×

A goodness-of-fit test based on Bézier curve estimation of Kendall distribution. (English) Zbl 07194334

Summary: In this study, we propose an estimation method for the Archimedean family of the copula in a nonparametric setting. A Bézier curve approach based on Bernstein polynomials is used to estimate the Kendall distribution function. Also, a new goodness-of-fit test based on Cramér-von Mises statistic is proposed using the Bézier curve estimator. A Monte Carlo study is also conducted to measure the performance of the proposed estimator and goodness-of-fit test. Two real data examples are also given. The simulation study and real data applications show that the Bézier curve estimator leads to satisfactory estimates of underlying copula and also has better results compared with the estimators based on empirical and Bernstein methods.

MSC:

62F03 Parametric hypothesis testing
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Deheuvels P.Caracterisation complete des lois extremes multivariees et de la convergence des types extremes. Publ Inst Stat Univ Paris. 1978;3:1-36. [Google Scholar] · Zbl 0414.60043
[2] Genest C, Molina JJQ, Lallena JAR.De l’impossibilité de construire des lois á marges multidimensionnelles données á partir de copules. C R Acad Sci Paris. 1995;320:723-726. [Google Scholar] · Zbl 0832.60020
[3] Joe H, Xu JJ. The estimation method of inference functions for margins for multivariate models. Vancouver: Department of Statistics, University of British Columbia; 1996. p. 166. [Google Scholar]
[4] Joe H. Multivariate models and dependence concepts, monographs on statistics and applied probability. London: Chapmann and Hall; 1997. [Crossref], [Google Scholar] · Zbl 0990.62517
[5] Fermanian JD, Radulovic D, Wegkamp M.Weak convergence of empirical copula processes. Bernoulli. 2004;10:847-860. doi: 10.3150/bj/1099579158[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1068.62059
[6] Plackett RT.A class of bivariate distributions. J Am Stat Assoc. 1965;60:516-522. doi: 10.1080/01621459.1965.10480807[Taylor & Francis Online], [Web of Science ®], [Google Scholar]
[7] Clayton DG.A model for association in bivariate life tables and its application in epidemiological studies of familial tendency in chronic disease incidence. Biometrika. 1978;65:141-151. doi: 10.1093/biomet/65.1.141[Crossref], [Web of Science ®], [Google Scholar] · Zbl 0394.92021
[8] Frank MJ.On the simultaneous associativity of ##img####img####img##F(x,y) and ##img####img####img##x+y−F(x,y). Æquationes Mathematiæ. 1979;19:194-226. doi: 10.1007/BF02189866[Crossref], [Google Scholar] · Zbl 0444.39003
[9] Gumbel EJ.Distributios des valeurs extrémes en plusiers dimensions. Publ Inst Stat Univ Paris. 1960;9:171-173. [Google Scholar] · Zbl 0093.15303
[10] Cook RD, Johnson ME.A family of distributions for modelling non-elliptically symmetric multivariate data. J R Stat Soc B. 1981;43:210-218. [Google Scholar] · Zbl 0471.62046
[11] Oakes D.A model for association in bivariate survival data. J R Stat Soc B. 1982;44:414-422. [Google Scholar] · Zbl 0503.62035
[12] Oakes D.Bivariate survival models induced by frailties. J Am Stat Assoc. 1989;84:487-493. doi: 10.1080/01621459.1989.10478795[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 0677.62094
[13] Tawn JA.Bivariate extreme value theory: models and estimation. Biometrika. 1988;75:397-415. doi: 10.1093/biomet/75.3.397[Crossref], [Web of Science ®], [Google Scholar] · Zbl 0653.62045
[14] Genest C, MacKay RJ.Copules archimediennes et families de lois bidimensionelles dont les marges sont donnees. Can J Stat. 1986;14:145-159. doi: 10.2307/3314660[Crossref], [Web of Science ®], [Google Scholar] · Zbl 0605.62049
[15] Nelsen RB. An introduction to copulas. New York: Springer; 2006. [Google Scholar] · Zbl 1152.62030
[16] Genest C, Rivest LP.Statistical inference procedures for bivariate Archimedean copulas. J Am Stat Assoc. 1993;88:1034-1043. doi: 10.1080/01621459.1993.10476372[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 0785.62032
[17] Lambert P.Archimedean copula estimation using Bayesian splines smoothing techniques. Comput Stat Data Anal. 2007;51:6307-6320. doi: 10.1016/j.csda.2007.01.018[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1445.62105
[18] Dimitrova DS, Kaishev VK, Penev SI.GeD spline estimation of multivariate Archimedean copulas. Comput Stat Data Anal. 2008;52:3570-3582. doi: 10.1016/j.csda.2007.11.010[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1452.62347
[19] Susam SO, Ucer BH.Testing independence for Archimedean copula based on Bernstein estimate of Kendall distribution function. J Stat Comput Simul. 2018;88:2589-2599. doi: 10.1080/00949655.2018.1478978[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 07192676
[20] Diebold FX, Hahn J, Tay AS.Multivariate density forecast and calibration in financial risk management: high-frequency returns on foreign exchange. Rev Econ Stat. 1999;81(4):661-673. doi: 10.1162/003465399558526[Crossref], [Web of Science ®], [Google Scholar]
