Activity Number:
|
474
- Nonparametric Density and Variance Estimation
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 2, 2017 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Nonparametric Statistics
|
Abstract #324251
|
|
Title:
|
Nonparametric Estimation of a Variance Function with Shape Restrictions
|
Author(s):
|
Soo Young Kim* and Haonan Wang and Mary Meyer
|
Companies:
|
Colorado State University and Colorado State University and Colorado State University
|
Keywords:
|
Nonparametric regression ;
shape restrictions ;
variance estimation
|
Abstract:
|
We consider the problem of estimating a shape-restricted variance function in a heteroscedastic regression model. The proposed method uses regression splines with shape constraints for estimation of the variance function. The method is based on the maximum likelihood principle, and its computation is carried out through the convex programming. The convergence rate of the spline approximant is derived, and the same optimal rate is preserved as an unconstrained spline approximant. Simulation results show that our proposed method is comparable or outperforms existing methods under various settings. In addition, the application of the method is illustrated through the analysis of real datasets.
|
Authors who are presenting talks have a * after their name.