Bias in progression‐free survival analysis due to intermittent assessment of progression

摘要: Cancer clinical trials are routinely designed to assess the effect of treatment on disease progression and death, often in terms a composite endpoint called progression‐free survival. When status is known only at periodic assessment times, time interval censored, complications arise analysis Despite advances methods for dealing with interval‐censored data, naive such as right‐endpoint imputation widely adopted this setting. We examine asymptotic empirical properties estimators marginal survival functions associated effects under scheme. Specifically, we explore determinants bias point out that there typically loss power tests effects. Copyright © 2015 John Wiley & Sons, Ltd.