Journal of the Korean Statistical Society

The Korean Statistical Society (한국통계학회)
권호 표지

Kernel Density Estimation in the L$^{\infty}$ Norm under Dependence

  • Kim, Tae-Yoon (Department of Mathematics and Statistics, Keimyung University)
  • Published : 1998.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

We investigate density estimation problem in the L$^{\infty}$ norm and show that the iii optimal minimax rates are achieved for smooth classes of weakly dependent stationary sequences. Our results are then applied to give uniform convergence rates for various problems including the Gibbs sampler.

Keywords

References

  1. Michigan Math. J. v.30 Approzimation theorems for strongly mixing random variables Bradley, R. C.
  2. IEEE TRANS. Pattern Analysis and Machine Intelligence v.6 Stochastic relaxation, Gibbs distributions, and the Baysean restoration of image Geman, S;Geman, D.
  3. Independent and Stationary Sequences of Random Variables Ibragimov, I.A.;Linnik, Y.A.
  4. Proceedigns of Mathematical Sciences, Institute of Mathecal Sciences A remark on optimal rates ofr kernel desity estimation in the $L^∞$norm under mising Kim, T.Y.
  5. Technical Report 304 Dept. Statistics Correlation structure and convergence rate of the Gibbs sampler with vatious scans Liu, J.;Wong, W.;Kong, A.
  6. Stochastic Process. Appl. v.29 Mixing properties of ATMA processes Mokkadem, A.
  7. Recent Advances in Statistics Optimal uniform rate of convergence for nonparametric estimators of density function or its derivatives Stone, C. J.
  8. Statist. Probab. Lett. v.10 Kernel density estimation under dependence Tran. L.T.
  9. Ann. Statist. v.21 Density estimation in the $L^∞$ norm for dependent data with applications to the Gibbs sampler Yu, B.