc. should explicitly be
included in the model in order to identify the fundamentals behind the observed jumps in electricity prices.
Going one step further, we could also study how futures markets prices jump risk.
By doing pair-wise comparisons of log-likelihoods between nested models based on Likelihood Ratio Test,
see Table 7 in Appendix B, we conclude GARCH-Poisson-Gaussian model outperforms: the constant
volatility model (Model 1), the GARCH model (Model 2), the pure jump model (Model 3 and 3b) in all of
the electricity markets but Spain (Spain is different!). (The oligopoly modeling approach of Fabra and Toro
(2001) of the Spanish electricity market, is informative about the particular microstructure characteristic of
the market which together with the particular rules for compensating the generators for the costs incurred in
the transition to competition (CTC), make the Spanish market to evolve differently).
We therefore conclude that both sources of uncertainty, stochastic volatility and discrete jumps, are useful in
explaining the volatility clustering, the skewness and the excess kurtosis observed in most of the electricity
markets.
We check the interaction of these two sources of volatility (GARCH behavior and jumps) by analyzing the
results of Model 4. In the case of NordPool, Australia and New Zealand, model 4 provides the best fit among
all models. In all the markets except Spain we may see that the GARCH process is stationary in Model 4 and
that the estimated probability of observing a jump, i.e. the estimated λ, is smaller than the reported in Model
3. We interpret this result as a support of the idea of take into account both sources of volatility. Therefore
jumps and GARCH are complementary rather than substitute factors in a model for electricity prices.
Finally, Model 4b allows for time dependency in the intensity of the Poisson process. In the case of
Argentina model 4b best fits data (under the Schwartz Criterion, SC). In the case of Argentina (see also
PJM), there is a clear seasonal pattern in jump behavior, with a higher probability of observing a jump in
June, July or August. In this case the effects of jump and volatility appear in a clear way. We may observe
the sharp decrease in the estimated value of α when allowing for jumps (see also the results for Victoria and
PJM). Also note that when moving from Model 3 to Model 4, the intensity of the Poisson process (λ)
decreases (because part of the movements of the price series are captured by the GARCH process), although
the estimated mean jump decrease is not statistically significant.
The Spanish market deserves a special comment. The results for this market point out as the best model,
Model 2. The estimated GARCH(1,1) process in model 2 is stationary. When we include jumps and estimate
Model 4 we see that either the jump process is not statistically significant (in the case of seasonality with
sinusoidal function) or we obtain an estimate of ω not statistically significant in Model 4 (with monthly

13
dummies). We believe that one of the main reasons for getting this unique behavior of the Spanish market
are the institutional framework. Mainly, the way stranded costs (or CTC) are treated in the Spanish
deregulation process creates conflictive incentives on the few players that are in the Spanish market, see
Federico and Whitmore (1999) and Fabra and Toro (2001) treatment of the interaction of incentives in the
Spanish market and its consequences on energy price risk. Basically, the amount of stranded costs to be paid
to generators depends negatively on the price observed in the pool. If prices are above a known and pre-
established level, generators earn higher profits from their operations in the pool but will receive a lower
amount of stranded costs. Therefore, there is a conflict of interests among power generating firms which
depend on the characteristics of each firm: market share, expectations about the probability of obtaining
stranded costs, etc. which affect the equilibrium price in a predictable way.
Our empirical results suggest an improvement by moving from Model 2 or Model 3 to Model 4. Moving
from Model 2 to Model 4 there is not only an improvement in terms of goodness of fit but also the
understanding of the behavior of electricity prices does so. On the other hand, moving from Model 3 to
Model 4 the goodness of fit also improves and we observe a clear interaction between GARCH and jumps
indicated by a decrease in the estimated intensity of the Poisson process. The effect of including
GARCH(1,1) model is clear in terms of the estimated frequency of jumps, however the effect of the mean
jump size is not so clear. We think there are two reasons for this ambiguous result. The first one is that since
we are using average daily prices, and although there is a weekly dummy that tries to capture the lower
demand on weekends, we are not capturing those holidays that are in the middle of a week, and some below
average demand weekends. Probably in those days we may observe a “negative” jump, that has a mixed
effect on µJ, because when we introduce GARCH behavior we are left with some negative and positive
jumps. Clearly we are not too interested on those negative jumps since they are predictable. Probably if we
work with an on-peak daily average price these problems will diminish. The other reason we have in mind is
that results are not so clear in those markets where jumps are relatively less important, where GARCH
behavior is more important to understand the uncertainty in that market.
More work is needed in this direction by increasing the number of analysed series, using on-peak series
and/or use a different specification for µJ (perhaps a time-dependent mean jump size, which is very easy to
handle in our model).
Although statistically speaking there is no huge improvement when we allow for time-dependent
intensity this is an appealing possibility if we want to understand other aspects of these markets. For
instance, the fact that there are time-dependent intensities could affect the behavior of risk premium, and the
term structure of forward curves. Those questions are left for future research.

6. UNIT ROOT TESTS

Traditional unit root tests, like Dickey-Fuller (1979) are powerful against most mean-reverting
alternatives if the errors are homoskedastic and there is no jumps in the data (stationarity). Pindyck (1999)
deals with the issue of unit roots test in the context of energy commodities (oil, gas, coal). In part, because

14
Pindyck (1999) focus on the long-run evolution of energy prices he does not take into account the possibility
of jumps or non-constant volatility in his unit root tests.
However, as we have seen in the previous section, those stationarity conditions are not satisfied by
equilibrium electricity prices. We propose to generalize recent powerful methods proposed in the
econometric literature that independently take into account the effects of heterocedasticity-GARCH(1,1)
errors, see Boswijk (2000), and outliers when testing for the presence of unit roots, see Arranz, Escribano
and Marmol (2000).
From our empirical analysis we conclude that the most appropiate model for equilibrium electricity prices
(Pt ) is a flexible model (Model 4b of Appendix B) with deterministic seasonality, autoregressive (AR(1)) and
GARCH(1,1) errors and with jumps with time dependent intensity of the Poisson process. That is,

Pt = f ( t ) + X t (12)

where f(t) is defined in equation (8) and the stochastic term X t is generated by an AR(1) process with
heterokedastic errors and additive outliers.

