Thursday, February 1, 2018

Playing around with a new version of response plots

On the develop branch of the R version of ENMTools, I've been playing around with a new way of plotting marginal response functions.  In the figure above, the solid blue line represents the relative suitability of habitat as a function of an environmental gradient, with all other variables being held constant at their mean value for all presence and background points.  The green and red dashed lines represent the relative frequency of occurrence of different values of the environmental variable.  This is a Bioclim model, which is why it looks so chunky.

The goal here is to give you some idea of what your model is saying in the context of the data that generated it, instead of just plotting the response function.  Currently it's been tested on GAM, GLM, Bioclim, and Domain models.  I'll do some more testing and probably move it over to the main branch before the weekend.