Forecasting value-at-risk under different distributional assumptions

Braione, Manuela; Scholtes, Nicolas K. Article Forecasting value-at-risk under different distributional assumptions Econometrics Provided in Cooperation with: MDPI – Multidisciplinary Digital Publishing Institute, Basel Suggested Citation: Braione, Manuela; Scholtes, Nicolas K. (2016) : Forecasting value-at-risk under different distributional assumptions, Econometrics, ISSN 2225-1146, MDPI, Basel, Vol. 4, Iss. 1, pp. 1-27, https://doi.org/10.3390/econometrics4010003 This Version is available at: https://hdl.handle.net/10419/171846 Standard-Nutzungsbedingungen: Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden. Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen. Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in EconStor may be saved and copied for your personal and scholarly purposes. You are not to copy documents for public or commercial purposes, to exhibit the documents publicly, to make them publicly available on the internet, or to distribute or otherwise use the documents in public. If the documents have been made available under an Open Content Licence (especially Creative Commons Licences), you may exercise further usage rights as specified in the indicated licence. http://creativecommons.org/licenses/by/4.0/ Article Forecasting Value-at-Risk under Different Distributional Assumptions Manuela Braione 1,† and Nicolas K. Scholtes 1,2,∗,† Received: 15 July 2015; Accepted: 21 December 2015; Published: 11 January 2016 Academic Editors: Fredj Jawadi, Tony S. Wirjanto and Nuttanan Wichitaksorn 1Center for Operations Research and Econometrics (CORE), Université catholique de Louvain, 34 Voie du Romans Pays, B-1348 Louvain-la-Neuve, Belgium; [email protected] 2Center for Research in Finance and Management (CeReFiM), Université de Namur, 62 Rue de Bruxelles, B-5000 Namur, Belgium *Correspondence: [email protected]; Tel.: +32-10-474-321 † These authors contributed equally to this work. Abstract: Financial asset returns are known to be conditionally heteroskedastic and generally non-normally distributed, fat-tailed and often skewed. These features must be taken into account to produce accurate forecasts of Value-at-Risk (VaR). We provide a comprehensive look at the problem by considering the impact that different distributional assumptions have on the accuracy of both univariate and multivariate GARCH models in out-of-sample VaR prediction. The set of analyzed distributions comprises the normal, Student, Multivariate Exponential Power and their corresponding skewed counterparts. The accuracy of the VaR forecasts is assessed by implementing standard statistical backtesting procedures used to rank the different specifications. The results show the importance of allowing for heavy-tails and skewness in the distributional assumption with the skew-Student outperforming the others across all tests and confidence levels. Keywords: Value-at-Risk; forecast accuracy; distributions; backtesting JEL classification: C01; C22; C52; C58 1. Introduction Value-at-Risk (VaR) is a quantitative tool used to measure the maximum potential loss in value of a portfolio of assets over a defined period for a given probability. Specifically, VaR construction requires a quantile estimate of the far-left tail of the unconditional returns distribution. Though widely-used as a risk measure in the past, standard methods of VaR construction assuming iid-ness and normality have come under criticism due to their failure to incorporate three stylized facts of financial returns, namely (i)the presence of volatility clustering, indicated by high autocorrelation of absolute and squared returns, (ii)excess kurtosis (fat tails) and (iii)skewness in the density of the unconditional returns distribution. The ability to account for volatility clustering is one of the key strengths of the ARCH modelling approach developed in Engle [1] and extended in Bollerslev [2]. By combining this approach with a non-normal conditional distribution assumption for the returns, several papers have shown that univariate GARCH models can produce reliable out-of-sample volatility forecasts. For example, Angelidis et al. [3] combine three GARCH specifications with the univariate skew-Student and skew-GED (Generalized Error) distributions to show that these are able to produce superior VaR forecasts compared to the normal. Specifically, they apply the exponential GARCH (EGARCH) model of Nelson [4] and the threshold ARCH (TARCH) model to five univariate returns series and find that while the choice of a skewed, heavy-tailed distribution significantly improves the Econometrics 2016,4, 3; doi:10.3390/econometrics4010003 www.mdpi.com/journal/econometrics Econometrics 2016,4, 3 2 of 27 forecasting performance, the choice of the volatility model appears to be irrelevant. These findings are echoed in Mittnik and Paolella [5] who combine the Asymmetric Power ARCH (APARCH) model of Ding et al. [6] with an asymmetric generalised Student distribution. Within the univariate framework the most complete study of VaR prediction methods is provided by Kuester et al. [7] who compare fully parametric models with VaR constructed using historical simulation, extreme-value theory and quantile regression. Their results show that considerable improvement over normality is achieved when using innovation distributions that allow for skewness and fat tails. Another salient feature of financial returns series is the fact that comovements between markets increase during periods of high volatility, as shown for example by Longin and Solnik [8] and Brooks et al. [9]. In light of this, a number of studies predict the VaR of a portfolio using multivariate models for the system of individual asset returns in order to achieve forecast improvements due to the use of more information. However, as mentioned in Bauwens et al. [10], in high dimensional frameworks these models can suffer from the “curse of dimensionality” problem thus being more computationally intensive. In order to shed some light on this issue, several papers focus on direct comparison of the predictive performance of univariate and multivariate GARCH (MGARCH) models under various distributional assumptions with the aim of providing evidence in favour of one of the two approaches. Key studies in this literature include Giot and Laurent [11] and Santos et al. [12]. In the first, the authors compare the univariate APARCH model with a multivariate TVC-APARCH combined with the normal, Student and skew-Student distributions, showing that in both the univariate and multivariate settings the latter produced superior VaR forecasts. In