Xt = φ · Xt-1 + ηt (13)

where the errors ηt follows a GARCH(1,1) process with jumps of time dependent intensities generated by a
Poisson distribution. That is,

h t1/2 ε1t; with prob. 1- λt

ηt = (14)
h t 1/2 ε1t + µJ + σJ· ε2t ; with prob. λt
h t = ω + α· εt-1 + β· ht-1 (15)
λt = L1 · wintert + L2 · fallt + L3 · spring t + L4 · summert (16)

where ε1t , ε2t and εt ~ i.i.d. N(0,1) and mutually independent. The objective now is to test the null
hypothesis of a unit root, H0 : φ =1, against the mean reverting alternative hypothesis, H1 : φ < 1.
6.1. Standard Unit Root Test, Dickey and Fuller(1979)
The most common procedure for testing the unit root hypothesis is to use Dickey-Fuller (DF) or
Augmented Dickey-Fuller (ADF) type of tests in the context of independent, Gaussian and homokedastic
errors, term εt on equation (17). As a benchmark, we report results of ADF-test for the unit root null
hypothesis, H0 : (φ - 1) = 0, against the alternative of mean reverting, H1 : (φ - 1) < 0. The ADF-test is based
on the t-ratio of (φ - 1) in the following regression equation,

15
 r
∆X t = c + (φ − 1) ⋅ X t −1 + ∑ φ j ∆X t − j + εt . (17)
j =1

The maximum order of the lags (r) differs in each of the individual market price series (Xt ) and it is
empirically determined in order to warranty that the residuals (estimates of εt ) have no serial correlation.
Table 6.1 includes the empirical results of the ADF-test for the five electricity markets (NP = NordPool,
ARG = Argentina, VIC = Victoria, NZ = New Zealand and SP = Spain) with the approximate 5 % critical
value.

Table 6.1.: Unit Root Tests (ADF)

Series ADF Test Statistic 5% Critical Value (McKinnon Critical Values)
NP -2,922 -2,863
ARG -6,376 -2,863
VIC -6,947 -2,863
NZ -6,031 -2,864
SP -4,686 -2,865
PJM -4,077 -2,864

Those results of Table 6.1, show that the unit root hypothesis is always rejected, in favor of mean reverting
alternative, at a 5% significance level. The lowest rejection occurs in the NordPool, as expected from the
empirical results mentioned in the previous section. However, in the application of unit root test to electricity
prices one has to face two additional problems that in principle creates doubts on the credibility of those
empirical results. First, the presence of volatility (GARCH) and second, the existence of outliers (jumps) in
the data. Most unit root testing procedures are sensitive to the occurrence of anomalous events (outliers, etc.)
and also to the presence of heteroskedasticity, specially with near-integrated volatility.
In what follows, we present the empirical results of addressing each of these issues independently and we
also suggest a new sequential unit root testing procedure when both problems appear in the price series.
6.2. Unit Root Tests with GARCH(1,1) errors: Boswijk (2001).
In cases where the error term follows a GARCH process, estimation and testing for a unit root
involves intrinsic problems, Pantula (1989). Peters and Veloce (1988) and Kim and Schmidt (1993) provided
simulation results to show that Dickey-Fuller tests based on LS estimators are often sensitive and, when α +
β <1 but is close to 1, the problem can be very serious. Ling et al. (2001) show by simulation analysis that
tests based on ML estimators perform better than tests based on LS estimators (Dickey-Fuller). Boswijk
(2000) considers tests for a unit root when the innovations follow a near-integrated GARCH process. As we
have seen in agreement with Duffie et al. (1998) near-integrated GARCH processes are common in
electricity price series. Typical unit root test rely on the constant volatility assumption. If the series has
heterocedasticity, Least Squares estimates are not efficient, and the test might not be able to detect the (low)
mean-reversion. The results in Boswijk (2000) point out an increase in power in unit root test (LR type of
test) when the test takes into account the possibility of GARCH(1,1) behavior. The increase in power is

16
higher when α + β ≈ 1, specially if α is high (large short-run variation in the volatility), as it is usually the
case with electricity price series.
We report the results for the unit root test proposed by Boswijk (2001). The test is a Likelihood Ratio type
of test based on the following specification:

∆X t = (φ − 1)( X t −1 − µ) + εt ⋅ ht
1
2

ht = ω + α ⋅ εt2−1 + β ⋅ ht −1 (18)
ηt ~ i.i .d .N (0,1)
The parameter (φ - 1) describes the degree of mean-reversion. The null hypothesis is the unit root hypothesis,
H0 : (φ - 1) = 0, which is tested against the mean reversion alternative, H1 : (φ - 1) < 0.
The likelihood ratio statistic for the null hypothesis is
LR = −2 ⋅ (l (θR ) − l (θU ))
where θR and θU are the restricted and unrestricted maximum likelihood estimators respectively. The
limiting distribution of LR under the null hypothesis depends on a nuisance parameter. The nuisance
parameter can be expressed (and therefore estimated) as a function of the GARCH parameters. For details on
the limiting distribution and the calculation of the p-values, see Boswijk, (2001) and Boswijk and Doornik,
(1999).

Table 6.2.: Unit Root Tests (Boswijk, 2001)

Series LR p-value
NP 20,07 0,0033
ARG 192,4 0,00
VIC 65,71 0,00
NZ 135,08 0,00
SP 168,76 0,00
PJM 320,4 0,00

This test statistic clearly rejects the unit root hypothesis in all markets.
6. 3. Unit Root Test in the Presence of Outliers: Arranz, Escribano and Marmol (2000).
The presence of additive transitory outliers in the series biases unit root inference towards rejection
of the unit root hypothesis, see for instance Franses and Haldrup (1994). We use a procedure recently
proposed in the literature in order to deal with this issue. Arranz et al. (2000) have proposed to use a
nonlinear filter (median filter) before we test for unit roots when the series has additive outliers. The
methodology proposed by Arranz et al. (2000) consists on applying Dickey-Fuller tests on the filtered series.
We have selected this procedure based on three arguments: this procedure is robust to the presence of
additive outliers, it improves the performance of traditional unit root tests and it much easier to apply than
other test based on robust estimation procedures, see for example Lucas (1995 a, b), Vogelsang (1999) and
Ng and Perron (1998) .

