Issue
ML.NET does not have an option for alternate covariance matrix estimators for use with OlsModelParameters. I would like to be able to select different covariance matrix estimators for estimating coefficient standard errors and p-values. These different covariance matrix estimators are standard in economics and other social sciences. See for example the covariance matrix estimators and software architecture here: https://cran.r-project.org/web/packages/sandwich/index.html
I understand that it would be difficult for the ML.NET team to add all possible covariance matrix options (nobody can). But an architecture that allows the community to contribute their own covariance estimators would be very useful.