statsmodels.robust.norms.RobustNorm

class statsmodels.robust.norms.RobustNorm[source]

The parent class for the norms used for robust regression.

Lays out the methods expected of the robust norms to be used by statsmodels.RLM.

Parameters
None :

Some subclasses have optional tuning constants.

See also

statsmodels.rlm

Notes

Currently only M-estimators are available.

References

PJ Huber. ‘Robust Statistics’ John Wiley and Sons, Inc., New York, 1981.

DC Montgomery, EA Peck. ‘Introduction to Linear Regression Analysis’,

John Wiley and Sons, Inc., New York, 2001.

R Venables, B Ripley. ‘Modern Applied Statistics in S’

Springer, New York, 2002.

Methods

__call__(z)

Returns the value of estimator rho applied to an input

psi(z)

Derivative of rho.

psi_deriv(z)

Deriative of psi.

rho(z)

The robust criterion estimator function.

weights(z)

Returns the value of psi(z) / z