|
Activity Number:
|
594
- Spatial Risk Assessment with Environmental Applications
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 3, 2017 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
|
Abstract #324640
|
View Presentation
|
|
Title:
|
Copula-Based Semiparametric Models for Spatial-Temporal Data
|
|
Author(s):
|
Huixia Judy Wang* and Yanlin Tang and Ying Sun
|
|
Companies:
|
The George Washington University and George Washington University and King Abdullah University of Science and Technology
|
|
Keywords:
|
copula ;
Markov process ;
spatio-temporal
|
|
Abstract:
|
We propose a copula-based semiparametric model for analyzing stationary spatial-temporal data. The semiparametric model is characterized by nonparametric marginal distribution at each location and parametric copula functions that capture the temporal and spatial dependence. We provide a nonparametric estimator for the marginal distribution and a pseudo maximum likelihood estimator for the copula parameters, and propose methods for prediction and forecasting. The asymptotic properties of the proposed estimators are established. The finite sample performance of the proposed method is assessed by simulation and real data analysis.
|
Authors who are presenting talks have a * after their name.
