Estimating Cumulative Distribution Function Using Gamma Kernel

Document Type : Original Research Articles

Authors
Behzad Mansouri
Sami Atiyah Sayyid Al-Farttosi
Habiballah Mombeni
Rahim Chinipardaz
Department of Statistics, Faculty of Mathematical Sciences and Computer, Shahid Chamran University of Ahvaz, Ahvaz, Islamic Republic of Iran
10.22059/jsciences.2021.324868.1007652
Abstract
In this article, we propose the gamma kernel estimator for the cumulative distribution functions with nonnegative support. We derive the asymptotic bias and variance of the proposed estimator in both boundary and interior regions and show that it is free of boundary bias. We also obtain the optimal smoothing parameter which minimizes the mean integrated square error (MISE). In addition to consistency, we prove the almost sure convergence of the proposed estimator and show that it follows the same approximate normal distribution as empirical distribution. We presented a simulation study to compare the performance of the proposed estimator with other estimators. We use the proposed estimator to estimate the cumulative probability distribution function of the food expenses for urban households in Iran.
Keywords
Asymmetric kernels
Cumulative distribution
Boundary problem
Almost sure convergence
Subjects
  1. Steutel FW, Van Harn K. Discrete analogues of self-decomposability and stability. Ann Probab. 1979; 7(5): 893–899.
  2. McKenzie E. Some simple models for discrete variate time series. J Am Water Resour Assoc. 1985; 21(4):  645–650.
  3. Al-Osh MA, Alzaid AA. First-order interger-valued autoregressive (INAR(1)) process. J Time Ser Anal. 1987; 8(3): 261–275.
  4. Johnson NL, Kemp AW, Kotz S. Univariate Discrete distributions. New York: John Wiley & Sons; 2005.
  5. Al-Osh MA, Alzaid AA. Integer-valued moving average (INMA) process. Stat Pap. 1988; 29: 281–300.
  6. Weiß CH. Thinning operations for modeling time series of counts – a survey. Adv Stat Anal. 2008; 92: 319–341.
  7. Bourguignon M. Poisson-geometric INAR(1) process for modelling count time series with overdispersion, Neerl. 2016; 70(3): 176–192.
  8. Weiß CH. Controlling jumps in correlated processes of Poisson counts. Appl Stoch Models Bus Ind. 2009; 25(5): 551–
  9. Weiß CH. Modelling time series of counts with overdispersion. Stat Methods Appl. 2009; 18(4): 507–519.
  10. Jazi MA, Jones G, Lai CD. First-order integer valued AR processes with zero inflated poisson innovations. J Time Ser Anal. 2012; 33(12): 954–963.
  11. Jazi MA, Jones G, Lai CD. Integer valued AR(1) with geometric innovations. 2012; 11(2): 173–190.
  12. Barreto-Souza W. Zero-modified geometric INAR(1) process for modelling count time series with deflation or inflation of zeros. J Time Ser Anal. 2015; 36(6): 839–852.

13. Bourguignon M. Vasconcellos KLP.  First order non-negative integer valued autoregressive processes with power series innovations.  Braz J Probab Stat. 2015; 29(1): 71-93.

  1. Jose KK, Mariyamma A note on an integer valued time series model with Poisson–negative binomial marginal distribution. Commun Stat Theory Methods. 2016;45(1): 123-131.
  2. Fernández-Fontelo A, Fontdecaba S, Alba A, Puig P. Integer-valued AR processes with hermite innovations and time-varying parameters: An application to bovine fallen stock surveillance at a local scale. Stat Modelling. 2017; 17(3): 172-195.
  3. Kim H, Lee S. On first-order integer-valued autoregressive process with Katz family innovations, J Stat Comput Simul. 2017; 87(3): 546–562.
  4. Bourguignon M, Weiß CH. An INAR(1) process for modelling count time series with equidispersion, underdispersion and overdispersion. Test. 2017; 26(4): 847–868.
  5. Bourguignon M, Rodrigues J, Santos-Neto M. Extended Poisson INAR(1) processes with equidispersion, underdispersion and overdispersion, J Appl Stat. 2019; 46(1): 101-118.
  6. Barreto-Souza W. Mixed Poisson INAR(1) processes. Stat Pap. 2019; 60(3): 2119-
  7. Delaporte P. Quelques problémes de statistiquemathématique posés par Ìassurance automobile et le bonus non sinistre. Bulletin Trimestriel de l’lnstitut des Actuaires Frana̧uis. 1959; 227: 87–102.
  8. Willmot GE, Sundt B. On evaluation of the Delaporte distribution and related distributions. Scand Actuar J. 1989; 101–113.
  9. Karlsen H, Tjøstheim D. Consistent estimates for the NEAR(2) and NLAR(2) time series models. J R Stat Soc Series B Stat Methodol. 1988; 50:313–320.
  10. Klimko LA, Nelson PI. On conditional least squares estimation for stochastic processes, Ann Stat. 1978; 6(3): 629–642.
  •  

 
  • Patriota B, Bourguignon M, Santos-Neto M. Tsinteger: Time series of counts analysis, R package version 0.1. 2017.
  1. Borges P, Bourguignon M, Molinares FF. A generalized NGINAR(1) process with inflated-parameter geometric counting series. Aust N Z J Stat. 2017; 59(1): 137–150.
Journal of Sciences, Islamic Republic of Iran
Volume 33, Issue 1
Winter 2022
Pages 45-54