410 – Space-Time Modeling 2
Spatial-Temporal Generalized Linear Models with Bark Beetle and Other Damage-Causing Agents in the Rocky Mountains Example
Kimberly Kaufeld
University of Northern Colorado
Trent L. Lalonde
University of Northern Colorado
Zhu et al (2008) developed a binary spatial-temporal autologistic regression model which accounts for spatial and temporal dependence at discrete time points. It uses logistic regression to model a response variable on explanatory variables and autoregression on responses from spatial neighborhoods. This research extends the work of Zhu et al's autologistic binary model to generalized linear models such as nominal multinomial models and models for ordinal response data where the spatial grid changes at each time point. The data are measured repeatedly based on spatial distances over discrete time points. A spatial neighborhood structure is constructed and ordered with respect to the adjacency of the initial site. A spatial-temporal autologistic regression model draws samples using Monte Carlo estimation using a Gibbs Sampler to obtain estimates of the model parameters. A dataset of bark beetle and multiple damage causing agents in the Rocky Mountain Forest Region from 2005-2009 is used to demonstrate the methodology.