A Comparison of Information Concerning the Regression Parameter in The Accelerated Failure Time Model under Current Duration and Length Biased Sampling: Does it Pay to be Patient?

摘要

Longitudinal observations are sometimes costly or not available. Crosssectional sampling can be an alternative. Observations are drawn then at aspecific point in time from a population of durations whose distributionssatisfy a {\em core model}. Subsequently, one has a choice. One may process thedata immediately, obtaining so called current duration data. Or one waits untilthe sampled durations are known completely obtaining the full durations vialength biased sampling. We compare the Fisher information for the Euclideanparameter corresponding to an Accelerated Failure Time core model when theobservations are obtained by either current duration or length biased sampling.