Closed VirginiaMorera closed 1 year ago
Hi Virginia! A few years too late, but the answer to this question is: there's no intrinsic cutoff associated with any given model. The summary() function runs a calculation that thresholds based on the true skill statistic, as basically a convenience function, but you could just as easily use any other threshold - the PresenceAbsence
package has a lot of nice examples. But the models themselves return continuous values, and there's no inherently correct way to do things beyond that point!
Cheers Colin! Funnily enough that project got stalled and I am only now restarting it, so still relevant and right on time! Thanks for that, I'll check the PresenceAbsence package to try and automatise the process
Many thanks,
On Tue, 14 Feb 2023 at 18:03, Colin J. Carlson @.***> wrote:
Hi Virginia! A few years too late, but the answer to this question is: there's no intrinsic cutoff associated with any given model. The summary() function runs a calculation that thresholds based on the true skill statistic, as basically a convenience function, but you could just as easily use any other threshold - the PresenceAbsence package has a lot of nice examples. But the models themselves return continuous values, and there's no inherently correct way to do things beyond that point!
— Reply to this email directly, view it on GitHub https://github.com/cjcarlson/embarcadero/issues/21#issuecomment-1430160063, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACUL4UMMBFT3BK4CUC76SCLWXPCG7ANCNFSM4QRS4UXQ . You are receiving this because you authored the thread.Message ID: @.***>
-- Dr. Virginia Morera-Pujol Post-doc researcher EDI Committee Postdoc and Research assistants Rep - School of Biology & Environmental Science
School of Biology and Environmental Science University College Dublin https://sites.google.com/ucd.ie/wildl-ecol-behav-at-ucd/home?authuser=0
My work day may look different than your work day. Please do not feel obligated to respond out of your normal working hours.
Super quick question! (hope that's ok)
I'm going to have to run several models and their corresponding predictions in a loop. I'd like to plot a binary map for each, but I haven't found a way to obtain a cutoff value from the object resulting from the
bart
function. it appears in the console when runningsummary(model)
, but haven't found it anywhere inside themodel
object. Any idea where to find it, or if it's even possible? I don't want to have to do each one by hand, printing the summary info on screen and typing the cutoff value myself, and I'm sure it must be tucked away inside the huge list somewhere, but I just haven't found it.