A maximum likelihood estimator for left-truncated lifetimes based on probabilistic prior information about time of occurrence. Issue 12 (10th September 2018)

• Record Type: Journal Article
• Authors: Manso, Rubén; Calama, Rafael; Pardos, Marta; Fortin, Mathieu
• Is Part Of: Journal of applied statistics. Volume 45:Issue 12(2018)
• Page Start: 2107
• Page End: 2127
• Publication Date: 2018-09-10
• Subjects: Lifetime analysis -- left truncation -- likelihood estimation -- marginal likelihood -- Bayes' theorem -- Gompertz hazard; Statistics -- Periodicals; 519.5
• DOI: 10.1080/02664763.2017.1410527
• Languages: English
• ISSNs: 0266-4763

Abstract

ABSTRACT: In forestry, many processes of interest are binary and they can be modeled using lifetime analysis. However, available data are often incomplete, being interval- and right-censored as well as left-truncated, which may lead to biased parameter estimates. While censoring can be easily considered in lifetime analysis, left truncation is more complicated when individual age at selection is unknown. In this study, we designed and tested a maximum likelihood estimator that deals with left truncation by taking advantage of prior knowledge about the time when the individuals enter the experiment. Whenever a model is available for predicting the time of selection, the distribution of the delayed entries can be obtained using Bayes' theorem. It is then possible to marginalize the likelihood function over the distribution of the delayed entries in the experiment to assess the joint distribution of time of selection and time to event. This estimator was tested with continuous and discrete Gompertz-distributed lifetimes. It was then compared with two other estimators: a standard one in which left truncation was not considered and a second estimator that implemented an analytical correction. Our new estimator yielded unbiased parameter estimates with empirical coverage of confidence intervals close to their nominal value. The standard estimator leaded to an overestimation of the long-term probability of survival.