[SciPy-user] scipy.optimize.leastsq and covariance matrix meaning
Mon Nov 10 04:29:05 CST 2008
Bruce Southey wrote:
> It is possible to be correct if the values of y are large and
> sufficiently variable.
y values should be in the 10**-10 range...
> But, based on the comment on the fit and the
> correlation in the matrix above is -0.98, my expectation is that there
> is almost no error/residual variation left. The residual variance should
> be very small (sum of squared residuals divided by defree of freedom).
Is the sum of squared residuals / degree of freedom a residual
variance... of what parameters? Sorry again, but I'm not that good in
non-linear fitting theory.
> You don't provide enough details but your two x variables would appear
> to virtually correlated because of the very highly correlation. There
> are other reasons, but with data etc. I can not guess.
I'll try to sketch up a script reproducing the core of the problem with
Massimo Sandal , Ph.D.
University of Bologna
Department of Biochemistry "G.Moruzzi"
Via Irnerio 48, 40126 Bologna, Italy
-------------- next part --------------
A non-text attachment was scrubbed...
Size: 274 bytes
Desc: not available
Url : http://projects.scipy.org/pipermail/scipy-user/attachments/20081110/8ee2794b/attachment.vcf
More information about the SciPy-user