Analysis of Multiscale Ecological Data

• Activity Number: 687
• Type: Contributed
• Date/Time: Thursday, August 13, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics and the Environment
• Author(s): Kelly-Ann Dixon Hamil* and Whitney Huang and Hao Zhang and Songlin Fei and Basil Iannone
• Companies: and Purdue University and Purdue University and Purdue University and Purdue University
• Keywords: Multiscale ; Ecological Fallacy ; Invasive Species

Abstract

In the study of species abundance, it is well documented that statistical inference for varying spatial scales may yield, not only different, but also contradictory results. This counter-intuitive observation is attributable to the effects of spatial aggregation over inhomogeneous areas where some important variables are not observed or missing in the study. The process of modelling such multiscale phenomena must take into account the fact that ecological processes operate at varying spatial scales and thus may produce patterns which differ from the scale at which they act. Using data for native and invasive species in forested areas, we will demonstrate this phenomena by presenting a statistical model which examines the relationship at multiple spatial extents.