statsmodels.robust.covariance.CovDetMM.fit

CovDetMM.fit(maxiter=100)

Estimate model parameters

Parameters:

maxiterint, optional

Maximum number of iterations in the second stage M-estimation.

Returns:

CovMResult

Named tuple with mean, shape, scale, cov, converged, n_iter, and mahalanobis. See CovMResult for details.

Notes

This uses CovDetS for the first stage estimation and CovM with fixed scale in the second stage MM-estimation.

TODO: fit options for the first stage CovDetS estimation are missing.