the second, the authors study a number of univariate and multivariate volatility models with normal and Student distributions, finding that the multivariate models combined with the Student offer superior out-of-sample performances. This paper builds on their approach by widening the set of distributions used to model the error term in both the univariate and multivariate frameworks while maintaining a generic specification for the conditional volatility. Specifically, we consider three symmetric distributions, i.e., normal, Student and Multivariate Exponential Power (MEP), and their corresponding skewed counterparts obtained by applying the transformation of Bauwens and Laurent [13]1. By incorporating skewness in the corresponding symmetric densities by means of new parameters, we can explicitly analyse its marginal contribution as well as its joint effect with heavy-tails in the model forecasting performance. As for the choice of the volatility models, within the MGARCH literature we employ the Rotated BEKK (RBEKK) model of Noureldin et al. [15] as it is easy to estimate using covariance targeting even for moderately large cross sections, while in the univariate setting GARCH(1,1) specifications are used to modeling the conditional portfolio variance. Our choice of a relatively simple volatility model allows us to limit our focus entirely on whether the chosen distribution contributes to adequately capture features of the return data. Within the univariate scenario we also consider the NCT-APARCH model proposed by Krause and Paolella [16], as the authors developed an extremely fast method for parameter estimation that is found to outperform highly competitive models and can be easily compared to ours 2. Both univariate and multivariate models are estimated employing the aforementioned set of distributional assumptions and their accuracy in producing out-of-sample VaR forecasts is assessed by means of statistical backtesting procedures. The selected tests include the Unconditional Coverage (UC), Independence (IND) and Conditional Coverage (CC) tests of Christoffersen [17], the Duration-Based Test of Independence (DBI) of Dumitrescu et al. [18], the Time Until First Failure (TUFF) test of Kupiec [19] and the Dynamic Quantile (DQ) test of Engle and Manganelli [20]. 1The interested reader is referred to Ley and Paindaveine [14] who provide a detailed overview of this approach. 2We thank the authors for kindly providing us their MATLAB codes. Econometrics 2016,4, 3 3 of 27 The results of the tests are summarized using a grading scheme based on the number of acceptances of the null hypothesis which determines the distributional assumption providing the most accurate VaR forecasts. Results from VaR backtesting show that in the multivariate setup the skew-Student clearly outperforms all other distributions. Moreover, its univariate version produces more accurate VaR forecasts than the NCT-GARCH and is able to compete with the NCT-APARCH which incorporates asymmetry into the conditional volatility specification. Overall, our results show that allowing for heavy-tails and skewness produces the most accurate VaR forecasts in both the univariate and multivariate setups. By comparison, specifications including only heavy tails underperform relative to their skewed counterparts with the difference being more pronounced at 5% VaR. Interestingly, the univariate skew-normal distribution produces Var forecasts comparable to the more heavily-parametrized skew-Student and skew-MEP. As regards comparing the performance of univariate and multivariate models in general, our results do not allow us to clearly advocate the use of one methodology over the other. However, given that the hierarchy of distributions according to VaR forecast accuracy is preserved under both frameworks, the univariate approach may be preferred due to its lower computational burden. The paper is organized as follows: Section 2reviews the GARCH modelling framework, the theoretical methodology used for constructing the skewed distributions and the Maximum Likelihood (ML) estimation of the models with the selected distributional assumptions. Section 3 introduces the empirical methodology, comprising the portfolio construction, VaR estimation and backtesting procedures. Section 4provides estimation results and outcomes of the VaR tests and Section 5concludes with some final remarks. 2. Theoretical Framework This section illustrates the key points of our theoretical framework. Namely, we outline the alternative approaches to obtain portfolio VaR forecasts using univariate and multivariate models, we describe the procedure used to construct skewed distributions from the corresponding symmetric counterparts and finally we provide an overview of the set of employed distributions, comprising their likelihood derivation. Two things are worth mentioning. First, we focus on the portfolio VaR for a long position, implying that the predictive power of the models is linked to their ability in modelling large negative returns. Second, we define the asset allocation scheme via an N-dimensional vector of equal weights wt, where Ndenotes the number of assets in the portfolio and wt= (w1,t, . . . wN,t), with wi=1/N,∑N i=1wi=1. As shown in DeMiguel et al. [21], Tu and Zhou [22], Brown et al. [23] and Fugazza et al. [24], this “naive” diversification rule is able to consistently outperform more sophisticated methods. Moreover, it has the advantage of not being affected by the specified target return as in the Markowitz framework, being only driven by the number of assets. 2.1. VaR Estimation Let yt= (y1,t, ..., yN,t)0denote the N-dimensional discrete time vector of de-meaned daily returns at time tand wtthe vector of equal weights known at time t−1. The portfolio return is obtained as rp,t=w0 t−1yt, and the portfolio VaR at time tis equal to VaRt,α=µp,t+σp,tqα, (1) where µp,tand σp,tare respectively the portfolio mean and standard deviation and qαis the left quantile of the assumed conditional distribution at α%. As usually done in practical applications, the considered VaR confidence levels are α=5% and 1%. Note that in the remainder of the paper we will set µp,t=0, thus considering a simplified analytical formula for the computation of the VaR which only accounts for the portfolio conditional variance. Alternative approaches, as done for example in Econometrics 2016,4, 3 4 of 27 Bauwens et al. [25], fit an ARMA-type structure to the portfolio conditional mean or just assume it to be constant over time (see Santos et al. [12]). Ultimately, when present, the dynamic dependence in the conditional means of portfolio returns is