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 /opt/hostedtoolcache/Python/3.10.19/x64/lib/python3.10/site-packages/statsmodels/regression/linear_model.py:996, in OLS.__init__(self, endog, exog, missing, hasconst, **kwargs)
991 msg = (
992 "Weights are not supported in OLS and will be ignored"
993 "An exception will be raised in the next version."
994 )
995 warnings.warn(msg, ValueWarning, stacklevel=2)
--> 996 super().__init__(endog, exog, missing=missing, hasconst=hasconst, **kwargs)
997 if "weights" in self._init_keys:
998 self._init_keys.remove("weights")
File /opt/hostedtoolcache/Python/3.10.19/x64/lib/python3.10/site-packages/statsmodels/regression/linear_model.py:806, in WLS.__init__(self, endog, exog, weights, missing, hasconst, **kwargs)
804 else:
805 weights = weights.squeeze()
--> 806 super().__init__(
807 endog, exog, missing=missing, weights=weights, hasconst=hasconst, **kwargs
808 )
809 nobs = self.exog.shape[0]
810 weights = self.weights
File /opt/hostedtoolcache/Python/3.10.19/x64/lib/python3.10/site-packages/statsmodels/regression/linear_model.py:220, in RegressionModel.__init__(self, endog, exog, **kwargs)
219 def __init__(self, endog, exog, **kwargs):
--> 220 super().__init__(endog, exog, **kwargs)
221 self.pinv_wexog: Float64Array | None = None
222 self._data_attr.extend(["pinv_wexog", "wendog", "wexog", "weights"])
File /opt/hostedtoolcache/Python/3.10.19/x64/lib/python3.10/site-packages/statsmodels/base/model.py:285, in LikelihoodModel.__init__(self, endog, exog, **kwargs)
284 def __init__(self, endog, exog=None, **kwargs):
--> 285 super().__init__(endog, exog, **kwargs)
286 self.initialize()
File /opt/hostedtoolcache/Python/3.10.19/x64/lib/python3.10/site-packages/statsmodels/base/model.py:103, in Model.__init__(self, endog, exog, **kwargs)
101 missing = kwargs.pop("missing", "none")
102 hasconst = kwargs.pop("hasconst", None)
--> 103 self.data = self._handle_data(endog, exog, missing, hasconst, **kwargs)
104 self.k_constant = self.data.k_constant
105 self.exog = self.data.exog
File /opt/hostedtoolcache/Python/3.10.19/x64/lib/python3.10/site-packages/statsmodels/base/model.py:144, in Model._handle_data(self, endog, exog, missing, hasconst, **kwargs)
143 def _handle_data(self, endog, exog, missing, hasconst, **kwargs):
--> 144 data = handle_data(endog, exog, missing, hasconst, **kwargs)
145 # kwargs arrays could have changed, easier to just attach here
146 for key in kwargs:
File /opt/hostedtoolcache/Python/3.10.19/x64/lib/python3.10/site-packages/statsmodels/base/data.py:707, in handle_data(endog, exog, missing, hasconst, **kwargs)
704 exog = np.asarray(exog)
706 klass = handle_data_class_factory(endog, exog)
--> 707 return klass(endog, exog=exog, missing=missing, hasconst=hasconst, **kwargs)
File /opt/hostedtoolcache/Python/3.10.19/x64/lib/python3.10/site-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 /opt/hostedtoolcache/Python/3.10.19/x64/lib/python3.10/site-packages/statsmodels/base/data.py:296, in ModelData.handle_missing(cls, endog, exog, missing, **kwargs)
293 return combined, []
295 elif missing == "raise":
--> 296 raise MissingDataError("NaNs were encountered in the data")
298 elif missing == "drop":
299 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.