[R] solnp Hessian problem in some datasets not in others

[Berend Hasselman]

On 02-03-2012, at 16:12, Diogo Alagador wrote:

> Dear all,
> 
> Sorry to insist in this, but I am passing really "bad times" trying to solve the problem. Just to remember you:
> 
> I am tryng to solve a nonlinear optimization probel using the solnp function.
> I have different datasets. For the smaller I get full solutions, for
> the bigger I got an error message stating:
> 
> ########################################
> Iter: 1 fn: 101.8017     Pars:  0.21000 0.21000 0.21000 0.21000
> 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000
> 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000
> 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000
> 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000
> 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000
> 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000
> 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000 0.21000
> 0.21000 0.21000 0.21000 0.21000
> 
> solnp--> Solution not reliable....Problem Inverting Hessian.
> Warning messages:
> 1: In p0 * vscale[(neq + 2):(nc + np + 1)] :
>    longer object length is not a multiple of shorter object length
> 2: In cbind(temp, funv) :
>    number of rows of result is not a multiple of vector length (arg
> 1) ########################################
> 
> 
> Anyone knows what may be the reason? Just remembering that the same
> problem runs OK for smaller datasets.

No.
You have not provided enough information.
I know nothing about solnp but I am quite prepared to investigate.
But from the warning message I would guess that [(neq + 2):(nc + np + 1)] is simply incorrect in your specific case.

But no data or no description of your data, no function, no reproducible example  ===> No help.
You should really try to be more informative.

Berend