Estimation and application of semiparametric stochastic volatility models based on kernel density estimation and hidden Markov models. (English) Zbl 1414.62418
Summary: Discrete-time stochastic volatility models play a key role in the analysis of financial time series. However, the parametric assumption of conditional distribution for asset returns, given the volatility, has been questioned. When the conditional distribution is unknown and unspecified, in this paper, a maximum-likelihood estimation approach for the semiparametric stochastic volatility models is proposed based on kernel density estimation and hidden Markov models. Several numerical studies are conducted to evaluate the finite sample performance of the proposed estimation method. Implementation on empirical studies also illustrates the validity of the proposed method in practice.
MSC:
| 62P05 | Applications of statistics to actuarial sciences and financial mathematics |
| 62M05 | Markov processes: estimation; hidden Markov models |
| 62G07 | Density estimation |
| 62M10 | Time series, auto-correlation, regression, etc. in statistics (GARCH) |
| 91G30 | Interest rates, asset pricing, etc. (stochastic models) |
Keywords:
forward algorithm; hidden Markov model; kernel density estimation; numerical integration; stochastic volatility modelsReferences:
| [1] | TaylorSJ. Financial returns modelled by the product of two stochastic processes‐a study of the daily sugar prices, 1961‐79. In: AndersonOD (ed.), ed. Time Series Analysis: Theory and Practice, vol. 1. Amsterdam: North‐Holland Publishing Company; 1982:203‐206. |
| [2] | ChibS, NardariF, ShephardN. Markov chain Monte Carlo methods for stochastic volatility models. J Econ. 2002;108(2):281‐316. · Zbl 1099.62539 |
| [3] | LangrockR, KneibT, SohnA, DeRuiterSL. Nonparametric inference in hidden Markov models using P‐splines. Biometrics. 2015;71(2):520‐528. · Zbl 1390.62045 |
| [4] | Barndorff‐NielsenOE. Normal inverse Gaussian distributions and stochastic volatility modelling. Scand J Stat. 1997;24(1):1‐13. · Zbl 0934.62109 |
| [5] | MahieuR, SchotmanP. An empirical application of stochastic volatility models. J Appl Econ. 1998;13(4):333‐360. |
| [6] | Abanto‐ValleCA, BandyopadhyayD, LachosVH, EnriquezI. Robust Bayesian analysis of heavy‐tailed stochastic volatility models using scale mixtures of normal distributions. Comput Stat Data Anal. 2010;54(12):2883‐2898. · Zbl 1284.91579 |
| [7] | JacquierE, PolsonNG, RossiPE. Bayesian analysis of stochastic volatility models with fat‐tails and correlated errors. J Econ. 2004;122(1):185‐212. · Zbl 1328.91254 |
| [8] | NakajimaJ, OmoriY. Stochastic volatility model with leverage and asymmetrically heavy‐tailed error using GH skew Student’s t‐distribution. Comput Stat Data Anal. 2012;56(11):3690‐3704. · Zbl 1255.62319 |
| [9] | BandiFM, RenòR. Time‐varying leverage effects. J Econ. 2012;169(1):94‐113. · Zbl 1443.62330 |
| [10] | YuJ. On leverage in a stochastic volatility model. J Econ. 2005;127(2):165‐178. · Zbl 1335.91116 |
| [11] | YuJ. A semiparametric stochastic volatility model. J Econ. 2012;167(2):473‐482. · Zbl 1441.62909 |
| [12] | JensenMJ, MaheuJM. Bayesian semiparametric stochastic volatility modeling. J Econ. 2010;157(2):306‐316. · Zbl 1431.62477 |
| [13] | DelatolaEI, GriffinJE. Bayesian nonparametric modelling of the return distribution with stochastic volatility. Bayesian Anal. 2011;6(4):901‐926. · Zbl 1330.62116 |
| [14] | DelatolaEI, GriffinJE. A Bayesian semiparametric model for volatility with a leverage effect. Comput Stat Data Anal. 2013;60:97‐110. · Zbl 1366.62195 |
| [15] | ElabedAG, MasmoudiA. Bayesian estimation of non‐Gaussian stochastic volatility models. JMF. 2014;4:95‐103. |
| [16] | XuL, LiuC, NieG. Bayesian estimation and the application of long memory stochastic volatility models. Stat Methodol. 2006;3(4):483‐489. · Zbl 1248.62162 |
| [17] | LangrockR, MacDonaldIL, ZucchiniW. Some nonstandard stochastic volatility models and their estimation using structured hidden Markov models. JEF. 2012;19(1):147‐161. |
| [18] | NadarayaEA. Some new estimates for distribution functions. Theory Probab Appl. 1964;9(3):497‐500. · Zbl 0152.17605 |
| [19] | AndersenTG, SørensenBE. GMM estimation of a stochastic volatility model: a Monte Carlo study. J Bus Econ Stat. 1996;14(3):328‐352. |
| [20] | HansenLP. Large sample properties of generalized method of moments estimators. Econometrica. 1982;50(4):1029‐1054. · Zbl 0502.62098 |
| [21] | TaylorSJ. Modelling Financial Time Series. New York, NY: John Wiley & Sons; 1986. · Zbl 1130.91345 |
| [22] | HarveyA, RuizE, ShephardN. Multivariate stochastic variance models. Rev Econ Stud. 1994;61(2):247‐264. · Zbl 0805.90026 |
| [23] | GourierouxC, MonfortA, RenaultE. Indirect inference. J Appl Econ. 1993;8(S1):S85‐S118. |
| [24] | JarquierE, PolsonN, RossiP. Bayesian analysis of stochastic volatility models (with discussion). J Bus Econ Stat. 1994;12(4):371‐417. |
| [25] | DanielssonJ. Stochastic volatility in asset prices estimation with simulated maximum likelihood. J Econ. 1994;64(1):375‐400. · Zbl 0825.62953 |
| [26] | FridmanM, HarrisL. A maximum likelihood approach for non‐Gaussian stochastic volatility models. J Bus Econ Stat. 1998;16(3):284‐291. |
| [27] | BartolucciF, De LucaG. Maximum likelihood estimation of a latent variable time-series model. Appl Stochastic Models Bus Ind. 2001;17(1):5‐17. · Zbl 0965.62071 |
| [28] | LangrockR, MichelotT, SohnA, KneibT. Semiparametric stochastic volatility modelling using penalized splines. Comput Stat. 2015;30(2):517‐537. · Zbl 1317.65038 |
| [29] | YeXG, LinJG, ZhaoYY, HaoHX. Two‐step estimation of the volatility function in diffusion models with empirical applications. JEF. 2015;33(4):135‐159. |
| [30] | LangrockR. Some applications of nonlinear and non‐Gaussian state-space modelling by means of hidden Markov models. J Appl Stat. 2011;38(12):2955‐2970. · Zbl 1511.62225 |
| [31] | HansenBE. Bandwidth selection for nonparametric distribution estimation. manuscript, University of Wisconsin; 2004. |
| [32] | RosenblattM. Remarks on a multivariate transformation. Ann Math Stat. 1952;23(3):470‐472. · Zbl 0047.13104 |
| [33] | ZucchiniW, MacDonaldIL. Hidden Markov Models for Time Series: An Introduction Using R. Boca Raton, FL: CRC Press; 2009. · Zbl 1180.62130 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
