class TLinearMinimizer: public ROOT::Math::Minimizer

 Default constructor implementation.
 type is not used - needed for consistency with other minimizer plug-ins

 constructor passing a type of algorithm, (supported now robust via LTS regression)

 Destructor implementation.

 Implementation of copy constructor.

 Set function to be minimized. Flag an error since only support Gradient objective functions

 Set the function to be minimized. The function must be a Chi2 gradient function
 When performing a linear fit we need the basis functions, which are the partial derivatives with respect to the parameters of the model function.

 set a fixed variable.

 find directly the minimum of the chi2 function
 solving the linear equation. Use  TVirtualFitter::Eval.

 set free variable (dummy impl. )

 return minimum function value

 return expected distance reached from the minimum

 return  pointer to X values at the minimum

 return pointer to gradient values at the minimum

 number of function calls to reach the minimum

 this is <= Function().NDim() which is the total
 number of variables (free+ constrained ones)

 number of free variables (real dimension of the problem)
 this is <= Function().NDim() which is the total

 minimizer provides error and error matrix

 return errors at the minimum

 return covariance matrices elements
       if the variable is fixed the matrix is zero
       The ordering of the variables is the same as in errors

 return covariance matrix status