[R] MLE where loglikelihood function is a function of numerical solutions

[Berend Hasselman]

Questions:

1. why are you defining Bo within a loop? 
2. Why are you doing library(nleqslv) within the loop?

Doing both those statements outside the loop once is more efficient.

In your transdens function you are not using the function argument
parameters, why?
Shouldn't there be a with(parameters) since otherwise where is for example
K_vv supposed to come from?

I can't believe that the code "worked": in the call of nleqslv you have ...
control=list(matxit=100000) ...
It should be maxit and nleqslv will issue an error message and stop (at
least in the latest versions).
And why 100000? If that is required, something is not ok with starting
values and/or functions.

Finally the likelihood function at the end of your code

#Maximum likelihood estimation using mle package 
library(stats4) 
#defining loglikelighood function 
#T <- length(v) 
#minuslogLik <- function(x,x2) 
#{    f <- rep(NA, length(x)) 
#        for(i in 1:T) 
#        { 
#            f[1] <- -1/T*sum(log(transdens(parameters = parameters, x = 
c(v[i],v[i+1])))-log(Jac(outmat=outmat, x2=c(v[i],r[i]))) 
#        } 
#    f 
# } 

How do the arguments of your function x and x2 influence the calculations in
the likelihood function?
As written now with argument x and x2 not being used in the body of the
function, there is nothing to optimize.
Shouldn't f[1] be f[i] because otherwise the question is why are looping
for( i in 1:T)?
But then returning f as a vector seems wrong here. Shouldn't a likelihood
function return a scalar?


Berend

--
View this message in context: http://r.789695.n4.nabble.com/MLE-where-loglikelihood-function-is-a-function-of-numerical-solutions-tp3439436p3447224.html
Sent from the R help mailing list archive at Nabble.com.