0
$\begingroup$

For right-censored failure time data, in a non-parametric setting, is there an equivalence between using the EM algorithm (i.e. calculating the expected log-likelihood and maximizing) and the Kaplan-Meier estimator? Any references or explanation are appreciated.

$\endgroup$

1 Answer 1

0
$\begingroup$

BW Turnbull - ‎1976 paper: The empirical distribution function with arbitrarily grouped, censored and truncated data

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.