[R] help for MLE

Edward Sun edwardweisun at hotmail.com
Sun Feb 22 20:12:13 CET 2004


Dear Sir/Madam,

I am using R version 1.8.1. I am doing following tast:

First generate 100 Gaussion(3,1) numbers, then write the likelihood function 
to estimate the parameters of Gaussian distribution by direct maximizing the 
likelihood function.

My likelihood function is:
>fn<-function(x) 
>(-50*log((sd(x))^2))-50*log(sqrt(2*pi))-(1/2*((mean(x))^2))*(sum((x-(mean(x))^2))

After I input above function, the '' >'' turned to be '' + ''. and it did 
not work.

I am looking for the help to solve this tast by writting a likelihood 
function.

Thanks a lot.

Best regards.
edward sun
p.s
>x=rnorm(100, mean=3, sd=1)
library(MASS)
fitdistr(x, "normal")

and

>fitdistr(x, "normal", list(mean=0, sd=1))

do not work.




More information about the R-help mailing list