statsmodels.sandbox.regression.try_catdata.groupsstats_dummy statsmodels.sandbox.regression.try_catdata.groupsstats_dummy(y, x, nonseq=0) [source]

statsmodels.sandbox.regression.try_catdata.groupsstats_1d statsmodels.sandbox.regression.try_catdata.groupsstats_1d(y, x, labelsunique) [source] use ndimage to get fast mean and variance

statsmodels.sandbox.regression.try_catdata.convertlabels statsmodels.sandbox.regression.try_catdata.convertlabels(ys, indices=None) [source] convert labels based on multiple variables or string labels to unique index labels 0,1,2,...,nk-1 where nk is the number of distinct labels

statsmodels.sandbox.regression.try_catdata.cat2dummy statsmodels.sandbox.regression.try_catdata.cat2dummy(y, nonseq=0) [source]

statsmodels.sandbox.regression.gmm.NonlinearIVGMM class statsmodels.sandbox.regression.gmm.NonlinearIVGMM(endog, exog, instrument, func, **kwds) [source] Class for non-linear instrumental variables estimation wusing GMM The model is assumed to have the following moment condition E[ z * (y - f(X, beta)] = 0 Where y is the dependent endogenous variable, x are the explanatory variables and z are the instruments. Variables in x that are exogenous need also be included in z. f is a nonlinear fun

statsmodels.sandbox.regression.gmm.LinearIVGMM class statsmodels.sandbox.regression.gmm.LinearIVGMM(endog, exog, instrument, k_moms=None, k_params=None, missing='none', **kwds) [source] class for linear instrumental variables models estimated with GMM Uses closed form expression instead of nonlinear optimizers for each step of the iterative GMM. The model is assumed to have the following moment condition E( z * (y - x beta)) = 0 Where y is the dependent endogenous variable, x are the explan

statsmodels.sandbox.regression.gmm.IVRegressionResults class statsmodels.sandbox.regression.gmm.IVRegressionResults(model, params, normalized_cov_params=None, scale=1.0, cov_type='nonrobust', cov_kwds=None, use_t=None) [source] Results class for for an OLS model. Most of the methods and attributes are inherited from RegressionResults. The special methods that are only available for OLS are: get_influence outlier_test el_test conf_int_el See also RegressionResults Methods HC0_se() See stat

statsmodels.sandbox.regression.gmm.IVGMMResults class statsmodels.sandbox.regression.gmm.IVGMMResults(*args, **kwds) [source] Methods calc_cov_params(moms, gradmoms[, weights, ...]) calculate covariance of parameter estimates compare_j(other) overidentification test for comparing two nested gmm estimates conf_int([alpha, cols, method]) Returns the confidence interval of the fitted parameters. cov_params(**kwds) f_test(r_matrix[, cov_p, scale, invcov]) Compute the F-test for a joint lin

statsmodels.sandbox.regression.gmm.IVGMM class statsmodels.sandbox.regression.gmm.IVGMM(endog, exog, instrument, k_moms=None, k_params=None, missing='none', **kwds) [source] Basic class for instrumental variables estimation using GMM A linear function for the conditional mean is defined as default but the methods should be overwritten by subclasses, currently LinearIVGMM and NonlinearIVGMM are implemented as subclasses. See also LinearIVGMM, NonlinearIVGMM Methods calc_weightmatrix(moms[,

statsmodels.sandbox.regression.gmm.IV2SLS class statsmodels.sandbox.regression.gmm.IV2SLS(endog, exog, instrument=None) [source] Class for instrumental variables estimation using Two-Stage Least-Squares Parameters: endog: array 1d : endogenous variable exog : array explanatory variables instruments : array instruments for explanatory variables, needs to contain those exog variables that are not instrumented out Notes All variables in exog are instrumented in the calculations. If vari