Multi-season, correlated detections model data setup

questions concerning analysis/theory using program PRESENCE

Multi-season, correlated detections model data setup

Postby leroy » Thu Aug 04, 2016 8:55 am

Hi,

I'm using a multi-season, correlated detections model using spatial repeats rather than temporal repeat visits. Just wondering whether the order of my spatial repeats needs to be consistent among seasons? For example, in season one my spatial repeats are A, B, C, D, E. Can I have my data arranged so that in season 2, the order of my spatial repeats is B, A, E, C, D? Or do I need to keep the same order as season 1 (A, B, C, D, E)? I'd be grateful to hear your thoughts.

Many thanks,

Leroy.
leroy
 
Posts: 10
Joined: Thu Aug 04, 2016 4:04 am

Re: Multi-season, correlated detections model data setup

Postby jhines » Thu Aug 04, 2016 9:57 am

For detection, it doesn't matter as you can build models with any p equal to any other p, using the design matrix.

For the local occupancy parameters, theta and theta', the order would not matter if you visited the segments in that order each season (ie., visited the segments in order, A,B,C,D,E in season 1 and visited the sites in order, B,A,E,C,D in season 2). The key issue is that the theta parameters depend on the previously visited segment each season. If you actually visited the segments in the same order, but input them in a different order, that would ruin the model as the theta's for one segment would be based on local occupancy of another segment which is not next to it (so no reason to expect it to be correlated.)
jhines
 
Posts: 599
Joined: Fri May 16, 2003 9:24 am
Location: Laurel, MD, USA


Return to analysis help

Who is online

Users browsing this forum: No registered users and 6 guests