This is for a 12-week internship position from June – August 2021.

Application of Bayesian design has been expanding in the regulatory setting to alleviate the unmet needs of clinical trial development (e.g. rare disease, pediatric studies) and to improve the efficiency of the trials with fewer patients and lower cost by leveraging external data. Though the regulatory entities support the proposal of Bayesian design in the registration trials, considerable evaluations of the design should be conducted including but not limited to the choice of prior distribution, chance of producing erroneous conclusions (type I error control), and the reliability of treatment effect estimates (power). These requirements necessitate intensive simulations to evaluate the operational characteristics of the Bayesian design. In the current regulatory settings, no formalization of the use of Bayesian design software packages has been endorsed. Therefore, it is critical to make appropriate choice of Bayesian software packages under various scenarios.

The main objective for this intern project is to compare the performance of Bayesian software packages and explore the algorithms utilized in the Bayesian software packages. In Bayesian inference, the posterior draws are generally from Makov Chain Monte Carlo (MCMC). The efficiency of the sampling and the accuracy of posterior estimates due to sampling error are also of interest when using different Bayesian software packages. To quantify Monte Carlo Standard Error (MCSE) for Bayesian designs becomes fundamental and the quantification of MCSE for the Bayesian design characteristics is challenging. Furthermore, the project will also review the Bayesian designs that have been accepted for the registration purpose in clinical development program (CDP).

Position Description

The Biostatistics Intern position provides an exciting opportunity to gain hands-on experience and exposure to the biotechnology/pharmaceutical industry.

• Detailed description of role including but not limited to:
• To review Bayesian designs utilized for clinical trial development
• To develop simulation plans that evaluate and compare the performance of Bayesian software packages (e.g. proc MCMC, Stan, Jags, Nimble)
• To execute simulations to understand implementations and configurations based on Bayesian applications with a wide range of complexity
• To provide recommendations and a concise overview of Bayesian software packages

To participate in the Biogen Internship Program, students must meet the following eligibility criteria:

• Legal authorization to work in the U.S.
• Grade point average of 3.2 or higher preferred
• At least 18 years of age prior to the scheduled start date
• Be currently enrolled in an accredited college or university

Education

Enrolled in a PhD program

All your information will be kept confidential according to EEO guidelines.