On induced dependent censoring for quality adjusted lifetime (QAL) data in a simple illness-death model

It is well known that the Kaplan-Meier estimate of QAL data leads to a biased estimate due to the induced dependence between the QAL and censoring time in the QAL scale. However, the issue of induced dependent censoring in the QAL scale remains less understood. We present a formal study of this induced dependence in the context of a simple illness-death model. The bias of the Kaplan-Meier estimate of the QAL distribution has been investigated.