Skip to content
Licensed Unlicensed Requires Authentication Published by De Gruyter February 2, 2021

Body tail adaptive kernel density estimation for nonnegative heavy-tailed data

Yasmina Ziane, Nabil Zougab and Smail Adjabi

Abstract

In this paper, we consider the procedure for deriving variable bandwidth in univariate kernel density estimation for nonnegative heavy-tailed (HT) data. These procedures consider the Birnbaum–Saunders power-exponential (BS-PE) kernel estimator and the bayesian approach that treats the adaptive bandwidths. We adapt an algorithm that subdivides the HT data set into two regions, high density region (HDR) and low-density region (LDR), and we assign a bandwidth parameter for each region. They are derived by using a Monte Carlo Markov chain (MCMC) sampling algorithm. A series of simulation studies and real data are realized for evaluating the performance of a procedure proposed.

MSC 2010: 62G07; 62G99

References

[1] D. K. Bhaumik, K. Kapur and R. D. Gibbons, Testing parameters of a gamma distribution for small samples, Technometrics 51 (2009), no. 3, 326–334. 10.1198/tech.2009.07038Search in Google Scholar

[2] T. Bjerkedal, Acquisition of resistance in guinea pigs infected with different doses of virulent tubercle bacilli, Amer. J. Hygiene 72 (1960), 130–148. Search in Google Scholar

[3] M. J. Brewer, A Bayesian model for local smoothing in kernel density estimation, Stat. Comput. 10 (2000), 299–309. 10.1023/A:1008925425102Search in Google Scholar

[4] S. X. Chen, Gamma kernel estimators for density functions, Ann. Inst. Statist. Math. 52 (2000), 471–480. 10.1023/A:1004165218295Search in Google Scholar

[5] D. Hinkley, On quick choice of power transformations, J. R. Stat. Soc. Ser. C. Appl. Stat. 26 (1977), no. 1, 67–69. 10.2307/2346869Search in Google Scholar

[6] M. S. de Lima and G. S. Atuncar, A Bayesian method to estimate the optimal bandwidth for multivariate kernel estimator, J. Nonparametr. Stat. 23 (2011), no. 1, 137–148. 10.1080/10485252.2010.485200Search in Google Scholar

[7] A. K. Gangopadhyay and K. N. Cheung, Bayesian approach to the choice of smoothing parameter in kernel density estimation, J. Nonparametr. Stat. 14 (2002), no. 6, 655–664. 10.1080/10485250215320Search in Google Scholar

[8] A. Gelman and D. B. Rubin, Inference from iterative simulation using multiple sequences, Stat. Sci. 7 (1992), 457–511. 10.1214/ss/1177011136Search in Google Scholar

[9] W. K. Hastings, Monte Carlo sampling methods using Markov chains and their applications, Biometrika 57 (1970), no. 1, 97–109. 10.1093/biomet/57.1.97Search in Google Scholar

[10] S. Hu, D. S. Poskitt and X. Zhang, Bayesian adaptive bandwidth kernel density estimation of irregular multivariate distributions, Comput. Statist. Data Anal. 56 (2012), no. 3, 732–740. 10.1016/j.csda.2011.09.022Search in Google Scholar

[11] X. Jin and J. Kawczak, Birnbaum–Saunders and lognormal kernel estimators for modelling durations in high frequency financial data, Ann. Econ. Finance 4 (2003), 103–124. Search in Google Scholar

[12] C. C. Kokonendji and F. G. Libengué, Méthode des noyaux associés continus et estimation de densité, Les 43èmes Journées de Statistique ont eu lieu à Tunis (Tunisie 2011), Société Française de Statistique, Paris (2011), 86–91. Search in Google Scholar

[13] K. B. Kulasekera and W. J. Padgett, Bayes bandwidth selection in kernel density estimation with censored data, J. Nonparametr. Stat. 18 (2006), no. 2, 129–143. 10.1080/10485250600556744Search in Google Scholar

[14] D. Kundu, N. Kannan and N. Balakrishnan, On the hazard function of Birnbaum-Saunders distribution and associated inference, Comput. Statist. Data Anal. 52 (2008), no. 5, 2692–2702. 10.1016/j.csda.2007.09.021Search in Google Scholar

[15] C. N. Kuruwita, K. B. Kulasekera and W. J. Padgett, Density estimation using asymmetric kernels and Bayes bandwidths with censored data, J. Statist. Plann. Inference 140 (2010), no. 7, 1765–1774. 10.1016/j.jspi.2010.01.001Search in Google Scholar

[16] C. Marchant, K. Bertin, V. Leiva and H. Saulo, Generalized Birnbaum–Saunders kernel density estimators and an analysis of financial data, Comput. Statist. Data Anal. 63 (2013), 1–15. 10.1016/j.csda.2013.01.013Search in Google Scholar

[17] N. M. Markovitch and U. R. Krieger, The estimation of heavy-tailed probability density functions, their mixtures and quantiles, Computer Networks 40 (2002), 459–474. 10.1016/S1389-1286(02)00306-7Search in Google Scholar

[18] N. Metropolis, A. W. Rosenbluth, M. N. Rosenbluth, A. H. Teller and E. Teller, Equation of state calculations by fast computing machine, J. Chemical Phys. 21 (1953), 1087–1093. 10.2172/4390578Search in Google Scholar

[19] A. E. Raftery and S. Lewis, How many iterations in the Gibbs sampler?, Bayesian Stat. 4 (1992), 763–773. 10.21236/ADA640705Search in Google Scholar

[20] G. O. Roberts, Markov chain concepts related to sampling algorithms, Markov Chain Monte Carlo in Practice, Interdiscip. Statist., Chapman & Hall, London (1996), 45–57. Search in Google Scholar

[21] O. Scaillet, Density estimation using inverse and reciprocal inverse Gaussian kernels, J. Nonparametr. Stat. 16 (2004), no. 1–2, 217–226. 10.1080/10485250310001624819Search in Google Scholar

[22] Y. Ziane, S. Adjabi and N. Zougab, Adaptive Bayesian bandwidth selection in asymmetric kernel density estimation for nonnegative heavy-tailed data, J. Appl. Stat. 42 (2015), no. 8, 1645–1658. 10.1080/02664763.2015.1004626Search in Google Scholar

[23] Y. Ziane, N. Zougab and S. Adjabi, Birnbaum-Saunders power-exponential kernel density estimation and Bayes local bandwidth selection for nonnegative heavy tailed data, Comput. Statist. 33 (2018), no. 1, 299–318. 10.1007/s00180-017-0712-8Search in Google Scholar

[24] N. Zougab, S. Adjabi and C. C. Kokonendji, Binomial kernel and Bayes local bandwidth in discrete function estimation, J. Nonparametr. Stat. 24 (2012), no. 3, 783–795. 10.1080/10485252.2012.678847Search in Google Scholar

[25] N. Zougab, S. Adjabi and C. C. Kokonendji, Adaptive smoothing in associated kernel discrete functions estimation using Bayesian approach, J. Stat. Comput. Simul. 83 (2013), no. 12, 2219–2231. 10.1080/00949655.2012.686615Search in Google Scholar

[26] N. Zougab, S. Adjabi and C. C. Kokonendji, Bayesian estimation of adaptive bandwidth matrices in multivariate kernel density estimation, Comput. Statist. Data Anal. 75 (2014), 28–38. 10.1016/j.csda.2014.02.002Search in Google Scholar

Received: 2019-02-28
Revised: 2020-12-10
Accepted: 2021-01-12
Published Online: 2021-02-02
Published in Print: 2021-03-01

© 2021 Walter de Gruyter GmbH, Berlin/Boston