Python statsmodel中的GLM残差 [英] GLM Residual in Python statsmodel
问题描述
如何在Python中为所有303个观测值生成残差:
How to generate residuals for all 303 observations in Python:
from statsmodels.stats.outliers_influence import OLSInfluence
OLSInfluence(resid)
或
res.resid()
我正在尝试生成类似于我们使用R在R中生成的残差:
I am trying to generate residual similar to what we generate in R using:
res$resid
推荐答案
statsmodels没有用于 GLM 的默认 resid ，但是具有以下内容
statsmodels does not have a default resid for GLM, but it has the following
resid_anscombe Anscombe残差.
resid_anscombe Anscombe residuals.
resid_anscombe_scaled缩放后的Anscombe残差.
resid_anscombe_scaled Scaled Anscombe residuals.
resid_anscombe_unscaled未缩放的Anscombe残差.
resid_anscombe_unscaled Unscaled Anscombe residuals.
resid_deviance偏差残差.
resid_deviance Deviance residuals.
resid_pearson皮尔逊残差.
resid_pearson Pearson residuals.
resid_response响应残差.
resid_response Response residuals.
resid_working工作残差.
resid_working Working residuals.
残差 y-E(y | x)是响应残差 resid_response
这些残差可用作 fit 方法返回的结果实例的属性.
Those residuals are available as attributes of the results instance that is returned by the fit method.
这篇关于Python statsmodel中的GLM残差的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
