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()
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)
const NaN
GNPDEFL NaN
GNP NaN
UNEMP NaN
ARMED NaN
POP NaN
YEAR NaN
dtype: float64
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)
Cell In[10], line 1
----> 1 ols_model = sm.OLS(data.endog, data.exog, missing='raise')
File /usr/lib/python3/dist-packages/statsmodels/regression/linear_model.py:1040, in OLS.__init__(self, endog, exog, missing, hasconst, **kwargs)
1035 msg = (
1036 "Weights are not supported in OLS and will be ignored"
1037 "An exception will be raised in the next version."
1038 )
1039 warnings.warn(msg, ValueWarning, stacklevel=2)
-> 1040 super().__init__(endog, exog, missing=missing, hasconst=hasconst, **kwargs)
1041 if "weights" in self._init_keys:
1042 self._init_keys.remove("weights")
File /usr/lib/python3/dist-packages/statsmodels/regression/linear_model.py:850, in WLS.__init__(self, endog, exog, weights, missing, hasconst, **kwargs)
848 else:
849 weights = weights.squeeze()
--> 850 super().__init__(
851 endog, exog, missing=missing, weights=weights, hasconst=hasconst, **kwargs
852 )
853 nobs = self.exog.shape[0]
854 weights = self.weights
File /usr/lib/python3/dist-packages/statsmodels/regression/linear_model.py:246, in RegressionModel.__init__(self, endog, exog, **kwargs)
245 def __init__(self, endog, exog, **kwargs):
--> 246 super().__init__(endog, exog, **kwargs)
247 self.pinv_wexog: Float64Array | None = None
248 self._data_attr.extend(["pinv_wexog", "wendog", "wexog", "weights"])
File /usr/lib/python3/dist-packages/statsmodels/base/model.py:287, in LikelihoodModel.__init__(self, endog, exog, **kwargs)
286 def __init__(self, endog, exog=None, **kwargs):
--> 287 super().__init__(endog, exog, **kwargs)
288 self.initialize()
File /usr/lib/python3/dist-packages/statsmodels/base/model.py:102, in Model.__init__(self, endog, exog, **kwargs)
100 missing = kwargs.pop("missing", "none")
101 hasconst = kwargs.pop("hasconst", None)
--> 102 self.data = self._handle_data(endog, exog, missing, hasconst, **kwargs)
103 self.k_constant = self.data.k_constant
104 self.exog = self.data.exog
File /usr/lib/python3/dist-packages/statsmodels/base/model.py:143, in Model._handle_data(self, endog, exog, missing, hasconst, **kwargs)
142 def _handle_data(self, endog, exog, missing, hasconst, **kwargs):
--> 143 data = handle_data(endog, exog, missing, hasconst, **kwargs)
144 # kwargs arrays could have changed, easier to just attach here
145 for key in kwargs:
File /usr/lib/python3/dist-packages/statsmodels/base/data.py:747, in handle_data(endog, exog, missing, hasconst, **kwargs)
744 exog = np.asarray(exog)
746 klass = handle_data_class_factory(endog, exog)
--> 747 return klass(endog, exog=exog, missing=missing, hasconst=hasconst, **kwargs)
File /usr/lib/python3/dist-packages/statsmodels/base/data.py:76, in ModelData.__init__(self, endog, exog, missing, hasconst, **kwargs)
74 self.formula = kwargs.pop("formula")
75 if missing != "none":
---> 76 arrays, nan_idx = self.handle_missing(endog, exog, missing, **kwargs)
77 self.missing_row_idx = nan_idx
78 self.__dict__.update(arrays) # attach all the data arrays
File /usr/lib/python3/dist-packages/statsmodels/base/data.py:319, in ModelData.handle_missing(cls, endog, exog, missing, **kwargs)
316 return combined, []
318 elif missing == "raise":
--> 319 raise MissingDataError("NaNs were encountered in the data")
321 elif missing == "drop":
322 nan_mask = ~nan_mask
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.