Fit Nonparametric Distributions to Survival Data 

Any of the nonparametric distributions can be fitted directly to censored and truncated data. Here are some doubly (left and right) censored event times.

In[1]:=

X \[ScriptCapitalD] = EventData[{10, 11, 12, 13, 14, 15, 16, 17, 18}, {{4, 0, 0}, {12, 0, 0}, {19, 2, 0}, {24, 15, 1}, {20, 24, 2}, {13, 18, 3}, {3, 14, 2}, {1, 6, 3}, {0, 4, 1}}];

Fit some nonparametric distributions and compute their means.

In[2]:=

X edist = EmpiricalDistribution[\[ScriptCapitalD]]; hdist = HistogramDistribution[\[ScriptCapitalD], {.8}]; sdist = SmoothKernelDistribution[\[ScriptCapitalD], .3]; kdist = KernelMixtureDistribution[\[ScriptCapitalD]]; Mean /@ {edist, hdist, sdist, kdist}

Out[3]=

Cumulative hazard estimates for the doubly censored EventData.