I am using the below code to perform a TukeyBiweight(Bisquare) Robust linear Model Regression of data X and y.
from sklearn import datasets, linear_model
from sklearn.metrics import mean_squared_error, r2_score
import statsmodels.api as sm
X = sm.add_constant(X)
rlm_model = sm.RLM(y, X, m=sm.robust.norms.TukeyBiweight())
rlm_results = rlm_model.fit()
Although the code runs without issue, the summary is what worries me. After running the below:
rlm_results.summary()
The following is outputted.
Robust linear Model Regression Results
==============================================================================
Dep. Variable: y No. Observations: 106721
Model: RLM Df Residuals: 106719
Method: IRLS Df Model: 1
Norm: HuberT
Scale Est.: mad
Cov Type: H1
Date: Wed, 08 Jun 2022
Time: 19:44:34
No. Iterations: 50
==============================================================================
coef std err z P>|z| [0.025 0.975]
------------------------------------------------------------------------------
const 0.0377 9.14e-06 4117.608 0.000 0.038 0.038
x1 -0.0076 1.58e-05 -478.404 0.000 -0.008 -0.008
==============================================================================
If the model instance has been used for another fit with different fit
parameters, then the fit options might not be the correct ones anymore .
The model and method are correct, but the Norm it says was not the norm that I fed to the M estimator field. Does anyone know why this occurs?
