statsmodels.discrete.discrete_model.Logit.fit_regularized Logit.fit_regularized(start_params=None, method='l1', maxiter='defined_by_method', full_output=1, disp=1, callback=None, alpha=0, trim_mode='auto', auto_trim_tol=0.01, size_trim_tol=0.0001, qc_tol=0.03, **kwargs) Fit the model using a regularized maximum likelihood. The regularization method AND the solver used is determined by the argument method. Parameters: start_params : array-like, optional Initial guess of the solution for the

Robust Linear Models Link to Notebook GitHub In [1]: from __future__ import print_function import numpy as np import statsmodels.api as sm import matplotlib.pyplot as plt from statsmodels.sandbox.regression.predstd import wls_prediction_std Estimation Load data: In [2]: data = sm.datasets.stackloss.load() data.exog = sm.add_constant(data.exog) Huber's T norm with the (default) median absolute deviation scaling In [3]: huber_t = sm.RLM(data.endog, data.e

statsmodels.tsa.filters.hp_filter.hpfilter statsmodels.tsa.filters.hp_filter.hpfilter(X, lamb=1600) [source] Hodrick-Prescott filter Parameters: X : array-like The 1d ndarray timeseries to filter of length (nobs,) or (nobs,1) lamb : float The Hodrick-Prescott smoothing parameter. A value of 1600 is suggested for quarterly data. Ravn and Uhlig suggest using a value of 6.25 (1600/4**4) for annual data and 129600 (1600*3**4) for monthly data. Returns: cycle : array The estimated cycle i

statsmodels.discrete.discrete_model.CountModel.fit CountModel.fit(start_params=None, method='newton', maxiter=35, full_output=1, disp=1, callback=None, **kwargs) [source] Fit the model using maximum likelihood. The rest of the docstring is from statsmodels.base.model.LikelihoodModel.fit Fit method for likelihood based models Parameters: start_params : array-like, optional Initial guess of the solution for the loglikelihood maximization. The default is an array of zeros. method : str, opti

statsmodels.miscmodels.count.PoissonGMLE.score_obs PoissonGMLE.score_obs(params, **kwds) Jacobian/Gradient of log-likelihood evaluated at params for each observation.

statsmodels.sandbox.regression.try_catdata.labelmeanfilter statsmodels.sandbox.regression.try_catdata.labelmeanfilter(y, x) [source]

Distributions This section collects various additional functions and methods for statistical distributions. Empirical Distributions ECDF(x[, side]) Return the Empirical CDF of an array as a step function. StepFunction(x, y[, ival, sorted, side]) A basic step function. Distribution Extras Skew Distributions SkewNorm_gen() univariate Skew-Normal distribution of Azzalini SkewNorm2_gen([momtype, a, b, xtol, ...]) univariate Skew-Normal distribution of Azzalini ACSkewT_gen() univariate Skew-

statsmodels.miscmodels.count.PoissonGMLE.nloglike PoissonGMLE.nloglike(params)

statsmodels.sandbox.distributions.transformed.Transf_gen.entropy Transf_gen.entropy(*args, **kwds) Differential entropy of the RV. Parameters: arg1, arg2, arg3,... : array_like The shape parameter(s) for the distribution (see docstring of the instance object for more information). loc : array_like, optional Location parameter (default=0). scale : array_like, optional Scale parameter (default=1).

statsmodels.sandbox.distributions.transformed.TransfTwo_gen.est_loc_scale TransfTwo_gen.est_loc_scale(*args, **kwds) est_loc_scale is deprecated! This function is deprecated, use self.fit_loc_scale(data) instead.