known to be weak and quite difficult to predict, thus assuming a zero mean will have a negligible effects on the VaR forecasts. The specification of the portfolio standard deviation σp,tdepends on whether we consider a univariate or multivariate approach, with the difference between the two occurring in the conditioning set used. In the univariate case, the portfolio standard deviation is obtained as the standard deviation of the portfolio returns conditional on past portfolio returns, i.e., as the square root of σ2 p,t=Ehr2 p,t|rp,1, . . . rp,t−1i, (2) where the conditional variance σ2 p,tis estimated using a model chosen from the univariate GARCH class. More precisely, we use a simple GARCH(1,1) specification with variance targeting, which is written as σ2 p,t=¯ σ+a1r2 p,t−1+b1σ2 t−1, (3) where ¯ σ= (1−a1−b1)¯ ωand ¯ ωequals the unconditional variance of returns. Covariance stationarity requires that a1+b1<1, with {a1,b1} ≥ 0 scalar parameters to be estimated. In the multivariate setup, the conditioning set is made up of the entire vector of past returns: σ2 p,t=Ehr2 p,t|Y1, . . . Yt−1i =w0 t−1Ht|t−1wt−1(4) such that Ht|t−1=E(Ht|=t−1)is the conditional covariance matrix of returns given the information set available at time t−1. In this case, a multivariate model for Htneeds to be specified. Given its computational ease in practical application, we implement the rotated BEKK (RBEKK) model of Noureldin et al. [15], as it can be estimated for relatively large cross sections even with reach dynamics. The basic idea underlying the model is to transform the original data by performing a rotation and then to fit to the rotated returns the popular BEKK specification of Engle and Kroner [26]. Consequently, the model can be easily estimated with covariance targeting, where the long-run covariance is given by the identity matrix. More precisely, let ¯ Hdefine the unconditional covariance of ytand let the latter be rewritten as yt=¯ H1/2et. Using the spectral decomposition of ¯ H, i.e.,¯ H=PΛP0, where Pis a squared matrix of eigenvectors and the eigenvalue matrix Λis diagonal with nonnegative elements, we can get the symmetric square root of ¯ Has ¯ H1/2 =PΛ1/2P0. The series of rotated returns is thus defined as et=¯ H−1/2yt=PΛ−1/2P0yt, with Var(et) = IN, the N-dimensional identity matrix. Note that the conditional covariance of the rotated returns is Var(et|=t−1) = Gt, given that Var(yt|=t−1) = Ht=¯ H1/2Gt¯ H1/2. Hence, any dynamic covariance model for Htcan also be applied to model the dynamics of Gt. Since the rotated returns are orthogonal, a suitable parameterization is represented by the scalar BEKK, which ensures the positive definiteness of the matrix Gtbeing a function of only two scalar parameters, under the assumption of covariance stationarity. Its dynamic equation is expressed as Gt= (1−a2−b2)IN+a2et−1e0 t−1+b2Gt−1, (5) where, as in the univariate setup, {a2,b2} ≥ 0 and a2+b2<1. Econometrics 2016,4, 3 5 of 27 2.2. Constructing Skew Densities As far as financial applications are concerned, modelling and inference based on the normal distribution have often been proven to be of limited usefulness, as it is possible to gain statistical efficiency by allowing for more involved distributions featuring heavy tails and skewness. As a way to capture higher moments, the literature offers several alternatives. For example, the multivariate noncentral tdistribution has fat tails and is skewed; however, the skewness is linked directly to the location parameter, making it somewhat inflexible. The lognormal distribution has also been used to model asset returns, but its skewness is a function of its mean and variance, not a separate parameter. Others, such as the generalized hyperbolic (GH) or mixtures of distributions have also been employed in financial applications, despite being more computationally demanding (see Barndorff-Nielsen [27] for an introduction and Paolella and Polak [28] for a recent application). In this respect, Fernández and Steel [29] in the univariate case and Bauwens and Laurent [13] in the multivariate one developed a practical procedure for constructing skewed densities from their symmetric unimodal counterparts. These densities can be defined by introducing skewness in the corresponding symmetric densities by means of new parameters, such that the symmetric density results as a particular case. We build on their findings in order to enlarge the set of distributions to be used for VaR forecasting. In the following, we briefly recall the main steps of the procedure, being the discussion restricted to the more general multivariate framework for sake of space. We begin by defining the notion of symmetry of a standardized density used hereafter. In the univariate case, symmetry corresponds to g(x) = g(−x), where g(x)is a unimodal probability density function with zero mean. In the multivariate case, we rely on the general notion of M-symmetry stated in Definition 1 of Bauwens and Laurent [13], which encompasses the class of spherically symmetric densities. These can be obtained as a special case of the general family of multivariate elliptical distributions, denoted as g(x;µ,Σ,η)∝h((x−µ)0Σ−1(x−µ),η), (6) where xis a random vector with an integrable, positive function h(·):R+→R+, and ηcaptures the shape parameter of the distribution, when present. The spherically symmetric set of distributions, comprising the standard normal, Student and MEP, are obtained by setting µand Σequal to zero and IN, respectively. The idea of introducing skewness into an M-symmetric standardized distribution revolves around scaling it differently for negative (positive) values by multiplying (dividing) by a positive constant. The value of this scaling parameter (hereafter referred to as ξ) determines whether the resulting distribution is skewed to the left (0 <ξ<1) or to the right (ξ>1). Definition 1. Given a random vector z= (z1, . . . , zN)0with multivariate symmetric standardized distribution g(z;η)following Equation (6), the standardized skewed density f(z|ξ;η)with vector of asymmetry parameters ξ= (ξ1, . . . ξN)0, is obtained as: f(z|ξ,η) = 2N N ∏ i=1 ξi 1+ξ2 i!g(z?;η)(7) with z?= (z? 1, ..., z? N)0(8) z? i=ziξIi i(9) and Ii=(−1 if zi≥0 1 if zi<0. (10) Econometrics 2016,4, 3 6 of 27 The marginal rth-order moment of the obtained skewed distribution can be computed directly from the standardized rth moment of the symmetric density g(·). This is accomplished by applying the following transformation function: E(z?r i|ξ) = Mi,r ξr+1 i+(−1)r ξr+1 i ξi+1 ξi , (11) where the rth-order moment of the marginal gi(·), truncated to the positive real values, is given by Mi,r=Z∞ 02urgi(u)du. (12) Since only the first two moments are required in the transformation process, their analytical expression for r=1, 2 in Equation (11) is reported below: mi=E(z? i|ξi) = Mi,1 ξi−1 ξi(13) s2 i=Var(z? i|ξi) = Mi,2 −M2 i,1 ξ2 i+1 ξ2 i!