The transformed Gram Charlier distribution: Parametric properties and financial risk applications
Introduction
Densities based on polynomial expansions (PE) have drawn great attention to model the departures from normality of the empirical return distributions. For instance, in a recent study, Bagnato et al. (2015) present a simple theorem that links the higher-order moments (skewness and kurtosis) of a polynomially expanded parent distribution to those of the resulting distribution. Within this framework, the Gram–Charlier (GC) probability density function (pdf) in Jondeau-Rockinger (2001) (henceforth, JR) is a PE density with the standard Normal as parent pdf. The GC distribution is very tractable theoretically and empirically mainly because its two parameters correspond directly to skewness and excess kurtosis. The following references, without being exhaustive, provide a research line on the development of the GC distribution: Beber and Brandt, 2006, Polanski and Stoja, 2010, Cheng et al., 2011, Ñíguez and Perote, 2012, Liu and Luger, 2015, Lönnbark, 2016, León and Moreno, 2017, Zoia et al., 2018 and Del Brio et al. (2020).1
A well-known problem of the GC density function is that it can render negative values. This issue has been mainly dealt with through two approaches. On the one hand, by means of parametric restrictions that ensure the GC pdf has positive probabilities, as in JR (2001). On the other hand, using density function transformations based on the methodology of Gallant and Nychka (1987) (GN henceforth). The latter approach was followed by León et al. 2005 (hereafter LRS) to define a positive GC density function with conditional autoregressive higher-order moments. The LRS model has been proven useful for numerous financial econometric applications; see, for instance, White et al., 2010, Alizadeh and Gabrielsen, 2013, Auer, 2015, Gabrielsen et al., 2015, Anatolyev and Petukhov, 2016, Kräussl et al., 2016, Narayan and Liu, 2018 and Wu et al. (2020).
Henceforth, the LRS density will be referred to as the transformed GC (TGC) since it is the result of transforming the GC density in JR (2001) in order to obtain a well-defined density without parameter restrictions. However, unlike the GC density parameters, the TGC ones do lose their direct interpretation as skewness and excess kurtosis. In this paper we study the TGC’s parametric properties providing its true higher-order moments and other features of the TGC pdf such as the conditions for unimodality, allowable ranges of skewness and kurtosis, closed-form formulae for (i) the cumulative distribution function (cdf), (ii) one-sided truncated TGC moments, and (iii) asymmetric risk measures such as expected shortfall (ES) and lower partial moments (LPMs).
We illustrate the practical use of this pdf through an application to modeling asset returns. For that purpose, we implement the threshold GARCH (TGARCH) model of Zakoïan (1994) for the conditional volatility. We test the performance of our model through an in-sample analysis, and out-of-sample (OOS) exercises for backtesting VaR and ES as well as for density forecasting. We derive the analytic expressions for the kth order stationarity conditions for the unconditional moments of the errors under the TGARCH with TGC density for the standardized errors (henceforth, TGC-TGARCH). Indeed, the second and fourth moments will receive special attention and so, the unconditional variance and kurtosis. Besides, we test the finiteness of the unconditional moments through the robust tail-index method of Gabaix and Ibragimov (2011). As a result, we provide stronger evidence respecting the one obtained from the second and fourth order stationarity conditions driven by the TGC-TGARCH parameter estimates. The data we use comprises stock indexes, exchange rates, a commodity and a cryptocurrency. For comparison purposes, we consider both the Normal distribution as the benchmark as well as the symmetric-GC pdf of Zoia et al. (2018), which we refer to as GCK hereafter. Our choice of the latter is based on that, unlike the TGC, the GCK does model directly kurtosis. Hence, in our comparison analyses we can easily isolate the effect of skewness on the performance of the density. Besides, we also compare the TGC’s performance with the popular skewed-t distribution of Hansen (1994). Furthermore, a robustness check of the conditional variance under the TGC is done using the nonlinear asymmetric GARCH (NAGARCH) of Engle and Ng (1993) as an alternative to the TGARCH.2 We evaluate density forecasting performance through -value discrepancy plots (Davidson and MacKinnon, 1998) together with proper scoring rules in Amisano and Giacomini (2007). VaR and ES forecasting accuracies are tested via the backtesting procedures in Du and Escanciano (2017).