[21] Berkowitz J.Testing density forecasts, with applications to risk management. J Bus Econ Stat. 2001;19:465-474. doi: 10.1198/07350010152596718[Taylor & Francis Online], [Web of Science ®], [Google Scholar]
[22] Breymann W, Dias A, Embrechts P.Dependence structures for multivariate high-frequency data in finance. Quant Finance. 2003;3:1-14. doi: 10.1080/713666155[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1408.62173
[23] Rosenblatt M.Remarks on a multivariate transformation. Ann Math Stat. 1952;23:470-472. doi: 10.1214/aoms/1177729394[Crossref], [Google Scholar] · Zbl 0047.13104
[24] Genest C, Quessy JF, Rémillard B.Goodness-of-fit procedures for copula models based on the probability integral transform. Scand J Stat. 2006;33:337-366. doi: 10.1111/j.1467-9469.2006.00470.x[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1124.62028
[25] Berg D.Copula goodness-of-fit testing: an overview and power comparison. Eur J Finance. 2009;15:675-701. doi: 10.1080/13518470802697428[Taylor & Francis Online], [Web of Science ®], [Google Scholar]
[26] Nelsen RB, Quesada-Molina JJ, Rodríguez-Lallena JA, et al. Kendall distribution functions and associative copulas. Fuzzy Sets Syst. 2009;160:52-57. doi: 10.1016/j.fss.2008.05.001[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1183.60006
[27] Babu GJ, Canty AJ, Chaubey YP.Application of Bernstein polynomials for smooth estimation of a distribution and density function. J Stat Plan Inference. 2002;105:377-392. doi: 10.1016/S0378-3758(01)00265-8[Crossref], [Web of Science ®], [Google Scholar] · Zbl 0992.62038
[28] Leblanc A.On estimating distribution functions using Bernstein polynomials. Ann Inst Stat Math. 2012;64:919-943. doi: 10.1007/s10463-011-0339-4[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1254.62042
[29] Oruc EO, Erdogan MS, Oruc H.Probabilistic approach to the Schoenberg spline operator and unimodal density estimator. ISTATISTIK, J Tur Stat Assoc. 2017;10:33-39. [Google Scholar] · Zbl 1420.62162
[30] Kaishev V, Dimitrova D, Haberman S. Geometrically designed, variable knot regression splines: asymptotics and inference. London, UK: Faculty of Actuarial Science & Insurance, City University London; 2006. [Google Scholar] · Zbl 1347.65020
[31] Kojadinovic I, Yan J.Comparison of three semiparametric methods for estimating dependence parameters in copula models. Insurance: Math Econ. 2010;47:52-63. [Crossref], [Web of Science ®], [Google Scholar] · Zbl 1231.62044
[32] Weiss G.Copula parameter estimation by maximum-likelihood and minimum-distance estimators: a simulation study. Comput Stat. 2011;26:31-54. doi: 10.1007/s00180-010-0203-7[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1304.65089
[33] Frees EW, Valdez EA.Understanding relationships using copulas. N Am Actuar J. 1998;2:1-25. doi: 10.1080/10920277.1998.10595667[Taylor & Francis Online], [Google Scholar] · Zbl 1081.62564
[34] Michiels F, Koch I, De Schepper A.How to improve the fit of Archimedean copulas by means of transforms. Stat Papers. 2012;53:345-355. doi: 10.1007/s00362-010-0341-6[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1440.62188
[35] Michiels F, Schepper A.A new graphical tool for copula selection. J Comput Graph Stat. 2013;22:471-493. doi: 10.1080/10618600.2012.672080[Taylor & Francis Online], [Web of Science ®], [Google Scholar]
[36] Gayraud G, Tribouley K.A test of goodness-of-fit for the copula densities. Test. 2011;20:549-573. doi: 10.1007/s11749-010-0217-z[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1367.62142
[37] Genest C, Ghoudi K, Rivest LP.Comment on “Understanding relationships using copulas,” by Edward W. Frees and Emiliano A. Valdez, January 1998. N Am Actuar J. 1998;2:143-149. doi: 10.1080/10920277.1998.10595749[Taylor & Francis Online], [Google Scholar]
[38] Klugman SA, Parsa R.Fitting bivariate loss distributions with copulas. Insurance Math Econ. 1999;24:139-148. doi: 10.1016/S0167-6687(98)00039-0[Crossref], [Web of Science ®], [Google Scholar] · Zbl 0931.62044
[39] Chen X, Fan Y.Pseudo-likelihood ratio tests for semiparametric multivariate copula model selection. Can J Stat. 2005;33:389-414. doi: 10.1002/cjs.5540330306[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1077.62032
[40] Najjari V, Bacigal T, Bal H.An archimedean copula family with hyperbolic cotangent generator. Int J Uncertainty Fuzziness Knowledge Based Syst. 2014;22(5):761-768. doi: 10.1142/S0218488514500391[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1323.62043
[41] Duncan M. Applied geometry for computer graphics and CAD. London: Springer; 2005. [Crossref], [Google Scholar] · Zbl 1061.68170
[42] Lorentz GG. Bernstein polynomials. Second Ed. New York (N.Y.): Chelsea Publishing Company; 1986. [Google Scholar] · Zbl 0989.41504
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.