17
We report the results obtained for the unit root test proposed by Arranz et al., (2000). The test consists on 2-
step: First filter the data (Xt ) with the “median filter”,

X t* = median ( X t − k ,..., X t ,...X t + k ) . (19)

That is, Xt * is the filtered values of Xt where the value of k is set k = 2, following the simulation results of
Arranz, et al. (2000). In the second step, apply an ADF-test based on the regression equation,

r
∆X t* = c + (φ − 1) ⋅ X t*−1 + ∑ φ j ∆X t*− j + εt . (20)
j =1

Table 6. 3. Unit Root Test, Arranz et al., (2000)

Series ADF Test Statistic 5% Critical Value (McKinnon critical values)
NP -2,937 -2,863
ARG -6,696 -2,863
VIC -5,246 -2,863
NZ -6,543 -2,864
SP -4,883 -2,865
PJM -6,788 -2,864

Table 6.3 reports the ADF results with the corresponding critical value (at 5%). Once again, we reject with a
95% confidence the unit root hypothesis against the mean reversion alternative for all the electricity markets.

6.4. Unit Root Testing Procedures in the Presence of Outliers and GARCH(1,1) Errors: a Bootstrap
Approach.
One of the main limitations of those recent unit roots tests statistics is the fact that they could deal with either
the presence of GARCH or alternatively with the presence of jumps but they cannot cope simultaneously
with both. Our goal now is to provide a new testing strategy that is able to cope with the simultaneous
presence of GARCH and jumps in the context of unit root testing.

18
We propose to implement this testing strategy in two step:
First, apply the median filter of Arranz et al. (2000) to the original series (P t ) without
deterministic seasonal components on it, (Xt ) in equation (12), and generate Xt * .
Second, apply the test proposed by Boswijk (2000) to the transformed series Xt * .
Since we do not know the limiting distribution, nor the small sample distribution of Boswijk´s LR test when
it is applied to Xt * , we suggest to implement the LR-test by bootstrap (re-sampling) techniques.
In particular, we are allowing the equilibrium price series to have non-constant volatility (GARCH(1,1)) and
outliers (additive), see equations (12)-(16). In order to simultaneously take into account these two features,
we suggest to sequentially apply both Arranz et al. (2000) and Boswijk (2001) procedures. The idea basically
is to use a powerful test for unit root in the presence of GARCH(1,1) errors, taking also into account the
existence of outliers and seasonality. In order to do so, we apply the median filter to the “deseasonalized”
series (preliminary steps). Once we have done those corrections we apply Boswijk´s unit root test combined
with bootstrap techniques in order to obtain valid the critical values.
Let Xt* be the equilibrium price series without seasonality and filtered with the median filter, equation (14)
with k=2. We are interested in testing the null of unit root in the following model:

1
∆X t * = c + (φ − 1) ⋅ X t −1 * + εt ⋅ ht 2
(21)
ht = ω + α ⋅ εt2−1 + β ⋅ ht −1

That is we want to test the null hypothesis H0 : (φ - 1) = 0 against H1 : (φ - 1) < 0 with the Boswijk’s LR

statistic. Let {cˆ, ω

ˆ , αˆ , βˆ } be the QML parameter estimates of model (16) under H0 and let εt* be the
bootstrap residuals from the QML residuals. Next, in order to generate bootstrap samples we have used the
following scheme under the null hypothesis (H0 ):

∆Z t* = cˆ + εt* ⋅ ht*
(22)
ht* = ω
ˆ + αˆ ⋅ εt*−1 + βˆ ⋅ ht*−1
We have done NB = 1000 bootstrap re-samples. For each sample we have estimated the model under the null
and under the alternative and we have calculated their corresponding LR statistic. The bootstrap critical
value is obtained by looking at the 5% lower tail of the empirical distribution of these Likelihood Ratios.
In summary, the new unit root sequential testing procedure is:
Step 1: Eliminate seasonality. Define Xt = Pt – f(t), where P t is the equilibrium electricity price series
and f(t) is the seasonal function defined in equation (8) using the parameter values estimated from Model 4
(Tables B.1 to B.5 of Appendix B).
Step 2: Apply the median filter of equation (14) to Xt.. That is generate
X t* = median ( X t − k ,..., X t ,...X t + k ) for k=2.
Step 3: Estimate the model (21) by QML under the null (H0 : (φ - 1) = 0) and under the alternative
(H1 : (φ - 1) < 0 ). Calculate and store the LR statistic in each case. Call this LR statistic LRZ .

19
 Step 4: The QML residuals obtained under the null are used to generate NB bootstrap samples with
the previous scheme (22). We have set NB = 1000.
Step 5: From the bootstrap samples ( Z t* ) we obtain bootstrap QML estimates and the corresponding

log-likelihood values, under the null and under the alternative, and the Likelihood Ratio (LRZ) is recorded.
Step 6: The hypothesis H0 : (φ - 1) = 0 is rejected if LRZ is bigger than the corresponding bootstrap
critical value, obtained by looking at the 5% lower tail of the empirical distribution.

Table 6.4 Results for Likelihood Ratio, critical value and p-value
Series Likelihood Ratio (LRZ) 5% bootstrap critical value p-value
NP 7,15 6,99 0,046
ARG 150,82 10,58 0,000
VIC 112,95 7,44 0,000
NZ 35,98 10,46 0,003
SP 28,96 10,64 0,004
PJM 248,25 25,41 0,000

The results of the proposed unit root tests, see Table 6.4, allow us to reject with a 95% confidence the null
hypothesis of unit root in all the series. Furthermore, from the estimation results of the previous section we
know that the NordPool estimate of the autoregressive parameter, (AR(1)), is the largest and it is near a unit
root. From the sequential testing procedure that we have proposed we observe that in the NordPool the unit
root hypothesis can be rejected at 5% and that the p-value of the NordPool3 is highest. Since the lowest
power in unit root test occurs when the roots are near unity, we should not be surprised by this result.
Our purpose in the near future is to do risk management in electricity markets and for that we will consider
that prices from the NordPool are slowly mean reverting. For other modeling purposes like forecasting,
cointegration, etc., the mistake one can make by imposing that there is a unit root in the NordPool when in
fact is slowly mean reverting should not be important and it could even be of some help, see for instance the
cointegration approach of De Vany and Walls(1999).

