Re: Fitting with leasqr and uncertainties

[Juan Pablo Carbajal]

On Mon, Jan 20, 2014 at 2:03 PM, Olaf Till <address@hidden> wrote:
> This determines an ellipsoid for a given degree of
> confidence. leasqr does not compute the length of the ellipsoid axes,
> but this is easily done.

Check function cov2ellipse in the geometry package for an example of
the calculation
https://sourceforge.net/p/octave/geometry/ci/default/tree/inst/geom2d/cov2ellipse.m