Date of Award
8-2015
Document Type
Thesis
Degree Name
Master of Science (MS)
Legacy Department
Mathematical Science
Committee Chair/Advisor
Luo, Jun
Committee Member
Gerard, Patrick
Committee Member
Bridges, William
Abstract
Nonparametric regression has been particularly well developed. Base on the asymptotic equivalence theory, there are some procedures that can turn more complicated nonparametric estimation problems into a standard nonparametric regression, especially in natural exponential families. This procedure is described in detail with a wavelet thresholding estimator for Gaussian nonparametric regression and simulation study shed light on the behavior of this method under different sample sizes and parameterizations of exponential distribution. The resulting estimators have a high degree of adaptivity in [2].
Recommended Citation
CHEN, YIJUN, "Nonparametric Regression In Natural Exponential Families: A Simulation Study" (2015). All Theses. 2204.
https://tigerprints.clemson.edu/all_theses/2204