Information matrix of an experimental design
= Information matrix of an experimental design
{title2=$M(\xi)=\int f(x)f(x)^T\,d\xi(x)$}
The normalized information <matrix> for a homoscedastic <linear regression> model is the average outer product of its regressor vector. It is <positive-definite> precisely when the supported regressors span the parameter space. The full <Fisher information matrix> under <normal> errors is $NM(\xi)/\sigma^2$.