Displaying 2 results from an estimated 2 matches for "wenwen".
Did you mean:
wenden
2010 Jul 23
1
(no subject)
...9991,0.0000001,0.0000001)
dev<-rbind(diag(3),-diag(3),rep(-1,3))
bvec<-c(rep(0,3),rep(-1,4))
constrOptim(start,tm,NULL,ui=dev,ci=bvec,control=list(maxit=10000))
Am i missing something obviously that cause the problem or there is some bugs in constrOptim. Could you please help me out
Cheers
Wenwen
_________________________________________________________________
Hotmail: Free, trusted and rich email service.
[[alternative HTML version deleted]]
2010 Jul 26
1
After writing data in MMF using SEXP structure, can i reference in R?
...iag(3), rep(-1, 3))
> bvec<-c(rep(0, 3), rep(-1, 4))
> constrOptim(start, tm, NULL, ui=dev, ci=bvec, control=list(maxit=10000))
>
> Am i missing something obviously that cause the problem or there is some
bugs in constrOptim. Could you please help me out
Wenwen,
I believe that the reason why constrOptim behaves as described is
related to the fact that
(p1, p2, p3) = (1, 0, 0)
is a stationary point and you use it as a starting point. Try a
different starting point.
If the objective is to maximize, then you should use the follo...