Re: [R] Not nice behaviour of nlminb (windows 32 bit, version 2.11.1)

>> >> Ph. (410) 502-2619 >> email: rvarad...@jhmi.edu >> >> >> - Original Message - >> From: Duncan Murdoch >> Date: Saturday, July 10, 2010 7:32 am >> Subject: Re: [R] Not nice behaviour of nlminb (windows 32 bit, version >> 2.11.1)

Re: [R] Not nice behaviour of nlminb (windows 32 bit, version 2.11.1)

And further to those two: nlminb( obj = function(x) 2*(x+3), start=-2, lower=-Inf, upper=Inf ) On 9 July 2010 23:09, Matthew Killeya wrote: > Yes clearly a bug... there are numerous variations ... problem seems to be > for a linear function whenever the first function valuation is 1. &

Re: [R] Not nice behaviour of nlminb (windows 32 bit, version 2.11.1)

33 >> >> >> This is clearly a bug. >> >> >> Ravi. >> >> -Original Message- >> From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] >> On >> Behalf Of Ravi Varadhan >> Sent: Friday, July 09

[R] Not nice behaviour of nlminb (windows 32 bit, version 2.11.1)

nlminb( obj = function(x) x, start=1, lower=-Inf, upper=Inf ) $par [1] 0 $objective [1] 0 $convergence [1] 0 $message [1] "absolute function convergence (6)" $iterations [1] 1 $evaluations function gradient 22 [[alternative HTML version deleted]] _