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)
836 **kwargs):
837 super(OLS, self).__init__(endog, exog, missing=missing,
--> 838 hasconst=hasconst, **kwargs)
839 if "weights" in self._init_keys:
840 self._init_keys.remove("weights")
/usr/lib/python3/dist-packages/statsmodels/regression/linear_model.py in __init__(self, endog, exog, weights, missing, hasconst, **kwargs)
682 weights = weights.squeeze()
683 super(WLS, self).__init__(endog, exog, missing=missing,
--> 684 weights=weights, hasconst=hasconst, **kwargs)
685 nobs = self.exog.shape[0]
686 weights = self.weights
/usr/lib/python3/dist-packages/statsmodels/regression/linear_model.py in __init__(self, endog, exog, **kwargs)
194 """
195 def __init__(self, endog, exog, **kwargs):
--> 196 super(RegressionModel, self).__init__(endog, exog, **kwargs)
197 self._data_attr.extend(['pinv_wexog', 'wendog', 'wexog', 'weights'])
198
/usr/lib/python3/dist-packages/statsmodels/base/model.py in __init__(self, endog, exog, **kwargs)
214
215 def __init__(self, endog, exog=None, **kwargs):
--> 216 super(LikelihoodModel, self).__init__(endog, exog, **kwargs)
217 self.initialize()
218
/usr/lib/python3/dist-packages/statsmodels/base/model.py in __init__(self, endog, exog, **kwargs)
66 hasconst = kwargs.pop('hasconst', None)
67 self.data = self._handle_data(endog, exog, missing, hasconst,
---> 68 **kwargs)
69 self.k_constant = self.data.k_constant
70 self.exog = self.data.exog
/usr/lib/python3/dist-packages/statsmodels/base/model.py in _handle_data(self, endog, exog, missing, hasconst, **kwargs)
89
90 def _handle_data(self, endog, exog, missing, hasconst, **kwargs):
---> 91 data = handle_data(endog, exog, missing, hasconst, **kwargs)
92 # kwargs arrays could have changed, easier to just attach here
93 for key in kwargs:
/usr/lib/python3/dist-packages/statsmodels/base/data.py in handle_data(endog, exog, missing, hasconst, **kwargs)
633 klass = handle_data_class_factory(endog, exog)
634 return klass(endog, exog=exog, missing=missing, hasconst=hasconst,
--> 635 **kwargs)
/usr/lib/python3/dist-packages/statsmodels/base/data.py in __init__(self, endog, exog, missing, hasconst, **kwargs)
63 if missing != 'none':
64 arrays, nan_idx = self.handle_missing(endog, exog, missing,
---> 65 **kwargs)
66 self.missing_row_idx = nan_idx
67 self.__dict__.update(arrays) # attach all the data arrays
/usr/lib/python3/dist-packages/statsmodels/base/data.py in handle_missing(cls, endog, exog, missing, **kwargs)
275
276 elif missing == 'raise':
--> 277 raise MissingDataError("NaNs were encountered in the data")
278
279 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.