|
Activity Number:
|
497
|
|
Type:
|
Invited
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
| Abstract - #302937 |
|
Title:
|
A Moving Average Approach for Spatial Statistical Models of Stream Networks
|
|
Author(s):
|
Jay Ver Hoef*+
|
|
Companies:
|
NOAA National Marine Mammal Lab
|
|
Address:
|
NMFS Alaska Fisheries Science Center, Fairbanks, AK, 99709,
|
|
Keywords:
|
geostatistics ; spatial autocorrelation ; Euclidean distance ; kernel convolution ; spatial linear model
|
|
Abstract:
|
I use moving average constructions to develop new classes of models in a flexible modeling framework for stream networks, using stream distance rather than Euclidean distance. One interesting aspect of stream networks is the dichotomy of autocorrelation between flow-connected and flow-unconnected locations. Various models are derived depending on whether the moving average has an upstream, downstream, or two-sided construction. These models can also account for the volume and direction of flowing water. The data for this article come from the Ecosystem Health Monitoring Program in Southeast Queensland, Australia. We model water chemistry and species biodiversity values for sample sizes of near 100. We achieve a flexible modeling framework for the example data by using a variance component approach.
|
