--
Message: 5
Date: Mon, 23 Sep 2013 15:29:54 +
From: "Lee, Laura"
To: "r-sig-ecology@r-project.org"
Subject: [R-sig-eco] convergence problems for zero-inflated model
Message-ID:
<2789d349964a854e9524a3cd0d759e042dbf0...@n
Hi all!
I'm using a zero-inflated model using the function 'zeroinfl' and running into
convergence problems (system is computationally singular). How can I modify the
code so it does not calculate a Hessian matrix?
Thanks,
Laura
E-mail correspondence to and from this address is subject to t
Laura,
Hacking the function is straightforward. Change this line:
hessian <- control$hessian
into
hessian <- FALSE
and then this one:
vc <- -solve(as.matrix(fit$hessian))
as
vc <- diag(1, length(fit$par), length(fit$par))
Then you take care of the unexported model_offset_2 function as
pscl