Finally, we highlight two possible extensions left for future research although we show some previous results here. First, we extend the TGC to incorporate time-varying (TV) higher-order moments where the dynamics for the implied TGC parameters are driven by the specification in, among others, Lalancette and Simonato (2017), which accounts for asymmetric responses of conditional skewness and kurtosis to positive and negative shocks. Our in-sample analysis results show that modeling the TGC with TV higher-order moments clearly contributes to improving goodness-of-fit. The empirical evidence from our daily conditional skewness series is also reinforced by using an asymmetry measure beyond the third central moment and specifically, the one based on the return distribution’s tails proposed in Jiang et al. (2020). Second, we present a mixture of TGC (MTGC hereafter) densities that features higher flexibility than the TGC for capturing large ranges of kurtosis under a rather similar model framework to that in Alexander and Lazar (2006).
The remainder of the paper is structured as follows. Section 2 deals with the GC pdf as a set-up base of our analysis. In Section 3 we characterize the TGC pdf and study its parametric properties. In Section 4 we apply the TGC for modeling the conditional distribution of asset returns under the TGARCH structure, and analyze the power-law tail properties. Section 5 provides an empirical application to asset return series. Section 6 presents two possible extensions of the TGC linked to lines for further research. Section 7 provides a summary of the conclusions. Appendix A includes some properties of the Hermite polynomials used throughout the paper. Appendix B includes all proofs, and also the kth order stationarity conditions for the unconditional moments under the NAGARCH model. Appendix C presents the estimation results of the NAGARCH under the TGC pdf (henceforth, TGC-NAGARCH). The robust tail-index estimation results for the asset returns are provided in Appendix D. Finally, Appendix E shows a sensitivity analysis based on a simulation procedure that aims to study the theoretical behavior of the implied tail index from Kesten’s equation.
Section snippets
The GC distribution
The GC pdf is defined according to following the polynomial expansion density: where , is the parameter vector, is the pdf of the standard Normal distribution and is defined as such that denote the (normalized) Hermite polynomials in (70) in Appendix A. The associated cdf, i.e. , is given by where , and . More details about (3) and other
The transformed GC distribution
As an alternative to the numerical method implemented in JR (2001) for building the restricted parameter set which ensures the positivity to the pdf in (1), Gallant and Tauchen (1989) suggested to square the polynomial component in (2). As a result, we can obtain a new pdf , which we call the transformed GC (TGC), and given by where the parameter verifies that the pdf in (4) is well-defined and hence, the integral of must be equal to one. The inverse of is
Model for returns
We assume the asset return process is defined as with , where and denote the conditional mean and variance of given by and such that is the information set available at and are the innovations with zero mean, unit variance and as the distribution with TV parameter set, i.e. . Note that nests the simple case of constant parameters across time of the distribution of , i.e. . . We adopt alternative
Dataset and summary statistics
The data used are daily percent log returns computed as from samples of daily closing prices for Eurostoxx50 and Nikkei indexes, Japanese Yen to U.S. dollar (JAP–US) and U.S. dollar to pound sterling exchange rates (US–UK) and West Texas Intermediate Crude Oil, all obtained from the New York Stock Exchange, sampled from January 14, 1999 to January 14, 2019 for a total of observations. We also consider Bitcoin prices sampled from July 18, 2010 to July 31, 2018 (
Extensions
There are at least two admissible extensions of the TGC framework in this paper. The first one follows recent results in the literature which show the importance of TV conditional higher-order moments with asymmetric response to positive and negative shocks; see e.g. Feunou et al. (2016), and Lalancette and Simonato (2017). The TGC pdf allows a natural extension to model directly clustering and asymmetries in skewness and kurtosis. The time-varying version of the TGC pdf is denoted as TV-TGC.
Conclusions
We analyze the parametric properties of a new density obtained as a result of applying the Gallant and Nychka (1987) method to the Gram–Charlier (GC) density in Jondeau-Rockinger (2001) in order to ensure positivity within the whole parametric space. This density is referred to as the transformed GC (TGC). We provide a thorough analysis of the TGC’s statistical properties deriving the conditions for unimodality, allowable ranges of skewness and kurtosis, closed-form expressions of the
CRediT authorship contribution statement
Ángel León: Conceptualization, Data curation, Formal analysis, Funding acquisition, Investigation, Methodology, Project administration, Resources, Software, Validation, Visualization, Roles/Writing - original draft, Writing - review & editing. Trino-Manuel Ñíguez: Conceptualization, Data curation, Formal analysis, Funding acquisition, Investigation, Methodology, Project administration, Resources, Software, Validation, Visualization, Roles/Writing - original draft, Writing - review & editing.