7. CONCLUSIONS AND FURTHER RESEARCH

Deregulation in electricity sector has among other things introduced price uncertainty. The main concern
of this paper is the source of equilibrium price uncertainty generated in each “pool” as a result of the
evolution of the intersections of demand and supply of electricity. We have shown the high degree of
volatility and the existence of price spikes (jumps) in several international markets. We have presented a
general model for electricity prices in deregulated markets that jointly takes into account those factors and
provides both empirical evidence and economic intuition for the presence of these factors, and the interaction
among them.

3
For the NordPool case we also have done the bootstrap analysis with 2000 bootstrap replications. In this case, the
critical value was 6,67 and the p-value was 0,039.

20
The main factors are: seasonality, mean-reversion, conditional heterokedasticity and jumps. We have shown
that our model is flexible enough to incorporate the main characteristics of equilibrium electricity prices in a
set of different markets. We have shown the adequacy of our model even for series with different degrees of
seasonality, different degree of persistence of shocks in the equation of the mean, different jump intensities
(different levels of kurtosis) and different markets structures (different technology mix in the power
generators offering electricity in each market).
We also provide a detailed analysis of mean-reversion in electricity prices. We did a comprehensive set of
unit root tests that take into account the effect of heterokedasticity and outliers. The new unit root testing
strategy proposed in this paper allow us to conclude that in five markets analyzed using daily data;
Argentina, Australia (Victoria), New Zealand (Hayward), Nordpool, PJM and Spain, equilibrium electricity
prices are mean-reverting . As expected, the lowest degree of mean-reversion is observed in the NordPool,
but even in this case the mean reverting degree increases when we simultaneously allow for jumps and
GARCH behavior. Although the GARCH(1,1) behavior is an important factor in general, the inclusion of
both GARCH and jumps are needed (except for the Spanish market) to get convincing results.
Our empirical methodology is flexible enough to model some other plausible characteristic elements of
equilibrium electricity prices. For example, given the seasonality observed in the electricity demand and
given the convexity of the electricity supply function, seasonal volatility could also be an interesting aspect
to consider when modeling equilibrium electricity prices. In our approach we tried to capture this behavior
by means of a time-dependent intensity process. However, other alternatives are available like the
introduction of periodic specifications of the GARCH(1,1) process (Bollerslev and Ghysels 1996). We could
also include some kind of asymmetric GARCH behavior, see Knittel and Roberts (2001). The idea is that the
convexity of the supply stack implies some asymmetric behavior on the volatility of electricity prices
contingent on the sign of the shock. For example , Knittel and Roberts (2001) estimated an EGARCH (1,1)
model (without jumps) to California electricity prices finding an “inverse leverage effect”. Therefore, a
plausible extension could be to consider and EGARCH with jumps, in order to capture the volatility effect on
the jump estimates. Another interesting extension would be to introduce some explanatory variables in the
jump process like, demand or capacity of the system, which will affect the probability of observing a jump
(λ) or the mean jump size (µJ).
However, our next line of research in the near future is to use our estimated models in the analysis and
quantification of risk management. Given that we are jointly taking into account two sources of uncertainty,
jumps and stochastic volatility, and since we found some predictable component in the estimated jumps, we
could compare the Value at Risk (VaR) estimates from our specification to those obtained with more
established methods. In particular, we could compare the VaR estimates “a la Riskmetrics”, that only take
into account GARCH uncertainty, with our modeling procedure that also allows for jumps of time dependent
intensity. Furthermore on the valuation side, since we are able to quantify the relative role of jumps and
stochastic volatility, we could search for evidence on the type of risk premiums that are relevant for pricing
of derivatives in electricity markets. Those questions are out of the scope of this paper and are left for future
research.

21
APPENDIX A
This table presents descriptive statistics for a set of daily average electricity spot prices for different
countries. Summary statistics are reported for the price level, units are expressed in local currency.
Series analyzed and samples:

NordPool (NP): January 1, 1993 – November 30, 1999

Argentina (Arg): January 1, 1995 – September 30, 2000
Australia, Victoria (Vic): July 1, 1994 – December 12, 1999
New Zealand, Hayward (NZ): October 1, 1996 – August 31, 2000
Spain (SP): January 1, 1998 – December 31, 2000
U.S., PJM (PJM): April 1, 1998 – December 31, 2001

Table 1. Descriptive statistics.

Series N. Obs. Mean Med. Min. Max. Std.Dev Skew. Kurt.
NP 2525 142,59 132,12 14,81 423,38 66,70 0,75 3,51
ARG 2100 18,79 17,46 8,03 111,44 6,39 6,39 35,65
VIC 1991 25,55 20,70 1,46 441,28 22,56 6,57 87,26
NZ 1431 37,12 38,40 0,58 115,00 14,32 0,04 3,63
SP 1096 4,52 4,42 1,62 8,54 1,04 0,91 4,48
PJM 1370 27,92 22,57 8,19 397,34 25,58 7,60 76,44

22
Figure 1a: NordPool. Daily Average Price.
500

400

300

200

100

0
1/01/93 5/16/94 9/28/95 2/09/97 6/24/98 11/06/99

Figure 1b: NordPool. Empirical Distribution (Kernel Density, Epanechnikov, h = 22,679)

0.010

0.008

0.006

0.004

0.002

0.000
0 100 200 300 400

Figure 2a: Argentina. Daily Average Price.

120

100

80

60

40

20

0
1/01/95 5/15/96 9/27/97 2/09/99 6/23/00

Figure 2b: Argentina. Empirical Distribution (Kernel Density, Epanechnikov, h = 1,5116)

0.14

0.12

0.10

0.08

0.06

0.04

0.02

0.00
20 40 60 80 100

23
Figure 3a: Australia. Daily Average Price.
500

400

300

200

100

0
7/01/94 11/13/95 3/27/97 8/09/98

Figure 3b: Australia. Empirical Distribution. (Kernel Density, Epanechnikov, h = 5,9686)

0.04

0.03

0.02

0.01

0.00
0 100 200 300 400

Figure 4a: New Zealand. Daily Average Price.

