Nonparametric variance function estimation with missing data

Authors:
A. Pérez-González;J. M. Vilar-Fernández;W. González-Manteiga
Affiliations:
Department of Statistics and Operations Research, University of Vigo, Faculty of Business Sciences, Campus South, Ourense, 32004, Spain;Department of Mathematics, University of A Coruña, Faculty of Computer Sciences, Campus de Elviña, A Coruña, Spain;Department of Statistics and Operations Research, University of Santiago de Compostela, Faculty of Mathematics, Campus South, Santiago de Compostela, Spain
Venue:
Journal of Multivariate Analysis
Year:
2010

Citing 7
Cited 0

Time series: theory and methods

Time series: theory and methods
Statistical analysis with missing data

Statistical analysis with missing data
Transformation and weighting in regression

Transformation and weighting in regression
Signal-to-noise ratios, performance criteria, and transformations

Technometrics
Local polynomial variance-function estimation

Technometrics
Resampling for checking linear regression models via non-parametric regression estimation

Computational Statistics & Data Analysis
A time series bootstrap procedure for interpolation intervals

Computational Statistics & Data Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a fixed design regression model where the errors follow a strictly stationary process is considered. In this model the conditional mean function and the conditional variance function are unknown curves. Correlated errors when observations are missing in the response variable are assumed. Four nonparametric estimators of the conditional variance function based on local polynomial fitting are proposed. Expressions of the asymptotic bias and variance of these estimators are obtained. A simulation study illustrates the behavior of the proposed estimators.