statsmodels.sandbox.regression.gmm.IVRegressionResults.mse_model static IVRegressionResults.mse_model()

statsmodels.regression.linear_model.OLSResults.cov_HC0 static OLSResults.cov_HC0() See statsmodels.RegressionResults

statsmodels.discrete.discrete_model.DiscreteModel.loglike DiscreteModel.loglike(params) Log-likelihood of model.

statsmodels.sandbox.regression.gmm.GMMResults.jtest GMMResults.jtest() [source] overidentification test I guess this is missing a division by nobs, what?s the normalization in jval ?

statsmodels.miscmodels.count.PoissonZiGMLE class statsmodels.miscmodels.count.PoissonZiGMLE(endog, exog=None, offset=None, missing='none', **kwds) [source] Maximum Likelihood Estimation of Poisson Model This is an example for generic MLE which has the same statistical model as discretemod.Poisson but adds offset and zero-inflation. Except for defining the negative log-likelihood method, all methods and results are generic. Gradients and Hessian and all resulting statistics are based on numer

statsmodels.robust.robust_linear_model.RLM.hessian RLM.hessian(params) The Hessian matrix of the model

statsmodels.discrete.discrete_model.ProbitResults.initialize ProbitResults.initialize(model, params, **kwd)

statsmodels.sandbox.regression.gmm.IVRegressionResults.bse static IVRegressionResults.bse()

statsmodels.regression.linear_model.OLSResults.centered_tss static OLSResults.centered_tss()

statsmodels.tsa.stattools.arma_order_select_ic statsmodels.tsa.stattools.arma_order_select_ic(y, max_ar=4, max_ma=2, ic='bic', trend='c', model_kw={}, fit_kw={}) [source] Returns information criteria for many ARMA models Parameters: y : array-like Time-series data max_ar : int Maximum number of AR lags to use. Default 4. max_ma : int Maximum number of MA lags to use. Default 2. ic : str, list Information criteria to report. Either a single string or a list of different criteria is po