[R] Using optim function for logistic model simulation

Charlotte Chang c.h.w.chang at gmail.com
Mon Apr 26 10:33:46 CEST 2010


 Great! Thank you for your help!

-Charlotte

>>
>> On Mon, Apr 26, 2010 at 1:12 AM, Tal Galili <tal.galili at gmail.com> wrote:
>>>
>>> mm...
>>> I also noticed the function you wrote didn't use parenthesis, mixed b and c and used different names for K.
>>> Your code is a great exercise in debugging  (no offense intended :) )
>>> Try using:
>>> bird<-bird.density[0] # I assume this exists
>>> eqn<- function(K1, b1 = 1.22, c1 = .55) {
>>>                b<-1.22
>>>                c<-0.55
>>>                bird <- c1*bird + b1*bird*(1-b1*bird)*bird/K1
>>>             return(bird)
>>> }
>>>
>>> k1<-optim(c(0,10),eqn)
>>>
>>>
>>>
>>> ----------------Contact Details:-------------------------------------------------------
>>> Contact me: Tal.Galili at gmail.com |  972-52-7275845
>>> Read me: www.talgalili.com (Hebrew) | www.biostatistics.co.il (Hebrew) | www.r-statistics.com (English)
>>> ----------------------------------------------------------------------------------------------
>>>
>>>
>>>
>>>
>>> On Mon, Apr 26, 2010 at 11:08 AM, Tal Galili <tal.galili at gmail.com> wrote:
>>>>
>>>> Hi Charlotte ,
>>>> I can't reproduce your code, but skimming through it -
>>>> It would appear that:
>>>> 1) in
>>>> eqn1<- function(K1, bird)
>>>> you didn't define "bird" (you did define it before the function, so I'd suggest just removing it from the function call like this:
>>>> eqn1<- function(K1)
>>>> 2) you didn't "return" and value at the end of the function.
>>>> 3) you use different name in optim then in the function you made.
>>>> 4) I see no point for you to use the for loop.
>>>>
>>>>
>>>> Consider trying the following code:
>>>> b<-1.22
>>>> c<-0.55
>>>> bird<-bird.density[0] # I assume this exists
>>>> eqn<- function(K1, bird) {
>>>>                b<-1.22
>>>>                c<-0.55
>>>>                bird <- 0.55*bird + b*bird*1-b*bird*bird/K
>>>>             return(bird)
>>>> }
>>>>
>>>> k1<-optim(c(0,10),eqn)
>>>>
>>>>
>>>> ----------------Contact Details:-------------------------------------------------------
>>>> Contact me: Tal.Galili at gmail.com |  972-52-7275845
>>>> Read me: www.talgalili.com (Hebrew) | www.biostatistics.co.il (Hebrew) | www.r-statistics.com (English)
>>>> ----------------------------------------------------------------------------------------------
>>>>
>>>>
>>>>
>>>>
>>>> On Mon, Apr 26, 2010 at 9:00 AM, Charlotte Chang <c.h.w.chang at gmail.com> wrote:
>>>>>
>>>>> optim
>>>
>>
>



More information about the R-help mailing list