Internal vs External covariance matrices

Hi guys,

In Minuit2, we set limits to some parameters avoiding some parameters to go wild outside the boundaries. We noticed that the internal covariance matrix when used would return error bars that would scale with the boundary conditions. Since there is a transformation from internal to external matrices, what is the line code to get the external matrice instead of the internal one?

Thanking you in advance,


I think @moneta can help you.

Thanks. I got the answer from the same question answered by Lorenzo in a different post from 2016:

"Hi Tim,

I think this is an intended behaviour. The computed error in case of parameter with limits is computed by transforming the full interval from the internal Minuit coordinates. which are unlimited, to the externals one (the user ones which have the limit).
The covariance matrix is instead transformed just using the derivatives.

Since both cases are only approximations, it is difficult to say that one is better than the other one. As you know the correct procedure to estimate errors in case of bounds is at least to use Minos

Best Regards