+2M2 i,1 −Mi,2. (14) As shown in Appendix A,s2 ican also be expressed directly as a function of m2 i. Note that the resulting skewed distribution, f(z|ξ,η)from Definition 1, is not centered at 0 and the variance is a function of ξ(and, where is the case, of the shape parameter η). Given that the elements of z?are uncorrelated (since those of xare uncorrelated by assumption), standardization of z?is achieved by the following transformation: z= (z?−m)./s, (15) where m= (m1, ..., mN)and s= (s1, ..., sN)are the vectors of unconditional means and standard deviations of z?computed in Equations (13) and (14) respectively and “./” denotes element-by-element division. Consequently, the standardized form of Definition 1requires replacing Equation (9) with the following one: z? i= (sizi+mi)ξIi i, (16) where Ii=(−1 if zi≥ −mi si 1 if zi<−mi si (17) 2.3. Distributions As already mentioned, three symmetric and three asymmetric distributions are considered in the univariate and multivariate framework. Again, for sake of brevity, we only report the multivariate log-likelihood functions as the univariate can be obtained as special cases 3. The algebraic derivations of the formulas of the moments can be found in Appendix A.2. In all cases, estimation of the parameters is performed in one step by Maximum Likelihood (ML). Namely, the log-likelihood function for Tobservations is expressed as `T(ψ) = T ∑ t=1 log f(·|ψ,Ft−1), (18) 3In Appendix Dwe provide a brief overwiew of the noncentral tdistribution and its likelihood derivation. Econometrics 2016,4, 3 7 of 27 where ψis the finite-dimensional vector of model parameters and f(·|ψ,Ft−1)denotes the assumed conditional density function of the portfolio returns, in the univariate case, or of the asset return vector in the multivariate one. Multivariate normal distribution This is the most commonly employed distribution in the literature as it is uniquely identified by its conditional first and second moments, which renders ML estimation much simpler from a computational point of view. In addition, given that the score of the normal log-likelihood function has the martingale difference property when the first two conditional moments are correctly specified, the Quasi Maximum Likelihood (QML) estimates are still consistent and asymptotically normal even if the true DGP is not normally-distributed Bollerslev and Wooldridge [30]. The log-likelihood function for Tobservations is expressed as follows `T(ψ) = −1 2 T ∑ t=1hNlog(2π) + log |Ht|+y0 tH−1 tyti. (19) As the multivariate normal does not incorporate extra parameters, here we have ψ= (a2,b2)04. Multivariate Student distribution The Student distribution is a symmetric and bell-shaped distribution, with heavier tails than the normal. Under the multivariate Student assumption, the log-likelihood function is obtained as `T(ψ) = −1 2 T ∑ t=1"log |Ht|+ (N+ν)log 1+y0 tH−1 tyt ν−2!# +Tlog Γν+N 2−log Γν 2−N 2log(π)−N 2log(ν−2), (20) where Γ(ν) = R∞ 0e−zzν−1dz denotes the Gamma function and ν>2 is the degree of freedom parameter representing the thickness of the distribution tails. As νincreases, the distribution converges to the multivariate normal. The vector of parameter to be estimated is ψ= (a2,b2,ν,ξ)0. Multivariate Exponential Power (MEP) distribution This distribution belongs to the Kotz family of distributions (a particular class of symmetric and elliptical distributions discussed extensively in Fang et al. [31]) and is known to have several equivalent definitions in the literature. It can also include both the normal and the Laplace as special cases, as a function of the value of the non-normality parameter βdictating the tail-behaviour of the distribution. Given its simple implementation, in this paper we consider the pdf given in Solaro [32], which gives rise to the following log-likelihood function: `T(ψ) = −1 2 T ∑ t=1"log |Ht|+y0 tH−1 tytβ 2# +Tlog(N) + log ΓN 2−N 2log(π)−log Γ1+N β−1+N βlog(2), (21) where ψ= (a2,b2,β)0. Note the restriction β>0. When β=2, the distribution reduces to the multivariate normal, while for β=1 it corresponds to the multivariate Laplace. Whenever β<2 (>2), the distribution exhibits thicker (thinner) tails than the normal. 4In the univariate case it corresponds to ψ= (a1,b1)0. Econometrics 2016,4, 3 8 of 27 Multivariate skew-normal distribution The multivariate skew-normal is the first non-symmetric distribution we consider herein; it accounts for the skewness of the return distribution without taking into account its kurtosis (as it does not involve a tail parameter). Applying Definition 1we derive the skew-normal density function, with corresponding log-likelihood function equal to `T(ψ) = −1 2 T ∑ t=1 log |Ht|+ N ∑ i=1 si N ∑ j=1 pij,tyj,t+mi!2 ξ2Ii i  +T"N ∑ i=1 (log ξi+log si)−log(1+ξ2 i)#+TN 2[log(2)−log(π)], (22) where pij,tcorresponds to the jth element of the ith row of the inverse cholesky factor of the matrix Ht(the full derivation is provided in Appendix A.1), ξirepresents the asymmetry parameter of each marginal and Iiis the indicator function defined in Equation (17). The vector of parameters of interest is ψ= (a2,b2,ξ)0. Multivariate skew-Student distribution Applying the same procedure as for the skew-normal, the log-likelihood function of the skew-Student distribution is given by the following expression: `T(ψ) = −1 2 T ∑ t=1        log |Ht|+ (ν+N)log        1+ N ∑ i=1 si N ∑ j=1 pij,tyj,t+mi!2 ξ2Ii i ν−2               +TNlog(2)−N 2log(π) + log Γν+N 2−log Γν 2−N 2log(ν−2) +T"N ∑ i=1 (log ξi+log si)−log(1+ξ2 i)#, (23) where the parameter νdictates the thickness of the tails and ξiis again the asymmetry parameter of each marginal. Notice that the univariate means and standard deviations are functions of ξiand νand need not be estimated. Consequently, the skew-Student parametrization requires N+1 parameters to be estimated in addition to those stemming from the RBEKK specification, i.e.,ψ= (a2,b2,ν,ξ)0. Multivariate skew-MEP distribution The log-likelihood function to be maximized is given by `T(ψ) = −1 2 T ∑ t=1    log |Ht|+  N ∑ i=1 si N ∑ j=1 pij,tyj,t+mi!2 ξ2Ii i  β 2    +T"N ∑ i=1 (log ξi+log si)−log(1+ξ2 i)# +Tlog(N) + log ΓN 2−N 2log(π) −log Γ1+N β−1+N βlog(2), (24) where βis a parameter determining the tail-thickness of the density function, as in the symmetric case. Considering the skewness parameters implies the parameter vector ψ= (a2,b2,β,ξ)0. Econometrics 2016,4, 3 15 of 27 Panel (b) of Figure 2, this indicates that in this case tail thickness does not adjust to incorporate the addition of skewness. The effect of these features on VaR forecast accuracy will be seen in Section 4.2. 