120

100

80

60

40

20

0
10/01/96 2/13/98 6/28/99

Figure 4b: New Zealand. Empirical Distribution. (Kernel Density, Epanechnikov, h = 6,2931)
0.04

0.03

0.02

0.01

0.00
0 20 40 60 80 100 120

24
Figure 5a: Spain. Daily Average Price.
10

0
1/01/98 5/16/99 9/27/00

Figure 5b: Spain. Empirical Distribution. (Kernel Density, Epanechnikov, h = 0,3521)

0.6

0.5

0.4

0.3

0.2

0.1

0.0
2 4 6 8

Figure 6a: PJM. Daily Average Price.

500

400

300

200

100

0
4/01/98 8/14/99 12/26/00

Figure 6b: PJM. Empirical Distribution. (Kernel Density, Epanechnikov, h = 4,3946 )

0.06

0.05

0.04

0.03

0.02

0.01

0.00
100 200 300 400

25
APPENDIX B: MODELS AND EMPIRICAL RESULTS
Model 1: Autoregressive (AR(1)), constant volatility model with no jumps (pure diffusion model).
Pt = f(t) + Xt
Xt = φ Xt-1 + σ ε1t
ε1t ∼ i.i.d. N(0,1)
Model 2: Autoregressive (AR(1)), GARCH(1,1) model with no jumps.
Pt = f(t) + Xt
Xt = φ Xt-1 + h 0.5t-1 ε1t
h t = ω + α εt-1 + β ht-1
ε1t ∼ i.i.d. N(0,1)
Model 3: Autoregressive (AR(1)), pure jump model.
Pt = f(t) + Xt
φ Xt-1 +σ· ε1t; prob. 1- λ
Xt =
φ Xt-1 +σ· ε1t+µJ+σJ· ε2t ; prob. λ
ε1t , ε2t ~ i.i.d. N(0,1)
Model 3b: Autoregressive (AR(1)), pure jump model, intensity of the Poisson process time
dependent.

Pt = f(t) + Xt
φ Xt-1 +σ· ε1t; prob. 1- λt
Xt =
φ Xt-1 +σ· ε1t+µJ+σJ· ε2t ; prob. λt
λt = L1 · wintert + L2 · fallt + L3 · spring t + L4 · summert
ε1t , ε2t ~ i.i.d. N(0,1)

Model 4: AR(1), GARCH(1,1) model with jumps, intensity of Poisson process constant.
Pt = f(t) + Xt
φ· Xt-1 +ht ε1t ; prob. 1- λ
1/2

Xt =
φ· Xt-1 +ht 1/2 ε1t +µJ+σJ· ε2t ; prob. λ
h t =ω + α· εt-1 + β · ht-1
ε1t , ε2t ~ i.i.d. N(0,1).

26
Model 4b: Autoregressive (AR(1)), GARCH(1,1) model with jumps, intensity of the Poisson
process time dependent. This is general the model we have presented previously (equations (4) –
(7)).
Pt = f(t) + Xt
φ · Xt-1 + h t ε ; prob. 1- λt
1/2
1t

Xt =
φ· Xt-1 + h t1/2 ε1t +µJ+σJ· ε2t ; prob. λt
h t = ω + α· εt-1 + β · ht-1
λt =L1· wintert + L2 · fallt + L3 · spring t + L4 · summert
ε1t , ε2t ~ i.i.d. N(0,1).

27
APPENDIX B. Estimation Results

Table B.1: Estimation Results (NORDPOOL).

Model 1 Model 2 Model 3 Model 3b Model 4
Parameter Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat.
B0 137,04 63,03 111,81 195,95 110,14 65,57 111,75 66,71 111,73 181,77
φ 0,93 134,69 0,82 57,04 0,90 114,22 0,90 117,43 0,82 60,61
D1 7,99 4,16 7,33 13,35 7,56 5,48 7,51 5,38 6,41 11,07
C1 30,02 14,77 38,68 58,41 37,13 28,69 40,18 28,39 40,29 64,36
C2 221,09 63,86 200,13 237,81 213,12 98,66 212,12 93,70 201,23 233,23
σ 34,26 74,35 18,50 24,03 19,22 28,84
ω 10,30 8,40 6,03 3,67
α 0,41 10,58 0,41 10,33
β 0,59 22,98 0,58 19,32
λ 0,28 5,65 0,04 0,85
L1 0,14 4,21
L2 0,29 5,67
L3 0,26 5,23
L4 0,31 5,14
µJ 50,78 6,43 53,93 6,94 15,89 0,91
σJ 33,84 7,82 33,46 7,31 12,82 1,81

LL -12505 -11131 -12177 -12165 -11095

SC 25057 22324,7 24424,5 24424 22278,2

Table B.2: Estimation Results (ARGENTINA ).

Model 1 Model 2 Model 3 Model 3b Model 4 Model 4b
Parameter Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat.
B0 19,36 42,39 18,75 184,24 19,26 99,21 19,27 99,19 19,25 137,14 19,22 136,12
φ 0,61 96,36 0,56 33,44 0,58 53,89 0,58 53,88 0,55 23,79 0,55 23,17
B2 -0,0021 -8,12 -0,0022 -39,33 -0,0028 -20,41 -0,0028 -20,51 -0,0026 -24,49 -0,0026 -24,59
D1 2,14 6,64 1,05 12,32 1,34 10,62 1,34 10,74 1,13 13,19 1,16 13,35
C1 -2,03 -6,81 -1,07 -15,16 -1,00 -8,97 -0,99 -9,10 -0,78 -8,89 -0,76 -8,70
C2 103,88 10,58 170,65 45,64 140,79 23,47 145,50 23,10 139,38 20,88 142,99 20,11
C3 -1,71 -6,21 -0,74 -9,85 -0,64 -5,90 -0,57 -5,24 -0,61 -7,11 -0,57 -6,54
C4 131,69 25,85 145,06 57,60 126,58 26,24 128,46 24,09 122,63 27,98 122,33 26,14
σ 4,55 216,10 1,90 50,84 1,90 52,42
ω 0,95 14,87 0,797 10,03 0,83 10,11
α 0,85 24,15 0,486 13,56 0,47 13,27
β 0,37 29,75 0,329 11,35 0,32 10,18
λ 0,11 11,09 0,049 4,51
L1 0,087 5,21 0,037 2,92
L2 0,070 4,60 0,037 2,68
L3 0,028 2,93 0,027 2,60
L4 0,264 10,07 0,125 4,66
µJ 8,09 7,82 8,00 7,82 7,01 3,55 6,80 4,46
σJ 10,10 42,73 10,07 41,60 6,50 6,19 6,48 7,63

