Linear rank tests for doubly censored data

Abstract

Abstract This paper establishes the asymptotic properties of the non‐parametric maximum likelihood estimator of the survival function based on data censored both from the left and the right. We show that the sample mean based on the survival estimator converges to a normal distribution, and we derive non‐parametric tests for the differences in survival functions. The methods are applied to a study of dementia associated with Parkinson's disease.