statsmodels.genmod.families.family.InverseGaussian.resid_anscombe

method

InverseGaussian.resid_anscombe(endog, mu, var_weights=1.0, scale=1.0)

The Anscombe residuals

Parameters

endogarray

The endogenous response variable

muarray

The inverse of the link function at the linear predicted values.

var_weightsarray-like

1d array of variance (analytic) weights. The default is 1.

scalefloat, optional

An optional argument to divide the residuals by sqrt(scale). The default is 1.

Returns

resid_anscombearray

The Anscombe residuals for the inverse Gaussian distribution as defined below

Notes

\[resid\_anscombe_i = \log(Y_i / \mu_i) / \sqrt{\mu_i * scale} * \sqrt(var\_weights)\]