Least-Squares Fitting with asymmetric errors

[Adam Kleczkowski]

> If I understand your question correctly, it's simple:  that is
> the least squares
> criterion.  You could construct some other criterion, but usually
> it doesn't
> make much difference.  The reason that you have a non-linear
> model is because
> your errors are not mound-shaped and in this case they are not
> symmetric either.

This is getting very off-topic (not related directly to GSL), so probably
should be moved to private e-mail rather than being discussed in the GSL
group.

I would only like to comment on Rodney's comment that error structure could
make a huge difference, but this very much depends on a particular
situation.

Adam

--
Adam Kleczkowski, University of Cambridge
adamk@mathbio.com, http://mathbio.com
There are few mathematical topics that are as badly taught
to physicists as probability theory. (R.F. Streater)