4.2. VaR Backtesting Results In the multivariate setting, the out-of-sample covariance matrix predictions are used to construct equally-weighted portfolios for the computation of the one-step-ahead VaR. Table 3compares portfolios standard deviation obtained using the univariate and multivariate approaches over both the in- and out-of-sample periods. Table 3. Portfolios descriptive statistics. Univariate Models Normal Student MEP Skew-Normal Skew-Student Skew-MEP NCT-APARCH NCT-GARCH In-sample: 1 February 2001 to 23 January 2007 (1500 observations) ¯ σp0.8716 0.8722 0.8662 0.8709 0.8718 0.8780 0.8222 0.8720 min{σp}0.4159 0.4155 0.3899 0.4134 0.4141 0.4457 0.3727 0.3852 max{σp}2.7805 2.6827 2.8234 2.8147 2.6965 2.7095 2.5242 2.5826 Forecasting sample: 24 January 2007 to 30 October 2009 (700 observations) ¯ σp1.4659 1.4601 1.4800 1.4656 1.4550 1.4573 1.4569 1.4644 min{σp}0.4398 0.4448 0.4139 0.4334 0.4427 0.4718 0.3745 0.3899 max{σp}3.9589 3.8967 3.9743 3.9656 3.8033 3.9281 4.2310 3.1567 Multivariate Models Normal Student MEP Skew-Normal Skew-Student Skew-MEP In-sample: 1 February 2001 to 23 January 2007 (1500 observations) ¯ σp0.9021 0.9115 0.8983 0.9018 0.9115 0.8924 min{σp}0.5226 0.5474 0.5077 0.5212 0.5478 0.4840 max{σp}1.9067 1.7923 1.9391 1.9097 1.7935 1.9972 Forecasting sample: January 24, 2007 to October 30, 2009 (700 observations) ¯ σp1.4721 1.4646 1.4875 1.4740 1.4549 1.4691 min{σp}0.5226 0.5474 0.5105 0.5233 0.5479 0.4908 max{σp}3.1733 3.0657 3.2108 3.1728 3.0674 3.2683 Note: The table reports average, minimum and maximum value of portfolio standard deviation over the in- and out-of-sample periods. As already noted, the financial crisis features heavily in the summary statistics. Since this period is included in the forecasting sample (starting from observation 1921 according to Table A1), we notice a sharp increase in the portfolio standard deviation of all the models (see also the figures reported in Appendix C). On a general basis, heavy-tailed or skewed distributions do not lead to remarkable gains over the in-sample period, as all the models report very similar values on average. This pattern is partly reversed in the forecasting period: while the normal and skew-normal remain very close, the skew-Student and skew-MEP exhibit a lower portfolio standard deviation than their symmetric counterparts. Remarkably good is the performance of the models featuring the NCT distribution; the NCT-APARCH achieves the lowest standard deviation among the univariate alternatives and compares favorably also to many multivariate models, being only outperformed by the skew-Student RBEKK. It appears that the uncertainty due to the larger number of parameters to be estimated is not fully compensated by the gain coming from a better representation of the volatility dynamics in multivariate models. Overall, according to this table, the univariate and multivariate approaches deliver quite similar portfolio summary statistics. If the focus was on the predicted portfolio variance alone, then the ideal choice would be to use a univariate volatility model coupled with either the skew-Student or the NCT distribution, as they are easy to estimate and computationally faster than the multivariate specifications. Ultimately, we are interested in the models accuracy in forecasting the one-step-ahead portfolio VaR, so we move to analyse the outcomes of the statistical backtesting procedures. Tables 4and 5report the results from the TUFF, UC, IND, CC and DBI tests in the univariate and multivariate cases, respectively. Econometrics 2016,4, 3 16 of 27 All statistical tests are computed for the 5% and 1% VaR confidence level. For each portfolio we report test statistics along with their corresponding p-values in brackets. Since the applied tests measure the models accuracy in forecasting VaR along several dimensions (as detailed in Section 3.2), the overall results are summarized using a performance measure which considers the percentage of acceptances of the null hypothesis across the different tests at the standard 5% significance level. To this end, rejections of the null are highlighted in bold with the total grade across distributions reported in Table 6. Table 4. VaR backtesting results—Univariate. Norm Skew-Norm Student Skew-Student MEP Skew-MEP NCT-APARCH NCT-GARCH 5% VaR violation/frequency 52 (0.074)42 (0.060)53 (0.076)29 (0.041)52 (0.074)40 (0.057)53 (0.076)25 (0.036) TUFF 5.991 (0.014)5.991 (0.014)5.991 (0.014)5.991 (0.014)5.991 (0.014)5.991 (0.014)0.022 (0.883)5.991 (0.014) UC 7.611 (0.006)1.389 (0.239)8.476 (0.004)1.147 (0.284)7.611 (0.006)0.720 (0.396)3.326 (0.068)8.476 (0.004) IND 8.829 (0.003)2.646 (0.104)8.815 (0.003)1.155 (0.283)7.870 (0.005)1.676 (0.195)5.151 (0.023)9.861 (0.002) CC 16.440 (0.000)4.035 (0.133)17.290 (0.000)2.302 (0.316)15.481 (0.000)2.397 (0.302)8.477 (0.014)18.337 (0.000) DBI 0.023 (0.880)0.079 (0.778)0.087 (0.768)0.830 (0.362)0.046 (0.831)0.100 (0.751)0.797 (0.372)0.303 (0.582) 1% VaR violation/frequency 15 (0.021)12 (0.017)12 (0.017)5 (0.007)14 (0.020)11 (0.016)11 (0.016)8 (0.011) TUFF 1.426 (0.232)1.426 (0.232)1.426 (0.232)1.426 (0.232)1.426 (0.232)1.426 (0.232)1.426 (0.232)1.426 (0.232) UC 6.957 (0.008)2.972 (0.085)2.972 (0.085)0.641 (0.423)5.479 (0.019)1.967 (0.161)0.138 (0.710)1.967 (0.161) IND 7.638 (0.006)3.406 (0.065)3.406 (0.065)0.707 (0.400)6.072 (0.014)2.330 (0.127)0.326 (0.568)2.330 (0.127) CC 14.595 (0.001)6.378 (0.041)6.378 (0.041)1.348 (0.510)11.551 (0.003)4.297 (0.117)0.464 (0.793)4.297 (0.117) DBI 0.518 (0.472)0.126 (0.723)0.002 (0.969)0.000 (0.985)0.547 (0.459)0.281 (0.596)0.501 (0.479)0.281 (0.596) Table 5. VaR backtesting results—Multivariate. Norm Skew-Norm Student Skew-Student MEP Skew-MEP 5% VaR violation/frequency 53 (0.076)51 (0.073)56 (0.080)38 (0.054)52 (0.074)44 (0.063) TUFF 5.991 (0.014)5.991 (0.014)5.991 (0.014)0.022 (0.883)5.991 (0.014)5.991 (0.014) UC 8.476 (0.004)6.789 (0.009)11.311 (0.001)0.264 (0.608)7.611 (0.006)2.260 (0.133) IND 9.861 (0.002)7.849 (0.005)13.261 (0.000)0.273 (0.601)8.829 (0.003)2.516 (0.113) CC 18.337 (0.000)14.637 (0.001)24.572 (0.000)0.536 (0.765)16.440 (0.000)4.776 (0.092) DBI 0.858 (0.354)0.818 (0.366)1.052 (0.305)1.501 (0.221)0.797 (0.372)1.593 (0.207) 1% VaR violation/frequency 19 (0.027)18 (0.026)17 (0.024)8 (0.011)17 (0.024)15 (0.021) TUFF 1.426 (0.232)1.426 (0.232)1.426 (0.232)1.426 (0.232)1.426 (0.232)1.426 (0.232) UC 14.153 (0.000)12.176 (0.000)10.313 (0.001)0.138 (0.710)10.313 (0.001)4.051 (0.044) IND 14.568 (0.000)13.106 (0.000)11.190 (0.001)0.326 (0.568)10.978 (0.001)1.652 (0.199) CC 28.721 (0.000)25.282 (0.000)21.503 (0.000)0.464 (0.793)21.292 (0.000)5.702 (0.057) DBI 3.109 (0.078)0.902 (0.342)3.798 (0.055)0.282 (0.595)1.573 (0.210)0.774 (0.379) Econometrics 2016,4, 3 17 of 27 Table 6. Grade comparison—VaR backtesting. Norm Skew-Norm Student Skew-Student MEP Skew-MEP NCT-APARCH NCT-GARCH 5% VaR Univariate grade 20% 80% 20% 80% 20% 80% 60% 20% Multivariate grade 20% 20% 20% 100% 20% 80% 1% VaR Univariate grade 40% 80% 80% 100% 80% 100% 100% 100% Multivariate grade 40% 40% 40% 100% 40% 80% The first distinguishing feature from the VaR backtesting results is the clear predominance of the skew-Student distribution. This holds for both the univariate and multivariate frameworks with the former producing VaR forecasts that outperform the NCT-APARCH at 5% VaR. Similarly, the skew-MEP distribution produces highly accurate VaR forecasts across the board. These findings exemplify a second feature of the results namely, the impact on VaR forecast accuracy of introducing skewness into a heavy-tailed distribution. Clearly, the performance of both the skew-Student and skew-MEP distributions improves compared to their symmetric counterparts, but this effect is less pronounced at 1% VaR. Indeed, the performance of the Student and MEP distributions improves when moving from the 5 % to the 1% VaR scenario, suggesting that despite the improvement arising from the introduction of skewness, heavy-tails remain useful in capturing larger swings in returns, i.e., those events located further out in the tails. As a final remark on the effect of skewness, we observe the large difference in performance between the NCT-APARCH and NCT-GARCH at 5% VaR. Though both feature a skewed distributional specification, recall that the NCT-APARCH also features asymmetry in the conditional volatility model which explains its superior performance. An analogous result is obtained in Giot and Laurent [11]. Analysis of the differences between the univariate and multivariate models reveals two key points. First, while the skew-Student and skew-MEP retain their dominance under both frameworks, the performance of their symmetric counterparts at 1% VaR is worse under the multivariate specification. Second, within the univariate framework, the skew-normal is capable of producing VaR forecasts comparable to the high performance skewed and heavy-tailed distributions at both VaR confidence levels. This does not hold in the multivariate setup where the skew-normal offers no improvements in VaR accuracy over the normal. Besides, we observe that in both frameworks the empirical failure rate (i.e., the frequency of violations) of the skewed distributions is closer to the nominal value than their symmetric counterparts, which are oversized. The NCT-GARCH represents the only exception, being considerably more conservative than the NCT-APARCH at both 5% and 1% VaR confidence levels. With respect to the previous backtesting methods, the DQ test takes into account a more general temporal dependence between the series of violations and is considered the most reliable in assessing VaR accuracy 6. The DQ test results are reported in Tables 7and 8. In order to compare the different distributional assumptions, Table 9summarises the percentage of null hypothesis acceptances over the two lag-lengths for each confidence level. The DQ test results tell a similar story to the VaR backtesting procedures. As before, the skew-Student outperforms its competitors at both 5% and 1% VaR under both univariate and multivariate setups. The univariate skew-normal continues to produce VaR forecasts with an accuracy comparable to the top-performers. Again, this does not extend to the multivariate case. 6We thank an anonymous referee who pointed out the possibility of better comparing the outcomes of the DQ and Christoffersen’s CC and IND tests by allowing the latter to be computed in an extended framework than the standard one described in Section 3.2. As results did not lead to significant improvements, this issue is briefly covered in Appendix E. Econometrics 2016,4, 3 18 of 27 Finally, forecast accuracy at 5% VaR again reveals a more pronounced improvement when moving from symmetric to skewed distributions than in the 1% case. Overall, introducing skewness into heavy-tailed distributions continues to offer the highest VaR forecast accuracy. Table 7. Dynamic Quantile test results—Univariate models. Norm Skew-Norm Student Skew-Student MEP Skew-MEP NCT-APARCH NCT-GARCH 5% VaR K= 1 DQUC 9.319 (0.002)1.594 (0.207)10.092 (0.001)1.079 (0.299)8.965 (0.003)0.809 (0.368)3.188 (0.074)10.485 (0.001) DQIND 1.433 (0.231)1.168 (0.280)0.389 (0.533)0.020 (0.886)0.281 (0.596)0.867 (0.352)0.698 (0.403)1.651 (0.199) DQCC 10.189 (0.006)2.665 (0.264)10.201 (0.006)1.087 (0.581)9.036 (0.011)1.636 (0.441)3.680 (0.159)11.463 (0.003) K= 3 DQUC 7.028 (0.008)1.196 (0.274)6.821 (0.009)1.240 (0.265)6.193 (0.013)0.525 (0.469)3.024 (0.082)8.068 (0.005) DQIND 0.633 (0.426)0.251 (0.616)4.536 (0.033)0.712 (0.399)3.738 (0.053)0.042 (0.838)0.102 (0.749)0.382 (0.537) DQCC 12.280 (0.015)2.398 (0.663)18.210 (0.001)2.633 (0.621)15.467 (0.004)1.624 (0.805)5.220 (0.265)12.955 (0.011) 1% VaR K= 1 DQUC 9.622 (0.002)3.744 (0.053)3.744 (0.055)0.580 (0.446)7.357 (0.007)2.393 (0.122)0.151 (0.698)2.393 (0.122) DQIND 0.713 (0.398)0.363 (0.547)0.363 (0.557)0.026 (0.872)0.579 (0.447)0.280 (0.597)0.107 (0.744)0.280 (0.597) DQCC 9.985 (0.007)3.991 (0.136)3.991 (0.136)0.598 (0.741)7.680 (0.021) 2.603 (0.272)0.254 (0.881)2.603 (0.272) K= 3 DQUC 9.078 (0.003)3.376 (0.066)3.376 (0.066)0.373 (0.541)6.848 (0.009)2.118 (0.146)0.126 (0.723)2.118 (0.146) DQIND 0.013 (0.910)0.528 (0.468)0.528 (0.468)0.617 (0.432)0.100 (0.751)0.876 (0.349)2.605 (0.106)0.876 (0.349) DQCC 13.749 (0.008)9.654 (0.047) 9.654 (0.047) 19.505 (0.001)11.961 (0.018) 9.171 (0.057)10.840 (0.028)9.171 (0.057) Table 8. Dynamic Quantile test results—Multivariate. Norm Skew-norm Student Skew-Student MEP Skew-MEP 5% VaR K= 1 DQUC 10.485 (0.001)8.226 (0.004)14.416 (0.000)0.280 (0.597)9.319 (0.002)2.538 (0.111) DQIND 1.651 (0.199)1.232 (0.267)2.406 (0.121)0.000 (0.993)1.433 (0.231)0.261 (0.610) DQCC 11.463 (0.003)8.990 (0.011)15.751 (0.000)0.280 (0.869)10.189 (0.006)2.727 (0.256) K= 3 DQUC 7.733 (0.005)6.096 (0.014)10.767 (0.001)0.277 (0.599)7.028 (0.008)1.607 (0.205) DQIND 1.006 (0.316)0.914 (0.339)0.690 (0.406)0.789 (0.374)0.633 (0.426)3.148 (0.076) DQCC 14.578 (0.006)11.839 (0.019)18.650 (0.001)2.662 (0.616)12.280 (0.015)9.201 (0.056) 1% VaR K= 1 DQUC 19.549 (0.000)18.210 (0.000)15.080 (0.000)0.151 (0.698)13.358 (0.000)9.622 (0.002) DQIND 1.278 (0.258)1.167 (0.280)1.041 (0.308)0.107 (0.744)2.095 (0.148)0.713 (0.398) DQCC 22.121 (0.000)18.684 (0.000)15.521 (0.000)0.254 (0.881)16.575 (0.000)9.985 (0.007) K= 3 DQUC 13.935 (0.000)14.056 (0.000)9.885 (0.002)0.126 (0.723)10.157 (0.001)6.809 (0.009) DQIND 20.104 (0.000)6.375 (0.094)15.843 (0.000)2.605 (0.106)14.404 (0.000)4.056 (0.255) DQCC 44.966 (0.000)35.949 (0.000)47.702 (0.000)8.842 (0.065)33.192 (0.000)9.271 (0.054) Econometrics 2016,4, 3 19 of 27 Table 9. Grade comparison—DQ tests. Norm Skew-Norm Student Skew-Student MEP Skew-MEP NCT-APARCH NCT-GARCH 5% VaR Univariate grade 33% 100% 17% 100% 33% 100% 100% 33% Multivariate grade 33% 33% 33% 100% 33% 100% 1% VaR Univariate grade 33% 83% 83% 83% 33% 100% 83% 100% Multivariate grade 17% 33% 17% 100% 17% 50% 5. Conclusions Given its importance in risk management, practitioners must be capable of forecasting the Value-at-Risk of their asset portfolios to a high degree of accuracy. This requires taking into account a number of properties of financial returns namely, non-normality, heavy-tails, skewness and the possibility of comovements between assets. In this article, we focus primarily on the effect of varying the distributional assumption used to forecast VaR. Moreover, we addressed the still open question of whether univariate or multivariate models are most appropriate for the problem of portfolio VaR forecasting. The distributions treated in the paper comprised three symmetric and three skewed distributional assumptions (i.e., normal, Student, MEP and their skewed counterparts) which were coupled with the RBEKK model in the multivariate framework and GARCH in the univariate. In addition, we compared our specification with a novel method for fast estimation of the (univariate) NCT-GARCH and NCT-APARCH models. We then proceeded to the models’ accuracy in predicting equally-weighted portfolio VaR. Employing a series of standard backtesting methods to compare the distribution-based model performance, the results reveal that the skew-Student specification produces the most accurate one-step ahead VaR forecast across all multivariate specifications and is able to compete with the high-performance NCT-APARCH in the univariate setup. This finding is echoed in the univariate MEP results wherein the skewed version outperforms the symmetric across all tests and confidence levels. By contrast, the multivariate skew-MEP exhibits thinner tails than the normal and thus, performs poorly at the 1% confidence level. More generally, The test results reveal a clear hierarchy of distributional assumptions within the univariate and multivariate setups, with that hierarchy being preserved when moving from one to the other. However, attempting to compare the performance of univariate to multivariate distributions in general does not reveal any key differences with the exception of certain cases in the skew-normal and skew-MEP specifications. Consequently, the additional computational burden of estimating multivariate models does not seem to be justified. There are several possible avenues of research extending from this work. Given the focus on distributions, we limited our attention to relatively simple parametric models namely, the RBEKK and GARCH models. As the NCT-GARCH/APARCH results showed, capturing asymmetries in returns volatility improves forecast accuracy. Considering their multivariate versions would provide a useful contribution and allow for a detailed study of the optimal model-distribution-dimension combination. Another possibility would be to consider higher forecast horizons for the VaR in order to check if the inclusion of skewness and asymmetric forms of dependence can lead to significant improvements in the long run. Acknowledgments: Manuela Braione and Nicolas K. Scholtes acknowledge support of the “Communauté française de Belgique” through contracts “Projet d’Actions de Recherche Concertées” “12/17-045” and “13/17-055”, respectively granted by the Académie universitaire Louvain. We thank seminar participants at the 13th Journée d’économétrie at the Université Paris Ouest Nanterre La Défense along with Luc Bauwens and Florian Ielpo for useful comments. We also thank two anonymous referees and the academic editors for their comments and advice, all of which led to considerable improvements in the paper. Author Contributions: Manuela Braione and Nicolas K. Scholtes contributed equally to the writing of the MATLAB code as well as the preparation of the current manuscript. Econometrics 2016,4, 3 20 of 27 Conflicts of Interest: The authors declare no conflict of interest. Appendixes A. Derivations A.1. Transformation The transformation zt=H−1/2 tytis incorporated into the symmetric, standardised pdfs as follows: κ?0κ?= (κ? 1, ..., κ? N)0(κ? 1, ..., κ? N) =. . . (sizi+mi)ξIi i. . .0. . . (sizi+mi)ξIi i. . . = . . . (si N ∑ j=1 pijyj+mi)ξIi i. . .!0 . . . (si N ∑ j=1 pijyj+mi)ξIi i. . .! = N ∑ i=1 si N ∑ j=1 pijyj+mi!ξ2Ii i, where pij corresponds to the jth element of the ith row of H−1/2 t. Note that the tsubscript is dropped for simplicity. The matrix square root operation is carried out by applying the Cholesky decomposition of Htsuch that BB0=Ht. As a result, each ziis obtained by multiplying the row vector of H−1/2 tcorresponding to asset iwith the demeaned return vector (giving us the inner summation above) which is then multiplied by the univariate standard deviation and added to the univariate mean. The presence of skewness is factored in by the term ξIi i, where the factor Iiis defined as in Equation (17). A.2. Distributions Moments We report the first two moments of the univariate symmetric normal, Student and MEP distributions used to compute the log-likelihood function as given in Section 2.3. Note that the following relation holds: mi=Mi,1 ξi−1 ξi⇒M2 i,1 =m2 i ξ2 i (ξ2 i−1)2!. Hence, substituting this result into Equation (14), the 2nd order moment of the skewed distributions can be obtained as a function of the first: s2 i=M2 i,1 −ξ2 i−1 ξ2 i +2!+Mi,2 ξ2 i+1 ξ2 i−1! =ξ2 i (ξ2 i−1)2 −ξ4 i+2ξ2 i−1 ξ2 i!m2 i+Mi,2 ξ4 i−ξ2 i+1 ξ2 i! =ξ2 i (ξ2 i−1)2 (−ξ2 i+1)(ξ2 i−1) ξ2 i!m2 i+Mi,2 ξ2 iξ2 i−1+1 ξ2 i ξ2 i =m2 i 1−ξ2 i ξ2 i−1!