Skip to main content
eScholarship
Open Access Publications from the University of California

UC San Diego

UC San Diego Electronic Theses and Dissertations bannerUC San Diego

Nonparametric function estimation with infinite-order kernels and applications

  • Author(s): Berg, Arthur Steven
  • et al.
Abstract

Improved performance in higher-order spectral density estimation (polyspectral estimation) and density estimation of censored data is achieved using a general class of infinite-order kernels. These estimates are asymptotically less biased but with the same order of variance as compared to the classical estimators with second-order kernels. A simple, data-dependent algorithm for selecting the bandwidth is introduced and is shown to be consistent with estimating the optimal bandwidth for the infinite-order kernels. The combination of the specialized family of kernels with the new bandwidth selection algorithm yields a considerably improved density estimation procedure surpassing the performances of existing estimators using second-order kernels. Infinite- order estimators are also utilized in a secondary manner as pilot estimators in the plug-in approach for bandwidth choice in second-order kernels. Simulations illustrate the improved accuracy of the proposed estimator against other nonparametric estimators of the density, bispectrum, and hazard function. Symmetries of the auto-cumulant function of a kth-order stationary time series play an important role in polyspectral estimation, and these symmetries are derived through a connection with the symmetric group of degree k. Using theory of group representations, these symmetries are demystified and lag-window functions are symmetrized to satisfy these symmetries. A generalized Gabr-Rao optimal kernel, used to estimate general kth- order spectra, is also derived through the developed theory

Main Content
For improved accessibility of PDF content, download the file to your device.
Current View