statsmodels.robust.norms.HuberT

class statsmodels.robust.norms.HuberT(t=1.345)

Huber’s T for M estimation

Parameters:

tfloat or array_like, optional

The tuning constant for Huber’s t function. It has to be positive. An array is used element-wise, broadcast with the argument of the methods. The default value is 1.345.

Methods

__call__(z)

Return the value of estimator rho applied to an input

Raises:

TypeError

If t is not a real number or an array of real numbers.

ValueError

If t or any element of t is not positive, or is nan.

See also

statsmodels.robust.norms.RobustNorm

Notes

Changed in version 0.15.1: The tuning constant is validated. Zero, negative and nan values raise a ValueError instead of creating a degenerate norm.

The tuning constant is validated when the norm is created and in _set_tuning_param. Plain attribute assignment after construction, norm.t = value, is not validated.

Methods

max_rho()
psi(z)	The psi function for Huber's t estimator
psi_deriv(z)	Derivative of the Huber T psi function.
rho(z)	The robust criterion function for Huber's t estimator
weights(z)	Huber's t weighting function for the IRLS algorithm

Properties

continuous
redescending