[R] Fwd: question on constrOptim
murdoch.duncan at gmail.com
Thu Mar 24 18:09:42 CET 2016
On 24/03/2016 8:13 AM, Anusha Kothapalli wrote:
> ---------- Forwarded message ----------
> From: *Anusha Kothapalli* <akothapa at umass.edu>
> Date: Wednesday, March 23, 2016
> Subject: question on constrOptim
> To: R-core at r-project.org
> To Whom It May Concern,
> We are using constrOptim to maximize a log likelihood function. The
> constrOptim call returns values, however, they are *exactly identical* to
> the initial values we input. Our ci, ui, gradient, etc. match the
> requirements for use of this function. So we are out of ideas. Would you
> happen to know how to make constrOptim run multiple iterations and/or
> return values that aren't equal to our initial values?
> Any input you have would be greatly appreciated!
Modify your objective function to print out the arguments it is given
and the result it produces. You'll likely see something wrong when you
look at those.
If you still can't figure out the problem, simplify things enough to
post to R-help, and post it there. It needs to be in a form that
someone else can run. (Don't email it just to me, send it to the list.)
More information about the R-help