我希望这是我提出问题的正确地点。
我想了解运行 sm.OLS 时如何使用“hac-panel”cov_type。我已经为此奋斗了一整天，但仍然无法弄清楚。这是我的代码示例（带有数据）：
import pandas as pd
import statsmodels.api as sm
import statsmodels.formula.api as smf
from pandas.tseries.offsets import *
# Just grabbing some random data here
dat = sm.datasets.macrodata.load_pandas().data
dat['time'] = dat['year'].apply(lambda x: pd.to_datetime(x, format='%Y'))
dat['time'] = dat.apply(lambda x:(x['time'] + BQuarterBegin(x['quarter'])), axis=1)
dat = dat.set_index('time')
dat = dat.sort_index()
dat['dGDP'] = (dat['realgdp'] - dat['realgdp'].shift(1))/dat['realgdp'].shift(1) * 100.0
dat['dM1'] = (dat['m1'] - dat['m1'].shift(1))/dat['m1'].shift(1) * 100.0
dat['dUEMP'] = dat['unemp'] - dat['unemp'].shift(1)
dat['dCPI'] = dat['infl'] - dat['infl'].shift(1)
dat = dat[['dGDP', 'dM1', 'dUEMP', 'dCPI']]
# Fitting the model
y_var = dat.unstack()
x_var = pd.DataFrame(dat.shift(1).unstack(), columns=['01m']).combine_first(pd.DataFrame(dat.shift(3).unstack(), columns=['03m'])).combine_first(pd.DataFrame(dat.shift(12).unstack(), columns=['12m']))
model = sm.OLS(y_var, sm.add_constant(x_var), missing='drop')
这是有效的 - 据我了解它执行 HAC cov 的文档。但是，我不确定我是否正确调用它
res = model.fit(cov_type='hac-panel', cov_kwds={'time': dat.index, 'maxlags': 11})
res.summary()
这是我遇到问题的地方。假设我还想按时间进行聚类，我认为应该是这样的：
model.fit(cov_type='hac-panel', cov_kwds={'time': dat.index, 'groups': dat.index, 'maxlags': 11})
非常感谢所有帮助。预先非常感谢您。即使给我指出一个例子也很棒 - 找不到任何东西。
我收到此错误：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-2-74b3e662267b> in <module>
----> 1 model.fit(cov_type='hac-panel', cov_kwds={'time': dat.index, 'groups': dat.index, 'maxlags': 11})
~\anaconda3\lib\site-packages\statsmodels\regression\linear_model.py in fit(self, method, cov_type, cov_kwds, use_t, **kwargs)
343 self, beta,
344 normalized_cov_params=self.normalized_cov_params,
--> 345 cov_type=cov_type, cov_kwds=cov_kwds, use_t=use_t)
346 else:
347 lfit = RegressionResults(
~\anaconda3\lib\site-packages\statsmodels\regression\linear_model.py in __init__(self, model, params, normalized_cov_params, scale, cov_type, cov_kwds, use_t, **kwargs)
1555 # TODO: warn or not?
1556 self.get_robustcov_results(cov_type=cov_type, use_self=True,
-> 1557 use_t=use_t, **cov_kwds)
1558 for key in kwargs:
1559 setattr(self, key, kwargs[key])
~\anaconda3\lib\site-packages\statsmodels\regression\linear_model.py in get_robustcov_results(self, cov_type, use_t, **kwargs)
2490 res.cov_params_default = sw.cov_nw_panel(self, maxlags, groupidx,
2491 weights_func=weights_func,
-> 2492 use_correction=use_correction)
2493 res.cov_kwds['description'] = descriptions['HAC-Panel']
2494
~\anaconda3\lib\site-packages\statsmodels\stats\sandwich_covariance.py in cov_nw_panel(results, nlags, groupidx, weights_func, use_correction)
785 xu, hessian_inv = _get_sandwich_arrays(results)
786
--> 787 S_hac = S_nw_panel(xu, weights, groupidx)
788 cov_hac = _HCCM2(hessian_inv, S_hac)
789 if use_correction:
~\anaconda3\lib\site-packages\statsmodels\stats\sandwich_covariance.py in S_nw_panel(xw, weights, groupidx)
723 S = weights[0] * np.dot(xw.T, xw) #weights just for completeness
724 for lag in range(1, nlags+1):
--> 725 xw0, xwlag = lagged_groups(xw, lag, groupidx)
726 s = np.dot(xw0.T, xwlag)
727 S += weights[lag] * (s + s.T)
~\anaconda3\lib\site-packages\statsmodels\stats\sandwich_covariance.py in lagged_groups(x, lag, groupidx)
706
707 if out0 == []:
--> 708 raise ValueError('all groups are empty taking lags')
709 #return out0, out_lagged
710 return np.vstack(out0), np.vstack(out_lagged)
ValueError: all groups are empty taking lags
