Missing Data¶
All of the models can handle missing data. For performance reasons, the default is not to do any checking for missing data. If, however, you would like for missing data to be handled internally, you can do so by using the missing keyword argument. The default is to do nothing
In [1]: import statsmodels.api as sm
In [2]: data = sm.datasets.longley.load(as_pandas=False)
In [3]: data.exog = sm.add_constant(data.exog)
# add in some missing data
In [4]: missing_idx = np.array([False] * len(data.endog))
In [5]: missing_idx[[4, 10, 15]] = True
In [6]: data.endog[missing_idx] = np.nan
In [7]: ols_model = sm.OLS(data.endog, data.exog)
In [8]: ols_fit = ols_model.fit()
In [9]: print(ols_fit.params)
[nan nan nan nan nan nan nan]
This silently fails and all of the model parameters are NaN, which is probably not what you expected. If you are not sure whether or not you have missing data you can use missing = ‘raise’. This will raise a MissingDataError during model instantiation if missing data is present so that you know something was wrong in your input data.
In [10]: ols_model = sm.OLS(data.endog, data.exog, missing='raise')
---------------------------------------------------------------------------
MissingDataError Traceback (most recent call last)
<ipython-input-10-5debd60362bf> in <module>
----> 1 ols_model = sm.OLS(data.endog, data.exog, missing='raise')
/usr/lib/python3/dist-packages/statsmodels/regression/linear_model.py in __init__(self, endog, exog, missing, hasconst, **kwargs)
856 def __init__(self, endog, exog=None, missing='none', hasconst=None,
857 **kwargs):
--> 858 super(OLS, self).__init__(endog, exog, missing=missing,
859 hasconst=hasconst, **kwargs)
860 if "weights" in self._init_keys:
/usr/lib/python3/dist-packages/statsmodels/regression/linear_model.py in __init__(self, endog, exog, weights, missing, hasconst, **kwargs)
699 else:
700 weights = weights.squeeze()
--> 701 super(WLS, self).__init__(endog, exog, missing=missing,
702 weights=weights, hasconst=hasconst, **kwargs)
703 nobs = self.exog.shape[0]
/usr/lib/python3/dist-packages/statsmodels/regression/linear_model.py in __init__(self, endog, exog, **kwargs)
188 """
189 def __init__(self, endog, exog, **kwargs):
--> 190 super(RegressionModel, self).__init__(endog, exog, **kwargs)
191 self._data_attr.extend(['pinv_wexog', 'wendog', 'wexog', 'weights'])
192
/usr/lib/python3/dist-packages/statsmodels/base/model.py in __init__(self, endog, exog, **kwargs)
234
235 def __init__(self, endog, exog=None, **kwargs):
--> 236 super(LikelihoodModel, self).__init__(endog, exog, **kwargs)
237 self.initialize()
238
/usr/lib/python3/dist-packages/statsmodels/base/model.py in __init__(self, endog, exog, **kwargs)
74 missing = kwargs.pop('missing', 'none')
75 hasconst = kwargs.pop('hasconst', None)
---> 76 self.data = self._handle_data(endog, exog, missing, hasconst,
77 **kwargs)
78 self.k_constant = self.data.k_constant
/usr/lib/python3/dist-packages/statsmodels/base/model.py in _handle_data(self, endog, exog, missing, hasconst, **kwargs)
98
99 def _handle_data(self, endog, exog, missing, hasconst, **kwargs):
--> 100 data = handle_data(endog, exog, missing, hasconst, **kwargs)
101 # kwargs arrays could have changed, easier to just attach here
102 for key in kwargs:
/usr/lib/python3/dist-packages/statsmodels/base/data.py in handle_data(endog, exog, missing, hasconst, **kwargs)
669
670 klass = handle_data_class_factory(endog, exog)
--> 671 return klass(endog, exog=exog, missing=missing, hasconst=hasconst,
672 **kwargs)
/usr/lib/python3/dist-packages/statsmodels/base/data.py in __init__(self, endog, exog, missing, hasconst, **kwargs)
69 self.formula = kwargs.pop('formula')
70 if missing != 'none':
---> 71 arrays, nan_idx = self.handle_missing(endog, exog, missing,
72 **kwargs)
73 self.missing_row_idx = nan_idx
/usr/lib/python3/dist-packages/statsmodels/base/data.py in handle_missing(cls, endog, exog, missing, **kwargs)
283
284 elif missing == 'raise':
--> 285 raise MissingDataError("NaNs were encountered in the data")
286
287 elif missing == 'drop':
MissingDataError: NaNs were encountered in the data
If you want statsmodels to handle the missing data by dropping the observations, use missing = ‘drop’.
In [11]: ols_model = sm.OLS(data.endog, data.exog, missing='drop')
We are considering adding a configuration framework so that you can set the option with a global setting.