Control‐based imputation for sensitivity analyses in informative censoring for recurrent event data

In clinical trials, missing data commonly arise through nonadherence to the randomized treatment or to study procedure. For trials in which recurrent event endpoints are of interests, conventional analyses using the proportional intensity model or the count model assume that the data are missing at random, which cannot be tested using the observed data alone. Thus, sensitivity analyses are recommended. We implement the control‐based multiple imputation as sensitivity analyses for the recurrent event data. We model the recurrent event using a piecewise exponential proportional intensity model with frailty and sample the parameters from the posterior distribution. We impute the number of events after dropped out and correct the variance estimation using a bootstrap procedure. We apply the method to an application of sitagliptin study.     

A course for clinical trial personnel in clinical study designs, randomization, allocation schedules, and interactive response systems

This continuing education course for professionals involved in all areas of clinical trials integrates concepts related to the role of randomization in the scientific process. The course includes two interactive lecture and discussion sections and a workshop practicum. The first interactive lecture introduces basic clinical trial issues and statistical principles such as bias, blinding, randomization, control groups, and the importance of formulating clear and discriminating clinical and statistical hypotheses. It then focuses on the most commonly used clinical study designs and the corresponding patient randomization schemes. The second interactive lecture focuses on the implementation of randomization of patients and drug supply through allocation and component ID schedules. The workshop practicum, conducted in small groups, enables students to apply the lecture concepts to real clinical studies. Flexibility was built into the workshop practicum materials to allow the course content to be customized to specific audiences, and the interactive lecture sessions can be stretched to cover more advanced topics according to class interest and time availability.     

Bringing the past into our future—using historic data to inform contemporary freshwater management

Knowledge of landscapes, and how landscapes were utilised by Ngāi Tahu, helps provide a context within which to examine the contemporary aspirations of Ngāi Tahu with respect to resource management. Using the Waitaki catchment as a case study, it describes how to weave together strands of Ngāi Tahu history from a variety of sources to guide contemporary resource management. One of the greatest challenges, however, is determining appropriate management goals and, in particular, restoration goals. Understanding sites as they existed at the time of European settlement can be extremely difficult due the nature and extent of modification in subsequent decades. Restoring a degraded area to match some pre-existing condition, such as pre-European settlement, which is often the goal of restoration initiatives, is difficult unless data on historic conditions are available. We describe how to piece together historic patterns of activity within the catchment, and the forces that have been instrumental in changing it, thus providing a framework upon which resource management goals can be developed.