[R] MLE with optim

[Sundar Dorai-Raj]

Carsten Steinhoff wrote:
> Hello,
>  
> I tried to fit a lognormal distribution by using optim. But sadly the output
> seems to be incorrect.
> Who can tell me where the "bug" is?
>  
> test     =     rlnorm(100,5,3)
> logL    =     function(parm, x,...) -sum(log(dlnorm(x,parm,...)))
> start    =     list(meanlog=5, sdlog=3)
> optim(start,logL,x=test)$par
>  
> Carsten.
> 

You are only supplying the meanlog argument to dlnorm. Also you can set 
log = TRUE in dlnorm to avoid the log computation after calling dlnorm.

set.seed(1)
x <- rlnorm(100, 5, 3)
logL <- function(par, x) -sum(dlnorm(x, par[1], par[2], TRUE))
start <- list(meanlog = 5, sdlog = 2)
optim(start, logL, x = x)

Why not just use MASS::fitdistr instead?

library(MASS)
fitdistr(x, dlnorm, start)

HTH,

--sundar