= Events divided by exposure estimator
{title2=$\widehat\theta=d/\sum_i x_i$}
For independent exponentially distributed failure times subject to independent <right censoring>, let $d$ be observed failures and $E=\sum_i x_i$ total follow-up exposure. The parameter-dependent <likelihood> is $\theta^d e^{-\theta E}$, giving <maximum-likelihood estimator> $\widehat\theta=d/E$. The fitted individual <cumulative hazards> sum to $d$, but this estimating identity alone does not establish that a constant hazard model fits.
Back to article page
