Journal de biométrie et biostatistique

On the Identification of the Survivor Average Causal Effect

Abstract

Yasutaka Chiba, Masataka Taguri and Yukari Uemura

In randomized trials in which the outcome requires considerable follow-up, participants may die before the trial is complete. In such cases, for the individuals who die before follow-up is complete, the outcome is not simply missing, but is undefined. Some authors refer to this situation as one in which the outcome is “truncated by death� [1,2], to distinguish this scenario from cases in which the outcome is merely missing because of inadequate data collection. In these settings, a crude comparison of the outcome between those who survived in each treatment arm may give misleading results, because we no longer preserve randomization by conditioning on a post-treatment event (survival) and thus the crude comparison is not a comparison for the same population comparing different treatments, but a comparison of different populations.