[R] Finding MLE

[li li]

I think I made an error in my funciton. Now it works.


library(stats4)
n <- 8
ll<- function(a,b,x){
-sum(log(gamma((n-1)/2+a-1)/(gamma((n-1)/2)*gamma(a))*1/(2*b^a)*(x/2)^((n-1)/2-1)*(1/b+x/2)^(-((n-1)/2+a-1))))}
fit <- mle(ll, start=list(a=3, b=1), fixed=list(x=c(2,3)))





2014-11-02 22:04 GMT-05:00 li li <hannah.hlx at gmail.com>:

> Thanks Bert for the reply. I still get a message when adding the start
> argument.
>
>
>
> > n <- 8
> > x0 <- c(2,3)
> >
> > ll<- function(a,b,x=x0,size=n){
> +
> -sum(log(gamma((n-1)/2+a-1)/(gamma((n-1)/2)*gamma(a))*1/(2*b^a)*(x/2)^((n-1)/2-1)*(1/b+x/2)^(-((n-1)/2+a-1))))}
> >
> > fit <- mle(ll, start=list(a=3, b=1), nobs = length(x0))
> Error in validObject(.Object) :
>   invalid class “mle” object: invalid object for slot "fullcoef" in class
> "mle": got class "list", should be or extend class "numeric"
> >
> >
>
>
>
>
>
>
> 2014-11-02 14:57 GMT-05:00 Bert Gunter <gunter.berton at gene.com>:
>
> You do not appear to provide initial values for a and b , i.e. the
>> "start" argument for mle.
>>
>> Cheers,
>> Bert
>>
>> Bert Gunter
>> Genentech Nonclinical Biostatistics
>> (650) 467-7374
>>
>> "Data is not information. Information is not knowledge. And knowledge
>> is certainly not wisdom."
>> Clifford Stoll
>>
>>
>>
>>
>> On Sun, Nov 2, 2014 at 10:36 AM, li li <hannah.hlx at gmail.com> wrote:
>> > Hi all,
>> >   I am trying to use the mle function in R to find the maximum
>> likelihood
>> > estimator. The ll function below is the negative of the log likelihood.
>> > Suppose x0 is the observed values, I want to find the maximum likelihood
>> > for a and b. After running the code below, I get the error message
>> "Error
>> > in eval(expr, envir, enclos) : argument is missing, with no default".
>> >   Could anyone familiar with this function give some suggetion? Thanks
>> very
>> > much!
>> >      Hanna
>> >
>> >> n <- 8
>> >> x0 <- c(2,3)
>> >>
>> >> ll<- function(a,b,x=x0,size=n){
>> > +
>> >
>> -sum(log(gamma((n-1)/2+a-1)/(gamma((n-1)/2)*gamma(a))*1/(2*b^a)*(x/2)^((n-1)/2-1)*(1/b+x/2)^(-((n-1)/2+a-1))))}
>> >>
>> >> fit <- mle(ll, nobs = length(x0))
>> >
>> >         [[alternative HTML version deleted]]
>> >
>> > ______________________________________________
>> > R-help at 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
>> <http://www.r-project.org/posting-guide.html>
>> > and provide commented, minimal, self-contained, reproducible code.
>>
>
>

	[[alternative HTML version deleted]]