Dear r-helpers,
I'm experiencing some problems in fitting a maximum likelihood binomial
model to some of my data. The error is in optim, which founds: Error in
optim(par = c(0.2, 0.5), fn = function (p) :
initial value in 'vmmin' is not finite
Yes, I know it's a common problem, and I've carefully searched and readed
all the posts about the issue, But, I can't find a solution. It looks like
it will be a small piece of my code, but I'm unable to find it. Maybe anyone
could help me...
Here is my data and the code:
> library(bbmle)
Loading required package: stats4
Loading required package: numDeriv
Loading required package: lattice
Loading required package: MASS
Warning message:
package 'bbmle' was built under R version 2.12.2
> Cov<-read.table("f:/Arribes/NutriaPopMod.csv", header=TRUE, sep=",")
> print(Cov)
Localidad sizec sizead
1 Villagonzalo 5 3
2 Villagonzalo 7 3
3 Villagonzalo 10 4
4 Riolobos 13 13
5 Riolobos 8 8
6 Riolobos 8 8
7 Riolobos 8 8
8 Riolobos 8 8
9 Salamanca 21 3
10 Salamanca 24 4
11 Salamanca 25 5
12 Salamanca 21 3
13 Salamanca 22 7
14 FA 24 5
15 FA 23 5
16 FA 14 8
17 FA 7 4
18 FA 8 3
19 Juzbado 13 2
20 Juzbado 10 2
21 Juzbado 3 2
22 Cristo 4 2
23 Cristo 4 2
24 Cristo 3 2
25 Cristo 4 2
26 Muñoz 2 2
27 Muñoz 2 2
28 Castraz 2 2
29 Castraz 2 2
30 Saldeana 2 2
31 Saldeana 2 2
32 Merchanas 2 2
33 Merchanas 2 2
34 Merchanas 2 2
35 CR 3 2
36 CR 2 2
37 Béjar 4 4
38 Béjar 8 8
39 Béjar 6 6
40 Gata 2 3
41 Gata 2 3
42 Sta Teresa 4 4
43 Sta Teresa 5 5
44 Sta Teresa 2 2
45 Sta Teresa 2 2
46 Francia 3 2
47 Francia 2 2
48 Navamuño 21 21
49 Navamuño 8 8
50 Ledesma 11 3
51 Ledesma 12 3
52 Ledesma 15 2
53 Ledesma 21 2
54 Ledesma 6 2
55 Monleras 2 2
56 Monleras 2 2
57 Uces 2 2
58 Uces 2 2
59 Molinera 2 2
60 Molinera 2 2
61 Aldeadávila 2 2
62 Aldeadávila 2 2
63 Pelayos 3 3
64 Pelayos 4 3
65 Pelayos 5 3
> Pr<-function(p1,p,n1,n2)
+ {P1=1-(1-p1)
+ POD=1-(1-p)
+ Pr=P1*POD
+ -sum(dbinom(length(Cov$Nt),size=Cov$sizead, prob=POD,
log=TRUE)*dbinom(length(Cov$Nt), size=Cov$sizec, prob=P1,log=TRUE))
+ }
> parnames(Pr)=c("p1","p")
> m1<-mle2(Pr, start=list(p1=0.2, p=0.5),
> data=list(Pr=Cov$Pr,n1=Cov$sizec,n2=Cov$sizead))
> Error in optim(par = c(0.2, 0.5), fn = function (p) :
initial value in 'vmmin' is not finite
Thanks in advance, regards,
Pablo
--
View this message in context:
http://r.789695.n4.nabble.com/error-in-optim-initial-value-in-vmmin-is-not-finite-tp4415385p4415385.html
Sent from the R help mailing list archive at Nabble.com.
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
