NegativeBinomialResults.t_test_pairwise(term_name, method='hs', alpha=0.05, factor_labels=None)
perform pairwise t_test with multiple testing corrected pvalues
This uses the formula design_info encoding contrast matrix and should work for all encodings of a main effect.
Parameters: 


Returns: 
results – The results are stored as attributes, the main attributes are the following two. Other attributes are added for debugging purposes or as background information.

Return type: 
instance of a simple Results class 
Status: experimental. Currently only checked for treatment coding with and without specified reference level.
Currently there are no multiple testing corrected confidence intervals available.
>>> res = ols("np.log(Days+1) ~ C(Weight) + C(Duration)", data).fit() >>> pw = res.t_test_pairwise("C(Weight)") >>> pw.result_frame coef std err t P>t Conf. Int. Low 21 0.632315 0.230003 2.749157 8.028083e03 0.171563 31 1.302555 0.230003 5.663201 5.331513e07 0.841803 32 0.670240 0.230003 2.914044 5.119126e03 0.209488 Conf. Int. Upp. pvaluehs rejecths 21 1.093067 0.010212 True 31 1.763307 0.000002 True 32 1.130992 0.010212 True
© 2009–2012 Statsmodels Developers
© 2006–2008 Scipy Developers
© 2006 Jonathan E. Taylor
Licensed under the 3clause BSD License.
http://www.statsmodels.org/stable/generated/statsmodels.discrete.discrete_model.NegativeBinomialResults.t_test_pairwise.html