Hi Chong,

If I understood correctly, it seems to me like you are trying to minimize a
least-squares like metric - where the function you are simulating depends
on the vector of parameters, and the data represents the quantities you
have measured.

Although my C++ is a bit rusty - there are two ways of doing this.  The
first way, is to wrap up everything up in a class, where the data is held
in a class variable.  Then, create a functor that performs the calculation
that you want, that has access to the data.

The second option is to create a closure.  You want to create a function,
that takes as an input your data, then returns a function with the correct
signature for nlopt.

Hope this helps!

Federico



> Message: 1
> Date: Sun, 25 May 2014 11:40:20 -0400
> From: Chong Li <[email protected]>
> To: [email protected]
> Subject: [NLopt-discuss] help with MLE estimation with NLopt in C++
> Message-ID:
>         <CAPPgUKJ=
> [email protected]>
> Content-Type: text/plain; charset="utf-8"
>
> Hi, dear all:
>
>    I am having some difficulties in using NLopt to maximize the likelihood
> function that takes data as an argument. Only the constraint function in
> the example in NLopt tutorial has used a data parameter to pass data to the
> constraint function. Could anyone help me out with some example code on how
> to deal with this or any general way to do a maximum likelihood estimation
> with NLopt in C++?
>
> Thanks a lot for your attention and have a good week ahead!
>
>
> Chong
>
>
>
> --
> Chong Li (? ?)
>
> Department of Economics,
> Maxwell School of Citizenship and Public Affairs,
> Syracuse University
> Syracuse, NY 13244-1020
>
> Email:[email protected]
>
> Mobile: 315-744-2709
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <
> http://ab-initio.mit.edu/pipermail/nlopt-discuss/attachments/20140525/bc83f598/attachment-0001.html
> >
>
> ------------------------------
>
> Subject: Digest Footer
>
> _______________________________________________
> NLopt-discuss mailing list
> [email protected]
> http://ab-initio.mit.edu/cgi-bin/mailman/listinfo/nlopt-discuss
>
>
> ------------------------------
>
> End of NLopt-discuss Digest, Vol 56, Issue 3
> ********************************************
>
_______________________________________________
NLopt-discuss mailing list
[email protected]
http://ab-initio.mit.edu/cgi-bin/mailman/listinfo/nlopt-discuss

Reply via email to