Generalized linear models currently supports estimation using the one-parameter exponential families
>>> import scikits.statsmodels as sm >>> data = sm.datasets.scotland.Load() >>> data.exog = sm.add_constant(data.exog)Instantiate a gamma family model with the default link function.
>>> gamma_model = sm.GLM(data.endog, data.exog, family=sm.family.Gamma()) >>> gamma_results = gamma_model.fit()
see also the examples and the tests folders
GLMResults(model, params, ...) | Class to contain GLM results. |
The distribution families currently implemented are
Family | |
Binomial | |
Gamma | |
Gaussian | |
InverseGaussian | |
NegativeBinomial | |
Poisson |
The link functions currently implemented are the following. Not all link functions are available for each distribution family. The list of available link functions can be obtained by
>>> ssm.family.family.<familyname>.available ?
Link | |
CDFLink | |
CLogLog | |
Log | |
Logit | |
NegativeBinomial | |
Power | |
cauchy | |
cloglog | |
identity | |
inverse | |
inverse_squared | |
log | |
logit | |
nbinom | |
probit |