R help - Oct 2008 - Maximizing a function - optim does not always converge

Hello All,
 
I¢m  kinda new to R language and any help that I can get is greatly appreciated.
 
Basically, I want to find the values of the two parameters that will maximize
the function and I¢m currently using the optim function to find these values. 
My R code works fine but not all the time.  Sometimes the solution converges,
sometimes not.   Since I¢m planning to do this 5000 times, is there a way where
I can make sure the solution always converge?
 
size <- 25
n <- rbinom(1, size, 0.6)
data <- log(rlnorm(n, -0.075, sqrt(.15)))
xbar <- mean(data)
sigma2 <- var(data)
s <- n*xbar
tsq <- sum(data^2) 
t_init <- xbar-2*sqrt(sigma2/n)

  l2 <- function(x){
        x1 <- x[1]
        x2 <- x[2]
        (size - n)*log(1 - exp(t_init - x1 - x2/2)) + n*(t_init -x1 - x2/2) -
(n/2)*log(2*pi) - (n/2)*log(x2) - tsq/(2*x2) + x1*s/x2 - n*(x1^2)/(2*x2)
  }
 
  gr.l2 <- function(x){
        x1 <- x[1]
        x2 <- x[2]
        c((size-n)*exp(t_init - x1 -x2/2)/(1-exp(t_init - x1 -x2/2)) - n +
(s/x2) - (n*x1/x2),
          (size-n)*exp(t_init - x1 -x2/2)/(1-exp(t_init - x1 -x2/2)) - n/2 -
n/(2*x2) + tsq/(2*x2^2) - x1*s/x2^2 + n*x1^2/(2*x2^2))
  }

optim(c(xbar,sigma2), l2, gr.l2, method="BFGS",
control=list(fnscale=-1))  


 
 Also, I would like to impose 2 conditions: 
            1)   x2 > 0  and 
2) t_init - x1 - x2/2 < 0.
 
 
Thanks,
Matt


      
	[[alternative HTML version deleted]]