Seminars

back Back to all Seminars

Statistics Seminar| Spatial Estimation and Inference Based on Area Aggregated Data.

Start Date: October 16, 2017
End Date: October 16, 2017

By Prof. Hsin-Cheng Huang, Academia Sinica, Taipei, Taiwan
Institute of Statistical Science, Academia Sinica, Taiwan
 
This talk contains two parts. Firstly, we consider estimation of intensity function for a spatial point pattern based on spatially aggregated count data. A standard approach for estimating the intensity function is to use a kernel estimator. However, when data are only available in a spatially aggregated form with the numbers of events available in geographical subregions, traditional methods become infeasible. In this research, a kernel-based method is proposed to produce a smooth intensity function based on aggregated data. Secondly, we consider testing a spatial signal based on data obtained by aggregating an image into several subregions. Our method utilizes a nonparametric testing procedure called enhanced false discovery rate originally developed to detect a spatial signal from an image. Some numerical examples will be given to demonstrate the effectiveness of the proposed methods.
 
Biography: Hsin-Cheng Huang is a Research Fellow in Institute of Statistical Science, Academia Sinica, Taiwan. He graduated from National Taiwan University in 1989 with a BS degree in mathematics and received his MS and PhD degrees from Iowa State University in 1994 and 1997. He has been in Academia Sinica since 1997. His main research interests include spatial statistics, spatio-temporal modeling of environmental processes, and model selection.
 

More Information:

For more info contact: Distinguished Prof. Marc Genton: email: marc.genton@kaust.edu.sa
 
Date: Monday 16th Oct 2017
Time:04:00 PM - 05:00 PM
Location: Building 1, Level4, room# 4102
Refreshments: Light refreshments to be served at 3:45 PM