February 4th 2016
Faculty of Economic and Business Sciences | Salón de Grados
Survival analysis with delayed entry in selected families with application to human longevity
2016/02/04 – 10:00 h | Mar R. Girondo (Leiden University Medical Center)
Abstract
In the field of aging research, family-based sampling study designs are commonly used to study the lifespans of long-lived family members. However, the specific sampling procedure should be carefully taken into account in order to avoid biases. This work is motivated by the Leiden Longevity Study (LLS), a family-based cohort of long-lived siblings. Families were invited to participate in the study if at least two siblings were `long-lived’, where `long-lived’ meant being older than 89 years for men or older than 91 years for women. As a result, more than 400 families were included in the study and followed for around 10 years. Statistical challenges in this framework are to deal with delayed entry due to outcome-dependent sampling mechanisms, to take into account correlation between family members, and to deal with the interplay between them. We consider shared frailty models to model left-truncated correlated survival data. The treatment of left truncation in shared frailty models is still an open issue and the literature on this topic is scarce. We show that the current approaches provide, in general biased estimates and we proposea new method to tackle this selection problem by applying a correction on the likelihood estimation by means of inverse probability weighting at the family level.
Gallery
Planning clinical trials with composite endpoints
2016/02/04 – 11:00 h | Guadalupe Gómez (Universitat Politécnica de Catalunya)
Abstract
Randomized clinical trials (RCT) provide compelling evidence that a study treatment causes an effect on human health. A primary endpoint (PE) ought to be chosen to confirm the effectiveness of the treatment and is the basis for computing the number of subjects in the RCT. Often a Composite Endpoint (CE) based on a combination of individual endpoints is chosen as a PE. As a tool for a more informed decision between using the CE as PE or one of the components or the CE, Gómez and Lagakos (Statistics in Medicine, 2013) proposed the ARE method. This method uses the asymptotic relative efficiency between the two possible logrank tests to compare the effect of the treatment.
I will give an overview of RCT and discuss advantages and disadvantages of CE. Next I will explain the ARE method and illustrate how can be applied in several areas: oncology, cardiovascular research area, etc. I will present CompARE, a web-based interface tool that computes the ARE in terms of interpretable parameters such as the anticipated probabilities of observing the primary and secondary endpoints and the relative treatment effects on every endpoint given by the corresponding hazard ratios. I will close the talk with ongoing research on the use of the ARE to derive the sample size for the CE, in particular when the proportional hazards assumption does not hold, and on the extension of the ARE method to observational studies end to binary CE.
Gallery
