Estimation of average mortality under censoring and truncation

In demography mortality is usually reported through averages over time intervals. If average mortality is estimated from censored or truncated data, then direct methods of estimation may create biases that depend on the censoring or truncation distribution. Such discretization errors may be avoided by estimating survival curves first in continuous time, and then discretizing the estimators. We illustrate the different methods on data of the form obtained from family reconstitution.