Logo

Navigation

  • index
  • modules |
  • next |
  • previous |
  • Install
  •  | 
  • Support
  •  | 
  • Bugs
  •  | 
  • Develop
  •  | 
  • Examples
  •  | 
  • FAQ
  •  | 
  • Generalized Linear Models |

statsmodels.genmod.families.links.NegativeBinomial¶

class statsmodels.genmod.families.links.NegativeBinomial(alpha=1.0)[source]¶

The negative binomial link function

Parameters
alphafloat, optional

Alpha is the ancillary parameter of the Negative Binomial link function. It is assumed to be nonstochastic. The default value is 1. Permissible values are usually assumed to be in (.01, 2).

Methods

__call__(p)

Negative Binomial transform link function

deriv(p)

Derivative of the negative binomial transform

deriv2(p)

Second derivative of the negative binomial link function.

inverse(z)

Inverse of the negative binomial transform

inverse_deriv(z)

Derivative of the inverse of the negative binomial transform

inverse_deriv2(z)

Second derivative of the inverse link function g^(-1)(z).

Previous topic

statsmodels.genmod.families.links.Logit.inverse_deriv2

Next topic

statsmodels.genmod.families.links.NegativeBinomial.__call__

This Page

  • Show Source

Quick search

© Copyright 2009-2018, Josef Perktold, Skipper Seabold, Jonathan Taylor, statsmodels-developers. Created using Sphinx 2.1.2.