Search code examples
pythonrregressionlinear-regression

GLM Residual in Python statsmodel

How to generate residuals for all 303 observations in Python:

from statsmodels.stats.outliers_influence import OLSInfluence
OLSInfluence(resid)

or

res.resid()

I am trying to generate residual similar to what we generate in R using:

res$resid
Solution

  • statsmodels does not have a default resid for GLM, but it has the following

    resid_anscombe Anscombe residuals.

    resid_anscombe_scaled Scaled Anscombe residuals.

    resid_anscombe_unscaled Unscaled Anscombe residuals.

    resid_deviance Deviance residuals.

    resid_pearson Pearson residuals.

    resid_response Response residuals.

    resid_working Working residuals.

    https://www.statsmodels.org/stable/generated/statsmodels.genmod.generalized_linear_model.GLMResults.html

    The residual y - E(y|x) are the response residuals resid_response

    Those residuals are available as attributes of the results instance that is returned by the fit method.