JSM Preliminary Online Program
This is the preliminary program for the 2007 Joint Statistical Meetings in Salt Lake City, Utah.

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 2007 Program page

Activity Number: 98
Type: Topic Contributed
Date/Time: Monday, July 30, 2007 : 8:30 AM to 10:20 AM
Sponsor: Section on Physical and Engineering Sciences
Abstract - #310087
Title: Making the Best Use of Available Data: The Presence-Only Problem in Ecology
Author(s): Gillian Ward*+ and Trevor Hastie
Companies: Stanford University and Stanford University
Address: Department of Statistics Sequoia Hall, Stanford, CA, 94305,
Keywords: presence-only problem ; positive and unlabeled examples ; EM algorithm ; gradient boosting ; boosted trees ; logistic regression
Abstract:

Rich resources of species presence records are becoming freely available electronically, but they typically do not include records of species absence. A similar problem arises in text categorization, that of positive and unlabeled examples. As data collection can be prohibitively expensive, we would like to use these presence-only data to estimate a presence-absence model of species distribution across a landscape. We critique Maxent, an existing model, and propose two new methods: an EM algorithm that can be used with almost any off-the-shelf logistic model, and a gradient boosting model that is available in R. Both methods require an external estimate of overall population prevalence.

  • 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 2007 program

JSM 2007 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, 2007