+Mi,2 ξ2 i+1 ξ2 i−1!. Econometrics 2016,4, 3 21 of 27 Skew-Normal Mi,1 =Z∞ 0 2 √2πuexp −1 2u2du =r2 πZ∞ 0uexp −1 2u2du =r2 π Mi,2 =Z∞ 0 2 √2πu2exp −1 2u2du =r2 πZ∞ 0u2exp −1 2u2du =1 Skew-Student Mi,1 =2Γν+1 2 Γν 2pπ(ν−2)Z∞ 0u1+u2 ν−2−1+ν 2 du =2√ν−2ν−1 2Γν−1 2 √π(ν−1)Γν 2 =2√ν−2Γν+1 2 √π(ν−1)Γν 2 = Γν−1 2√ν−2 √πΓν 2 Mi,2 =2Γν+1 2 Γν 2pπ(ν−2)Z∞ 0u21+u2 ν−2−1+ν 2 du =(ν−2)Γν 2−1 2Γν 2 =(ν−2)Γν 2−1 2ν−2 2Γν 2−1=1 Skew-MEP Mi,1 =2−1 β Γ1+1 βZ∞ 0uexp −1 2uβdu =2−1+1 βΓ2+β β Γ1+1 β Mi,2 =2−1 β Γ1+1 βZ∞ 0u2exp −1 2uβdu =41 βΓ3 β βΓ1+1 β Econometrics 2016,4, 3 22 of 27 B. Tables Table A1. Windows length and corresponding calendar time. Rolling Fixed-Window Forecast Horizon It. Observations Days Observations Days 1 1–1500 1 Febraury 2001–23 January 2007 1501–1520 24 January 2007–21 Febraury 2007 2 21–1520 2 March 2001–21 Febraury 2007 1521–1540 22 Febraury 2007–21 March 2007 3 41–1540 30 March 2001–21 March 2007 1541–1560 22 March 2007–19 April 2007 4 61–1560 30 April 2001–19 April 2007 1561–1580 20 April 2007–17 May 2007 5 81–1580 29 May2001–17 May 2007 1581–1600 18 May 2007–15 June 2007 6 101–1600 26 June 2001– 15 June 2007 1601–1620 18 June 2007–16 July 2007 7 121–1620 25 July 2001–16 July 2007 1621–1640 17 July 2007–13 August 2007 8 141–1640 22 August 2001–13 August 2007 1641–1660 14 August 2007–11 September 2007 9 161–1660 26 September 2001–11 September 2007 1661–1680 12 September 2007–9 October 2007 10 181–1680 24 October 2001–9 October 2007 1681–1700 10 October 2007–6 November 2007 11 201–1700 21 November 2001–6 Novembe 2007 1701–1720 7 November 2007–5 December 2007 12 221–1720 20 December 2001–5 December 2007 1721–1740 6 December 2007–4 January 2008 13 241–1740 22 January 2002–4 January 2008 1741–1760 7 January 2008–4 Febraury 2008 14 261–1760 20 Febraury 2002–4 Febraury 2008 1761–1780 5 Febraury 2008– 4 March 2008 15 281–1780 20 March 2002–4 March 2008 1781–1800 5 March 2008–2 April 2008 16 301–1800 18 April 2002–2 April 2008 1801–1820 3 April 2008–30 April 2008 17 321–1820 16 May 2002–30 May 2008 1821–1840 1 May 2008–29 May 2008 18 341–1840 14 June 2002–29 May 2008 1841–1860 30 May 2008–26 June 2008 19 361–1860 15 July 2002–26 June 2008 1861–1880 27 June 2008–25 July 2008 20 381–1880 12 August 2002–25 July 2008 1881–1900 28 July 2008– 22 August 2008 21 401–1900 10 September2002–22 August 2008 1901–1920 25 August 2008– 22 September 2008 22 421–1920 8 October 2002–22 September 2008 1921–1940 23 September 2008–20 October 2008 23 441–1940 5 November 2002–20 October 2008 1941–1960 21 October 2008–17 November 2008 24 461-1960 4 December 2002–17 November 2008 1961–1980 18 November 2008–16 December 2008 25 481–1980 3 January 2003–16 December 2008 1981–2000 17 December 2008–15 January 2009 26 501–2000 3 Febraury 2003–15 January 2009 2001–2020 16 January 2009–13 Febraury 2009 27 521–2020 4 March 2003–13 Febraury 2009 2021–2040 17 Febraury 2009–16 March 2009 28 541–2040 1 April 2003–16 March 2009 2041–2060 17 March 2009–14 April 2009 29 561–2060 30 April 2003–14 April 2009 2061–2080 15 April 2009–12 May 2009 30 581–2080 29 May 2003–12 May 2009 2081–2100 13 May 2009–10 June 2009 31 601–2100 26 June 2003–10 June 2009 2101–2120 11 June 2009–9 July 2009 32 621–2120 25 July 2003–9 July 2009 2121–2140 10 July 2009–6 August 2009 33 641–2140 22 August 2003–6 August 2009 2141–2160 7 August 2009–3 September 2009 34 661–2160 22 September 2003–3 September 2009 2161–2180 4 September 2009–2 October 2009 35 681-2180 20 October 2003–2 October 2009 2181–2200 5 October 2009–30 October 2009 C. Figures 0 5 10 15 20 25 30 35 0.03 0.04 0.05 0.06 0.07 0.08 0.09 τ a Normal Student MEP 0 5 10 15 20 25 30 35 0.03 0.04 0.05 0.06 0.07 0.08 0.09 τ a skew−Normal skew−Student skew−MEP 0 5 10 15 20 25 30 35 0.01 0.015 0.02 0.025 τ a 0 5 10 15 20 25 30 35 0.01 0.015 0.02 0.025 0.03 τ a (a) Univariate models (b) Multivariate models Figure A1. Evolution across re-estimations of the GARCH/RBEKK parameter, a. Econometrics 2016,4, 3 23 of 27 0 5 10 15 20 25 30 35 0.91 0.92 0.93 0.94 0.95 0.96 0.97 τ b Normal Student MEP 0 5 10 15 20 25 30 35 0.9 0.91 0.92 0.93 0.94 0.95 0.96 τ b skew−Normal skew−Student skew−MEP 0 5 10 15 20 25 30 35 0.975 0.98 0.985 0.99 0.995 τ b 0 5 10 15 20 25 30 35 0.965 0.97 0.975 0.98 0.985 0.99 0.995 τ b (a) Univariate models (b) Multivariate models Figure A2. Evolution across re-estimations of the GARCH/RBEKK parameter, b. 0 200 400 600 800 1000 1200 1400 1600 1800 2000 2200 0 1 2 3 4 observation portfolio standard deviation Normal Student MEP 0 200 400 600 800 1000 1200 1400 1600 1800 2000 2200 0 1 2 3 4 observation portfolio standard deviation skew−Normal skew−Student skew−MEP 0 200 400 600 800 1000 1200 1400 1600 1800 2000 2200 0 1 2 3 4 observation portfolio standard deviation 0 200 400 600 800 1000 1200 1400 1600 1800 2000 2200 0 1 2 3 4 observation portfolio standard deviation (a) Univariate models (b) Multivariate models Figure A3. Portfolio standard deviations. 0 200 400 600 800 −15 −10 −5 0 5 10 t Portfolio returns and VaR (a) Normal Portfolio returns 1% VaR 5% VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 t Portfolio returns and VaR (b) skew−Normal Portfolio returns 1% VaR 5% VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 (c) Student t Portfolio returns and VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 (d) skew−Student t Portfolio returns and VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 (e) MEP t Portfolio returns and VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 (f) skew−MEP t Portfolio returns and VaR Figure A4. Cont. Econometrics 2016,4, 3 24 of 27 0 200 400 600 800 −15 −10 −5 0 5 10 t Portfolio returns and VaR (a) Normal Portfolio returns 1% VaR 5% VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 t Portfolio returns and VaR (b) skew−Normal Portfolio returns 1% VaR 5% VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 (c) Student t Portfolio returns and VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 (d) skew−Student t Portfolio returns and VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 (e) MEP t Portfolio returns and VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 (f) skew−MEP t Portfolio returns and VaR Figure A4. VaR: Univariate models. 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 (a) Normal t Portfolio returns and VaR Portfolio returns 1% VaR 5% VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 (b) skew−Normal t Portfolio returns and VaR Portfolio returns 1% VaR 5% VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 (c) Student t Portfolio returns and VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 (d) skew−Student t Portfolio returns and VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 (e) MEP t Portfolio returns and VaR 0 100 200 300 400 500 600 700 −15 −10 −5 0 5 10 (f) skew−MEP t Portfolio returns and VaR Figure A5. VaR: Multivariate models. D. The Univariate NCT-APARCH Model The main ingredients of the NCT-APARCH model discussed in the paper by Krause and Paolella [16] are, as the name may suggest, the use of a univariate noncentral t-distribution assumption for the error term and of an APARCH specification for the conditional variance equation.