Modelling the probability of occurrence in space

Much of the motivation for this course stems from the need to develop spatially explicit predictions about the likelihood that a species or event occurs in places we haven’t sampled. In ecology, we call these models by several different names: species distribution models, resource selection functions, habitat selection models. More generally we might call these ‘event occurrence models,’ statistical models that describe the relations between a number of predictors and the occurrence of any event of interest (e.g., presence of crimes, species, conservation actions, etc. )

Resources

• Logistic regression: a brief primer by (Stoltzfus 2011) is a nice introduction to logistic regression.

• Point process models for presence-only analysis by (Renner et al. 2015) provides a comprehensive overview and comparision of methods for analyzing presence-background datasets.

• Estimating site occupancy rates when detection probabilities are less than one by (MacKenzie et al. 2002) is one of the foundational papers describing the use of occupancy modelling to account for situations where absences are ambiguous.

• Is my species distribution model fit for purpose? Matching data and models to applications by (Guillera-Arroita et al. 2015) is an excellent, concise description of the relations between data collection, statistical models, and inference.

• Predicting species distributions for conservation decisions by (Guisan et al. 2013) is a foundational paper describing some of the challenges with making conservation decisions based on the outcomes of species distribution models.

Slides

View all slides in new window Download PDF of all slides

• Modelling the probability of occurrence in space
• Motivations
• Presence absence data
• Presence background data
• Imperfect detection