我有一个混合效果模型,如下所示:
import statsmodels.formula.api as smf
formula = "revised_error ~ C(condition, Treatment('solo_feedback'))*round_index"
model = smf.mixedlm(forumla, data=data, groups=data['player_id']).fit()
现在model.conf_int()
为我提供了基于标准正态分布的拟合参数的置信区间。但是,我需要自举系数和置信度,但是model.boostrap()
会引发错误:
AttributeError: 'MixedLMResults' object has no attribute 'endog'