Skip to content
BY 4.0 license Open Access Published by De Gruyter Open Access July 4, 2020

Bayesian estimation of generalized partition of unity copulas

  • Andreas Masuhr and Mark Trede EMAIL logo
From the journal Dependence Modeling

Abstract

This paper proposes a Bayesian estimation algorithm to estimate Generalized Partition of Unity Copulas (GPUC), a class of nonparametric copulas recently introduced by [18]. The first approach is a random walk Metropolis-Hastings (RW-MH) algorithm, the second one is a random blocking random walk Metropolis-Hastings algorithm (RBRW-MH). Both approaches are Markov chain Monte Carlo methods and can cope with ˛at priors. We carry out simulation studies to determine and compare the efficiency of the algorithms. We present an empirical illustration where GPUCs are used to nonparametrically describe the dependence of exchange rate changes of the crypto-currencies Bitcoin and Ethereum.

MSC 2010: 62H05; 62H12; 62G07; 62P20; 91B05

References

[1] Baker, R. (2008). An order-statistics-based method for constructing multivariate distributions with fixed marginals. J. Multivariate Anal. 99(10), 2312–2327.10.1016/j.jmva.2008.02.019Search in Google Scholar

[2] Bariviera, A. F., M. J. Basgall, W. Hasperué, and M. Naiouf (2017). Some stylized facts of the Bitcoin market. Physica A 484, 82–90.10.1016/j.physa.2017.04.159Search in Google Scholar

[3] Bedford, T. and R. M. Cooke (2002). Vines–a new graphical model for dependent random variables. Ann. Statist. 30(4), 1031–1068.10.1214/aos/1031689016Search in Google Scholar

[4] Begušić, S., Z. Kostanjčar, H. E. Stanley, and B. Podobnik (2018). Scaling properties of extreme price fluctuations in Bitcoin markets. Physica A 510, 400–406.10.1016/j.physa.2018.06.131Search in Google Scholar

[5] Chib, S. and S. Ramamurthy (2010). Tailored randomized block MCMC methods with application to DSGE models. J. Econometrics 155(1), 19–38.10.1016/j.jeconom.2009.08.003Search in Google Scholar

[6] Diaconis, P., G. Lebeau, and L. Michel (2012). Gibbs/Metropolis algorithms on a convex polytope. Math. Z. 272(1-2), 109–129.10.1007/s00209-011-0924-5Search in Google Scholar

[7] Dou, X., S. Kuriki, G. D. Lin, and D. Richards (2016). EM algorithms for estimating the Bernstein copula. Comput. Statist. Data Anal. 93, 228–245.10.1016/j.csda.2014.01.009Search in Google Scholar

[8] Guillotte, S. and F. Perron (2012). Bayesian estimation of a bivariate copula using the Jeffreys prior. Bernoulli 18(2), 496–519.10.3150/10-BEJ345Search in Google Scholar

[9] Hu, A. S., C. A. Parlour, and U. Rajan (2019). Cryptocurrencies: Stylized facts on a new investible instrument. Financ. Manag. 48(4), 1049–1068.10.1111/fima.12300Search in Google Scholar

[10] Joe, H. (1997). Multivariate Models and Dependence Concepts. CRC Press, Boca Raton FL.Search in Google Scholar

[11] Kyriazis, N. A., K. Daskalou, M. Arampatzis, P. Prassa, and E. Papaioannou (2019). Estimating the volatility of cryptocurrencies during bearish markets by employing GARCH models. Heliyon 5(8), Article ID e02239, 8 pages.10.1016/j.heliyon.2019.e02239Search in Google Scholar PubMed PubMed Central

[12] Liu, Y. and A. Tsyvinski (2018). Risks and returns of cryptocurrency. Available at https://www.nber.org/papers/w24877.10.3386/w24877Search in Google Scholar

[13] Osterrieder, J. (2017). The statistics of Bitcoin and cryptocurrencies. Proceedings of the 2017 International Conference on Economics, Finance and Statistics, pp. 285–289. Atlantis press, Paris.10.2991/icefs-17.2017.33Search in Google Scholar

[14] Osterrieder, J. and J. Lorenz (2017). A statistical risk assessment of Bitcoin and its extreme tail behavior. Ann. Financ. Econ. 12(1), Article ID 1750003, 19 pages.10.1142/S2010495217500038Search in Google Scholar

[15] Pfeifer, D., A. Mändle, and O. Ragulina (2017). New copulas based on general partitions-of-unity and their applications to risk management (part II). Depend. Model. 5, 246–255.10.1515/demo-2017-0014Search in Google Scholar

[16] Pfeifer, D., A. Mändle, O. Ragulina, and C. Girschig (2019). New copulas based on general partitions-of-unity (part III) - the continuous case. Depend. Model. 7, 181–201.10.1515/demo-2019-0009Search in Google Scholar

[17] Pfeifer, D., A. Mändle, and O. Ragulina (2017). Data driven partition-of-unity copulas with applications to risk management. Available at https://arxiv.org/abs/1703.05047.Search in Google Scholar

[18] Pfeifer, D., H. A. Tsatedem, A. Mändle, and C. Girschig (2016). New copulas based on general partitions-of-unity and their applications to risk management. Depend. Model. 4, 123–140.10.1515/demo-2016-0006Search in Google Scholar

[19] Sancetta, A. and S. Satchell (2004). The Bernstein copula and its applications to modeling and approximations of multivariate distributions. Econom. Theory 20(3), 535–562.10.1017/S026646660420305XSearch in Google Scholar

[20] Savu, C. and M. Trede (2010). Hierarchies of Archimedean copulas. Quant. Finance 10(3), 295–304.10.1080/14697680902821733Search in Google Scholar

[21] Sinkhorn, R. (1964). A relationship between arbitrary positive matrices and doubly stochastic matrices. Ann. Math. Statist. 35(2), 876–879.10.1214/aoms/1177703591Search in Google Scholar

[22] Zhang, W., P. Wang, X. Li, and D. Shen (2018). Some stylized facts of the cryptocurrency market. Appl. Econ. 50(55), 5950–5965.10.1080/00036846.2018.1488076Search in Google Scholar

Received: 2020-02-18
Accepted: 2020-06-08
Published Online: 2020-07-04

© 2020 Andreas Masuhr et al., published by De Gruyter

This work is licensed under the Creative Commons Attribution 4.0 International License.

Downloaded on 4.2.2023 from https://www.degruyter.com/document/doi/10.1515/demo-2020-0007/html
Scroll Up Arrow