LL -6148,1 -5052,2 -5148,3 -5096,6 -4822,6 -4810,8

SC 12365,0 10188,5 10388,4 10307,9 9752,3 9751,6

28
Table B.3: Estimation Results (AUSTRALIA (Victoria)).
Model 1 Model 2 Model 3 Model 3b Model 4 Model 4b
Parameter Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat.
B0 31,64 15,02 18,99 60,72 26,95 35,61 26,63 35,84 24,22 41,70 25,27 44,51
φ 0,47 49,27 0,57 45,04 0,55 57,48 0,54 56,18 0,61 30,98 0,61 31,09
B2 -0,011 -7,08 -0,002 -11,27 -0,008 -14,52 -0,008 -14,38 -0,0062 -14,63 -0,0067 -15,78
D1 6,82 5,53 2,13 9,23 5,20 10,08 5,07 10,02 3,17 9,94 3,30 10,20
C1 6,37 4,83 2,23 10,51 3,59 8,13 3,37 7,70 2,06 6,31 5,05 15,05
C2 53,82 10,61 110,27 51,27 55,42 15,79 57,53 15,62 45,55 10,62 46,50 13,07
C3 4,32 3,43 7,29 38,94 4,90 11,47 5,08 11,70 6,00 18,04 2,81 8,45
C4 48,50 2,74 63,72 44,56 58,03 11,02 59,78 12,12 52,13 18,02 37,10 11,56
σ 18,18 256,26 7,81 50,78
ω 2,31 7,06 3,23 6,51 3,72 7,01
α 1,07 33,89 0,32 10,75 0,33 10,92
β 0,49 77,96 0,62 29,45 0,61 28,41
λ 0,07 9,14 0,019 4,86
L1 0,141 6,49 0,030 2,59
L2 0,048 4,01 0,015 2,35
L3 0,031 2.81 0,006 1,18
L4 0,099 5,95 0,021 2,88
µJ 29,73 3,86 28,84 3,95 64,03 1,90 66,83 1,68
σJ 53,98 35,80 52,22 37,48 84,06 8,17 86,24 6,87

LL -8582,6 -7566,8 -7527,5 -7512,7 -7161,7 -7159,2

SC 17228,2 15210,6 15139,0 15130,4 14421,4 14447,4

Table B.4: Estimation Results (NEW ZEALAND (Hayward)).

Model 1 Model 2 Model 3 Model 3b Model 4 Model 4b
Parameter Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat.
B0 43,94 36,25 44,72 64,25 45,47 48,16 44,77 43,97 46,82 112,15 46,82 112,93
φ 0,62 47,94 0,61 23,70 0,64 45,22 0,65 42,54 0,57 22,89 0,57 22,67
B2 -0,013 -10,13 -0,011 -15,60 -0,015 -16,17 -0,014 -13,45 -0,017 -31,62 -0,017 -31,52
D1 3,35 5,05 3,25 6,53 2,44 4,36 2,77 4,67 2,83 9,56 2,82 9,57
C1 -4,05 -6,48 -5,69 -15,26 -5,27 -10,10 -4,91 -8,43 -4,57 -15,12 -4,53 -14,97
C2 52,59 5,83 64,60 17,62 40,30 7,14 48,73 7,62 46,32 11,26 46,62 11,20
C3 -2,50 -3,82 2,81 7,51 1,71 3,24 1,93 3,33 -1,07 -3,38 -1,03 -3,26
C4 -5,17 -0,72 -120,29 -30,96 458,06 53,76 455,55 55,96 22,01 2,51 21,48 2,36
σ 9,87 91,25 5,43 17,64 7,35 29,44
ω 8,14 9,42 1,11 3,60 1,13 3,64
α 0,40 9,91 0,36 8,84 0,36 8,61
β 0,60 25,77 0,59 19,75 0,58 18,93
λ 0,42 10,71 0,10 5,76
L1 0,066 1,88 0,096 3,40
L2 0,169 3,61 0,114 3,17
L3 0,279 5,03 0,089 2,89
L4 0,171 3,58 0,145 3,71
µJ 0,99 1,21 1,64 0,99 2,97 1,44 2,92 1,49
σJ 12,75 36,94 15,94 20,20 15,51 22,40 15,18 22,34

LL -5291,8 -5184,0 -5218,3 -5212,1 -4984,4 -4983,6

SC 10649,0 10447,9 10523,8 10533,2 10070,5 10090,7

29
Table B.5: Estimation Results (SPAIN).
Model 1 Model 2 Model 3 Model 4 Model 4b
Parameter Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat.
B0 3,32 39,24 3,81 91,52 3,44 47,21 3,62 32,90 3,97 75,94
φ 0,60 29,15 0,53 16,75 0,62 32,67 0,55 11,76 0,53 17,10
B2 0,001 10,54 0,0004 5,86 0,0008 8,41 0,0006 4,51 0,0002 2,73
D1 0,787 29,13 0,56 14,36 0,71 14,37 0,55 7,68 0,53 16,28
C1 0,18 3,26 0,15 4,94 0,16 3,46 0,13 2,07 0,17 5,79
C2 70,98 4,58 72,57 12,87 49,14 3,07 44,28 1,68 90,70 8,29
C3 -0,43 -8,33 -0,16 -4,99 -0,36 -7,92 -0,25 -4,54 -0,12 -3,87
C4 -2129,3 -639,3 -2112,2 -383,6 -2123,6 -591,4 -2120,3 -307,7 -2110,9 -267,4
σ 0,67 58,26 0,52 20,14
ω 0,018 6,66 0,034 1,95 0,002 0,80
α 0,18 6,66 0,14 2,76 0,16 5,79
β 0,78 32,88 0,85 17,05 0,81 29,09
λ 0,193 3,58 0,0002 0,00
L1 0,45 3,03
L2 0,25 2,23
L3 0,08 1,06
L4 0,15 2,10
µJ 0,378 2,61 0,61 0,00 -0,18 -2,16
σJ 0,919 11,49 0,41 0,00 0,50 8,26

LL -1107,9 -942,1 -1077,8 -1010,3 -915,2

SC 2278,8 1961,2 2239,6 2118,6 1949,4

Table B.6: Estimation Results (PJM).

