JSM 2012 Home

JSM 2012 Online Program

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

Online Program Home

Abstract Details

Activity Number: 504
Type: Contributed
Date/Time: Wednesday, August 1, 2012 : 10:30 AM to 12:20 PM
Sponsor: Section on Nonparametric Statistics
Abstract - #305715
Title: A Single Pass Smoothness Parameter Selection in the Estimation of the Pair Correlation Function for Spatial Point Processes
Author(s): Ivan Simeonov*+ and Francesca Chiaromonte and John Fricks
Companies: Penn State University and Penn State University and Penn State University
Address: 326 Thomas Building, University Park, PA, 16802, United States
Keywords: Spatial Point Processes ; Pair Correlation Function ; Local Polynomial regression ; Smoothing Splines ; B-Splines

The pair correlation function is a useful exploratory summary in the analysis of spatial point patterns. The estimation is performed nonparametrically using kernel smoothing methods. Selection of the bandwidth balances the trade-off between bias and variance and can substantially affect the final results of the estimation. Having an objective and data driven technique to select the bandwidth which works effectively for a broad range of point processes underlying the data is crucial. Recently, several data driven methods have been developed for selecting the bandwidth in the context of the pair correlation function estimation. As reported in the literature, the methods work well for small point pattern datasets(< 1000 points), however they can be computationally prohibitive for larger point patterns(>10000 points). We propose a procedure for estimating the pair correlation function that is both computationally feasible and accurate when applied to these datasets. We show the performance of the approach through a simulation study. We also applied the method to study the response of human epithelial cells to sequential infections with human respiratory syncytial virus strains A and B.

The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2012 program

2012 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.