JSM Preliminary Online Program
This is the preliminary program for the 2009 Joint Statistical Meetings in Washington, DC.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2009 Program page

Activity Number: 32
Type: Contributed
Date/Time: Sunday, August 2, 2009 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistics and the Environment
Abstract - #303316
Title: Significance Testing with the Pareto Set in Cluster Detection Problems
Author(s): Ronald Gangnon*+
Companies: University of Wisconsin-Madison
Address: 603 WARF, Madison, WI, 53726,
Keywords: cluster detection ; spatial scan statistic ; Pareto set ; Gumbel distribution ; Monte Carlo methods ; multiple comparisons
Abstract:

Cluster detection methods typically incorporate one or more user-specified parameters related to the (maximum) cluster complexity. For example, the circular spatial scan statistic requires the specification of a maximum cluster radius, either population or geographic. The selection of user-defined parameters is not straightforward in practice. An alternative approach is to identify the Pareto set (e.g., the complete set of optimal clusters for all possible choices of the parameter). Nominal significance of clusters in the Pareto set can be evaluated through simulation, possibly combined with a Gumbel distribution approximation. The smallest nominal p-value can be regarded as a new test statistic, and a second-stage Monte Carlo simulation employed to account for selection. The methods are illustrated using data on birth defects in Wisconsin.

  • 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 2009 program


JSM 2009 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.
Revised September, 2008