Model 1 Model 2 Model 3 Model 3b Model 4 Model 4b
Parameter Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat. Coeff. t-stat.
B0 17,59 4,90 8,70 22,60 15,92 22,26 15,88 21,60 16,70 32,71 16,69 32,25
φ 0,57 85,02 0,39 9,69 0,39 41,42 0,39 39,88 0,49 17,67 0,49 17,23
B2 0,0072 2,32 0,0079 15,76 0,008 11,71 0,008 11,83 0,006 10,50 0,006 10,31
D1 7,45 3,12 4,11 12,99 3,06 6,67 2,99 6,43 2,33 6,50 2,33 6,47
C1 5,79 2,62 4,91 22,56 1,46 4,21 1,28 3,65 0,97 3,12 0,95 3,01
C2 -68,75 -6,38 -128,08 -84,34 -91,41 -12,99 -95,33 -11,69 105,50 12,07 103,58 11,56
C3 5,61 2,38 -7,21 -19,41 2,05 5,78 2,12 6,09 -3,39 -11,42 -3,29 -11,00
C4 -733,18 -22,36 1452,43 777,25 -685,66 -68,04 -682,03 -67,76 556,72 101,39 557,43 98,16
σ 20,29 14,92 5,99 42,95
ω 1,42 2,06 3,96 7,30
α 1,117 16,80 0,31 9,80
β 0,498 27,02 0,56 25,67
λ 0,065 8,02 0,027 4,43
L1 0,07 4,11 0,01 1,20
L2 0,01 1,70 0,01 1,24
L3 0,02 1,85 0,03 2,41
L4 0,14 6,61 0,06 3,42
µJ 46,34 4,28 47,13 4,27 54,98 1,91 54,35 1,83
σJ 65,81 13,37 67,00 12,66 67,05 4,94 66,67 4,50

LL -6050,03 -5285,00 -4836,07 -4809,47 -4686,32 -4678,13

SC 12165,06 10649,45 9758,81 9727,28 9473,76 9479,04

30
Table B. 7: Generalized Likelihood Ratio Tests * (p-values in parenthesis).
Series [1] χ 2 (2) [2] χ 2 (3) [3] χ 2 (5) [4] χ 2 (3) [5] χ 2 (2) [6] χ 2 (3) [7] χ 2 (3)

NordPool 2748 656 2820 72 2164 24 N.A.

(0.00) (0.00) (0.00) (0.00) (0.00) (0.00)

Argentina 2191 1999,6 2651 459,2 651,4 103,4 23,6

(0.00) (0.00) (0.00) (0.00) (0.00) (0.00) (0.00)

Australia 2031 2110 2841 810,2 731,6 29,6 5

(0.00) (0.00) (0.00) (0.00) (0.00) (0.00) (0.17)
(Victoria)
New Zealand 215,6 147 614,8 399,2 467,8 12,4 1,6
(0.00) (0.00) (0.00) (0.00) (0.00) (0.006) (0.659)
(Hayward)
Spain 331,6 60,2 195,2 N.A. 135 N.A. 190,2
(0.00) (0.00) (0.00) (0.00) (0.00)

PJM 1530,1 2427,9 2727,4 1197,4 299,5 53,2 16,4

(0.00) (0.00) (0.00) (0.00) (0.00) (0.00) (0.00)

*
[1] Constant variance, no jump model against GARCH(1,1), no jump model; [2] Constant variance, no jump model against pure
jump model; [3] Constant variance, no jump model against GARCH(1,1) jump(λ) model; [4] GARCH(1,1) model against
GARCH(1,1) jump(λ) model; [5] Pure jump model against GARCH(1,1) jump(λ) model; [6] Pure jump model against jump(λ(t));
[7] GARCH(1,1) jump(λ) model against GARCH(1,1) jump(λ(t)) model. P-values are given in parenthesis.

31
 REFERENCES
Arranz, M. A., Escribano, A., and Mármol,F. (2000), “Effects of Applying Linear and Nonlinear Filters
on Tests for Unit Roots with Additive Outliers”, Working Paper 00-86, Statistics and Econometrics
Series, Universidad Carlos III.
Bhanot, K. (2000), “Behavior of Power Prices: Implications for the Valuation and Hedging of Financial
Journal of Risk, 2 , 43-62.
Bergstrom, A. R. (1988), “The History of Continuous-Time Econometric Models”, Econometric
Theory, 4:3, 365-383.
Berndt, E.K., Hall, B.H., Hall, R.E., and Hausman, J.A. (1974), “Estimation and Inference in Non-
Linear Structural Models”. Annals of Economic and Social Measurement, 4 , 653-665.
Birnbaum, L., Del Aguila, J.Mª., Domínguez, G., and Lekander, P. (2002), “Why Electricity Markets
McKinsey Quarterly 1.
Bollerslev, T. (1986), “Generalized Autoregressive Conditional Heterokedasticity”, Journal of
Econometrics, 31 , 307-327.
Bollerslev, T., Engle, R.F., and Nelson, D.B. (1994), “ARCH Models”, in R.F. Engle and D.L.
McFadden (eds.), Handbook of Econometrics, vol. 4, Amsterdam: Elsevier.
Bollerslev, T., and Ghysels, E. (1996), “Periodic Autoregressive Conditional Heteroscedasticity”,
Journal of Business and Economic Statistics, 14 , 139-151.
Borenstein, S. (2001), “The Trouble with Electricity Markets (and some Solutions)”, POWER Working
Paper 081, University of California Energy Institute.
Boswijk, P.H. (2000), “Testing for a Unit Root with Near-Integrated Volatility”, unpublished
manuscript, Department of Quantitative Economics, Universiteit van Amsterdam.
Boswijk, P.H., and Doornik, J.A. (1999), “Distribution Approximations for Cointegration Tests with
Stationary Exogenous Regressors”, Discussion Paper 99-013/4, Tinbergen Institute.
Carnero, A., Peña, D., and Ruiz, E. (2001), “Outliers and Conditional Autoregressive Heterocedasticity
-07, Universidad Carlos III.
Carnero, A., Peña, D., and Ruiz, E. (2002), “Is Stochastic Volatility more flexible than GARCH?”, WP
01-08, Universidad Carlos III.
Clewlow, L., and Strickland, C. (2000), Energy derivatives: Pricing and Risk Management, Lacima
Publications.
Das, S.R. (2001), “The Surprise Element: Jumps in Interest Rate Diffusions”, Journal of Econometrics,
106, 27-65.
Das, S.R., and Sundaram, R.K. (1999), “Of Smiles and Smirks: a Term Structure Perspective”, Journal
of Financial and Quantitative Analysis, 34 , 211-239.
De Vany, A. S., and Walls, D.W. (1999), “Cointegration Analysis of Spot Electricity Prices: Insights on
Energy Economics, 21, 435-488.

