2
$\begingroup$

I know the formula for the likelihood of some parameters given the data. The result has to be maximised and I can avoid multiplication using the log. How can I make this a minimisation problem (i.e. rewrite the given formula). I presume it is not as easy as taking the negative log and than adding things - or is it? Thanks.

Christian

$\endgroup$
3
$\begingroup$

Yes, it is that simple. If you you want to maximize $\log(L)$ but you have a computational routine that minimizes a function, you can minimize $-\log(L)$.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.