loss
of precision when :math:`\exp(z)` is nearly :math:`0` or :math:`1`.
Similarly, the term "logarithmic sum" of :math:`w` and :math:`z`
is used here to mean the :math:`\log(\exp(w)+\exp(z))`, AKA
:math:`\text{LogSumExp}(w, z)`.

References
----------
.. [1] Cumulative distribution function, *Wikipedia*,
       https://en.wikipedia.org/wiki/Cumulative_distribution_function#Derived_functions

Examples
--------
Instantiate a distribution with the desired parameters:

>>> import numpy as np
>>> from scipy import stats
>>> X = stats.Uniform(a=-0.5, b=0.5)

Evaluate the log-CCDF at the desired argument:

>>> X.logccdf(0.25)
-1.3862943611198906
>>> np.allclose(X.logccdf(0.), np.log(X.ccdf(0.)))
True

r