statsmodels.tools.eval_measures.meanabs statsmodels.tools.eval_measures.meanabs(x1, x2, axis=0) [source] mean absolute error Parameters: x1, x2 : array_like The performance measure depends on the difference between these two arrays. axis : int axis along which the summary statistic is calculated Returns: meanabs : ndarray or float mean absolute difference along given axis. Notes If x1 and x2 have different shapes, then they need to broadcast. This uses numpy.asanyarray to convert t

statsmodels.genmod.families.family.Binomial.fitted Binomial.fitted(lin_pred) Fitted values based on linear predictors lin_pred. Parameters: lin_pred : array Values of the linear predictor of the model. dot(X,beta) in a classical linear model. Returns: mu : array The mean response variables given by the inverse of the link function.

statsmodels.sandbox.regression.gmm.IVGMMResults.calc_cov_params IVGMMResults.calc_cov_params(moms, gradmoms, weights=None, use_weights=False, has_optimal_weights=True, weights_method='cov', wargs=()) calculate covariance of parameter estimates not all options tried out yet If weights matrix is given, then the formula use to calculate cov_params depends on whether has_optimal_weights is true. If no weights are given, then the weight matrix is calculated with the given method, and has_optimal_

statsmodels.discrete.discrete_model.BinaryResults.resid_dev static BinaryResults.resid_dev() [source] Deviance residuals Notes Deviance residuals are defined where and is the total number of observations sharing the covariate pattern . For now is always set to 1.

statsmodels.regression.linear_model.GLS.predict GLS.predict(params, exog=None) Return linear predicted values from a design matrix. Parameters: params : array-like Parameters of a linear model exog : array-like, optional. Design / exogenous data. Model exog is used if None. Returns: An array of fitted values : Notes If the model has not yet been fit, params is not optional.

statsmodels.regression.mixed_linear_model.MixedLM.hessian_full MixedLM.hessian_full(params) [source] Calculates the Hessian matrix for the mixed effects model with respect to the parameterization in which the covariance matrix is represented directly (without square-root transformation). Parameters: params : MixedLMParams or array-like The model parameters at which the Hessian is calculated. If array-like, must contain the packed parameters in a form that is compatible with this model inst

statsmodels.emplike.descriptive.DescStatUV.test_mean DescStatUV.test_mean(mu0, return_weights=False) [source] Returns - 2 x log-likelihood ratio, p-value and weights for a hypothesis test of the mean. Parameters: mu0 : float Mean value to be tested return_weights : bool If return_weights is True the funtion returns the weights of the observations under the null hypothesis. Default is False Returns: test_results : tuple The log-likelihood ratio and p-value of mu0

statsmodels.sandbox.distributions.extras.SkewNorm_gen.var SkewNorm_gen.var(*args, **kwds) Variance of the distribution 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) Returns: var : float the variance of the distribution

statsmodels.regression.mixed_linear_model.MixedLM.EM MixedLM.EM(fe_params, cov_re, scale, niter_em=10, hist=None) [source] Run the EM algorithm from a given starting point. This is for ML (not REML), but it seems to be good enough to use for REML starting values. Returns: fe_params : 1d ndarray The final value of the fixed effects coefficients cov_re : 2d ndarray The final value of the random effects covariance matrix scale : float The final value of the error variance Notes This use

statsmodels.tsa.vector_ar.var_model.VARResults.test_normality VARResults.test_normality(signif=0.05, verbose=True) [source] Test assumption of normal-distributed errors using Jarque-Bera-style omnibus Chi^2 test Parameters: signif : float Test significance threshold Notes H0 (null) : data are generated by a Gaussian-distributed process