statsmodels.robust.norms.HuberT.rho¶
- HuberT.rho(z)[source]¶
The robust criterion function for Huber’s t estimator.
\[\begin{split}\rho(z) = \begin{cases} \frac{1}{2} z^2 & \text{for } |z| \le t \\ t|z| - \frac{1}{2} t^2 & \text{for } |z| > t \end{cases}\end{split}\]- Parameters:¶
- zarray_like
1d array
- Returns:¶
- rho
ndarray The value of the robust criterion function.
- rho