32
Dickey, D.A., and Fuller, W.A. (1979), “Distribution of the Estimators for Autoregressive Time Series
with a Unit Root”, Journal of the American Statistical Association, 74 , 427-31.
Duffie, D., Gray, S., and Hoang, P. (1998), “Volatility in Energy Prices”, Managing Energy Price Risk ,
RiskPublications, Second Edition.
Fabra, N. and Toro, J. (2001), “Price Wars and Collusion in the Spanish Electricity Spot Market”,
working paper, IDEI.
Federico, G., and Whitmore, A. (1999), “The Importance of Market Structure and Incentives in
Energy Modelling and the Management of Uncertainty,
RiskPublications
Franses, P. H., and Haldrup, N. (1994), “The Effects of Outliers on Unit Root and Cointegration”,
Journal of Business and Economic Statistics, 12 , 471-478.
Hogan, W. W. (1998), “Competitive Electricity Market Design: a Wholesale Primer”, unpublished
manuscript, Harvard Electricity Group.
Hotta, L. K., and Tsay, R. (1998), “Outliers in GARCH Process”, unpublished manuscript.
Johnson, B., and Barz, G. (1999), “Selecting Stochastic Process for Modelling Electricity Price
Energy Modelling and the Management of Uncertainty, RiskPublications.
Jorion, P. (1989), “On Jump Processes in the Foreign Exchange and Stock Markets”, Review of
Financial Studies, 1, 427-445.
Karesen, K.F., and Husby, E. (2000), “A Joint State-Space Model for Electricity Spot and Futures
Prices”, Report no. 965, Norwegian Computing Center.
Kim, K., and Schmidt, P. (1993), “Unit Root Tests with Conditional Heteroscedasticity”, Journal of
Econometrics, 59, 287-300.
Knittel, C. R., and Roberts, M. (2001), “An Empirical Examination of Deregulated Electricity Prices”,
POWER WP -087, University of California Energy Institute.
Leon, A., and Rubia, A. (2001), “Comportamiento del Precio y Volatilidad en el Pool Eléctrico
Español”, Instituto Valenciano de Investig -2001-04, (www.ivie.es)
Ling, S., Li, W.K. and McAleer, M. (2001), “Estimation and Testing For Unit Root Processes with
GARCH(1,1) Errors: Theory and Monte Carlo Evidence”, Discussion Paper No 544, Institute of
Social and Economic Research, Osaka University.
Lucas, A. (1995), “An outlier robust unit root test with an application to the extended Nelson-Plosser
data”, Journal of Econometrics, 66, 153-173.
Lucas, A. (1995b), “Unit root tests based on M Econometric Theory, 13, 331-346.
Lucia, J., and Schwartz, E. (2000), “Electricity Prices and Power Derivatives: Evidence from the Nordic
Review of Derivatives Research, 5 (1), 5-50.
Melino, A. (1994), “Estimation of Continuous-time Models in Finance”, in Advances in Econometrics,
Sixth World Congress, Volume II, edited by C. Sims, Cambridge University Press, Cambridge.
Neely, C. J. (1999), “Target Zones and Conditional Volatility: the Role of Realignments”, Journal of
Empirical Finance, 6:2, 177-192.

33
Nelson, D. B. (1990), “Stationarity and Persistence in the GARCH(1,1) Model”, Econometric Theory, 6,
318-344.
Ng, S., and Perron, P. (1998), “Lag Length Selection and the Construction of Unit Root Tests with
Working paper 319, Boston University.
Nieuwland, F., Verschoor, W., and Wolff, C. (1994), “Stochastic Trends and Jumps in EMS Exchange
Journal of International Money and Finance, 13, 699-727.
Pantula, S. G. (1989), “Estimation of Autoregressive Models with ARCH Errors”, Sankhya B, 50, 119-
138.
Peters, T.A. and Veloce W. (1998), “Robustness of Unit Root Tests in ARMA Models with Generalized
ARCH Errors”, unpublished manuscript, Brock University.
Pindyck, Robert S. (1999), “The Long-Run Evolution of Energy Prices”, The Energy Journal, 20, 1-27.
Pirrong, C., and Jermakyan, M. (1999), “The Price of Power: The Valuation of Power and Weather
Derivatives”, unpublished manuscript, Olin School of Business, Washington University.
Schwartz, E. (1997), “The Stochastic Behavior of Commodity Prices: Implications for Valuation and
Hedging”, Journal of Finance, 52, 923-973.
Schwartz, E., and Smith, J.E. (2000), “Short-Term Variations and Long-Term Dynamics in Commodity
Prices”, Management Science, 46, 893-911.
Verhoeven, P., and McAleer, M. (2000), “Modelling Outliers and Extreme Observations for ARMA-
GARCH Process”, unpublished manuscript.
Vlaar, P., and Palm, F.C. (1993), “The Message in Weekly Exchange Rates in the European Monetary
System: Mean Reversion, Conditional Heterokedasticity and Jumps”, Journal of Business and
Economic Statistics, 11, 351-360.
Vogelsang, T.J. (1999), “Two Simple Procedures for Testing for a Unit Root when there are Additive
Journal of Time series Analysis, 20, 173-192.
Wolak, F. (1997), “Market Design and Price Behavior in Restructured Electricity Markets: an
International Comparison”, working paper, available at www-leland.stanford.edu/~wolak.

34