statsmodels.genmod.families.family.Tweedie.resid_anscombe¶
- Tweedie.resid_anscombe(endog, mu, var_weights=1.0, scale=1.0)[source]¶
The Anscombe residuals
- Parameters:
- endog
ndarray
The endogenous response variable
- mu
ndarray
The inverse of the link function at the linear predicted values.
- var_weightsarray_like
1d array of variance (analytic) weights. The default is 1.
- scale
float
,optional
An optional argument to divide the residuals by sqrt(scale). The default is 1.
- endog
- Returns:
- resid_anscombe
ndarray
The Anscombe residuals as defined below.
- resid_anscombe
Notes
When \(p = 3\), then
\[resid\_anscombe_i = \log(endog_i / \mu_i) / \sqrt{\mu_i * scale} * \sqrt(var\_weights)\]Otherwise,
\[c = (3 - p) / 3\]\[resid\_anscombe_i = (1 / c) * (endog_i^c - \mu_i^c) / \mu_i^{p / 6} / \sqrt{scale} * \sqrt(var\_weights)\]