Facultade de Fisioterapia

Convergence rate of wavelet density estimator with data missing randomly when covariables are present

Zou, Yu-Ye; Liang, Han-Ying
Abstract:
In this article, we study global L2 error of non linear wavelet estimator of density in the Besov space Bspq for missing data model when covariables are present and prove that the estimator can achieve the optimal rate of convergence, which is similar to the result studied by Donoho et al. (1996) in complete independent data case with term-by-term thresholding of the empirical wavelet coefficients. Finite-sample behavior of the proposed estimator is explored via simulations.
Year:
2017
Type of Publication:
Article
Journal:
Communications in Statistics - Theory and Methods
Volume:
46
Number:
2
Pages:
1007-1023
Month:
January
DOI:
https://doi.org/10.1080/03610926.2015.1010008
Hits: 1194