6.9.7.3.1. statsmodels.sandbox.tests.test_gam.AdditiveModel

class statsmodels.sandbox.tests.test_gam.AdditiveModel(exog, smoothers=None, weights=None, family=None)

additive model with non-parametric, smoothed components

Parameters:

exog : ndarray

smoothers : None or list of smoother instances

smoother instances not yet checked

weights : None or ndarray

family : None or family instance

I think only used because of shared results with GAM and subclassing. If None, then Gaussian is used.

__init__(exog, smoothers=None, weights=None, family=None)

6.9.7.3.1.1. Methods

__init__(exog[, smoothers, weights, family])
cont()	condition to continue iteration loop
df_resid()	degrees of freedom of residuals, ddof is sum of all smoothers df
estimate_scale()	estimate standard deviation of residuals
fit(Y[, rtol, maxiter])	fit the model to a given endogenous variable Y
next()	internal calculation for one fit iteration