Psi estimates for each site with no covariates

questions concerning analysis/theory using program PRESENCE

Psi estimates for each site with no covariates

Postby pennyb » Tue Nov 10, 2015 3:52 am

Hi all,

If I have investigated effects of site-specific covariates on psi and found no effect, but I still want to have an individual estimate of psi for each site, what data do i input?

I have 15 sites, 3 sites in 5 different wetlands. I have tried modelling psi as a function of wetland - with 4 indicator covariates and 1 intercept, or just 5 indicator covariates, however am getting convergence problems (i think my data set may be too sparse).

But if I want to give each site a 'covariate' so that psi is estimated individually, i am stumped as to how to do this. I have coded each site from 1-15 and standardised this value ((value - mean)/10) and input this into PRESENCE as 1 parameter, however have realised that obviously sites with small standardised values have small psi's and sites with large standardised values have psi's close to 1 :cry: .

Can I use randomly generated numbers between 0 and 1? or can I code differently?

Cheers,
Penny.
pennyb
 
Posts: 13
Joined: Tue Sep 23, 2014 9:06 pm

Return to analysis help

Who is online

Users browsing this forum: No registered users and 8 guests