Acknowledgments
We are grateful to participants at the 44th Symposium of the Spanish Economic Association (Alicante, 2019) for helpful comments, discussions and suggestions. Of course, the usual caveat applies. Financial support from the Spanish Ministry of Economy and Competitiveness, Spain through grant ECO2017-87069-P is gratefully acknowledged by Ángel León.
References (69)
- et al.
Dynamics of credit spread moments of European corporate bond indexes
J. Bank. Financ.
(2013) - et al.
The effect of macroeconomic news on beliefs and preferences: Evidence from the options market
J. Monetary Econ.
(2006) - et al.
Modeling threshold conditional heteroscedasticity with regime-dependent skewness and kurtosis
Comput. Statist. Data Anal.
(2011) - et al.
Risk quantification for commodity ETFs: Backtesting value-at-risk and expected shortfall
Int. Rev. Financ. Anal.
(2020) - et al.
Properties of moments of a family of GARCH processes
J. Econometrics
(1999) - et al.
Gram–Charlier densities
J. Econom. Dynam. Control
(2001) - et al.
Conditional volatility, skewness and kurtosis: Existence, persistence, and comovements
J. Econom. Dynam. Control
(2003) - et al.
Backtesting for risk-based regulatory capital
J. Bank. Financ.
(2004) - et al.
Euro crash risk
J. Empir. Financ.
(2016) - et al.
One-sided performance measures under Gram–Charlier distributions
J. Bank. Financ.
(2017)
Modeling asset returns under time-varying semi-nonparametric distributions
J. Bank. Financ.
Autoregressive conditional volatility, skewness and kurtosis
Q. Rev. Econ. Finance
A dynamic view to moment matching of truncated distributions
Statist. Probab. Lett.
Unfolded GARCH models
J. Econom. Dynam. Control
A new GARCH model with higher moments for stock return predictability
J. Int. Financ. Mark. Inst. Money
Multivariate moments expansion density: application of the dynamic equicorrelation model
J. Bank. Financ.
Option pricing where the underlying assets follow a Gram/Charlier density of arbitrary order
J. Econom. Dynam. Control
Forecasting var using realized EGARCH model with skewness and kurtosis
Finance Res. Lett.
Threshold heteroskedastic models
J. Econom. Dynam. Control
Modeling and forecasting expected shortfall with the generalized asymmetric Student-t and asymmetric exponential power distributions
J. Empir. Financ.
Value at risk and expected shortfall based on Gram–Charlier-like expansions
J. Bank. Financ.
Normal mixture GARCH (1, 1): Applications to exchange rate modelling
J. Appl. Econometrics
Computation of the corrected Cornish–Fisher expansion using the response surface methodology: application to VaR and CVaR
Ann. Oper. Res.
Comparing density forecasts via weighted likelihood ratio tests
J. Bus. Econom. Statist.
Uncovering the skewness news impact curve
J. Financ. Econom.
Superstitious seasonality in precious metals markets? Evidence from GARCH models with time-varying skewness and kurtosis
Appl. Econ.
The role of orthogonal polynomials in adjusting hyperbolic secant and logistic distributions to analyse financial asset returns
Statist. Papers
Expansions for nearly Gaussian distributions
Astron. Astrophys. Suppl. Ser.
Tail index of an AR (1) model with ARCH (1) errors
Econom. Theory
Interval estimation of the tail index of a GARCH (1, 1) model
Test
Elements of Financial Risk Management
Is the potential for international diversification disappearing? A dynamic copula approach
Rev. Financ. Stud.
The hidden martingale restriction in Gram–Charlier option prices
J. Futures Mark.
Skewness and kurtosis in S & P 500 index returns implied by option prices
J. Financ. Res.
Cited by (5)
Analysis of Safe Storage of Network Information Data and Financial Risks Under Blockchain Combined With Edge Computing
2022, Journal of Global Information ManagementA Risk Feature Recognition Method of Cross-Border Financial Derivatives' Transaction Based on Fuzzy Support Vector Machine
2022, Mobile Information SystemsModified variance incorporating high-order moments in risk measure with Gram-Charlier returns
2022, Engineering Economist