Brian P. Hobbs

PhD Candidate

Division of Biostatistics



Brian Hobbs is a PhD student in the Division of Biostatistics and advisee of Dr. Bradley Carlin. His research involves adaptive Bayesian clinical trial designs which have the potential to save time and expense as well as minimize the number of subjects exposed to an inferior treatment by incorporating prior information using historical data from previous investigations or from published literature to update the likelihood or as non-randomized historical control groups. His work is featured prominently in sections 6.2 and 6.3 of the third edition of textbook Bayesian Methods for Data Analysis by Dr. Bradley Carlin & Dr. Thomas Louis. His first publication “Practical Bayesian design and analysis for drug and device clinical trials," J. Biopharmaceutical Statistics, 18, 54-80, 2008 demonstrates Bayesian analysis and sample size calculations in two applied settings where incorporation of available historical information is crucial, one concerning an AIDS drug trial and a comparison of left ventricular assist devices (LVADs). During the summer of 2007 Brian worked for Takeda Global Research & Development as an intern statistician. He also worked as an intern under Dr. Daniel Sargent in the Cancer Center Statistics department at the Mayo Clinic, Rochester, MN during the summer of 2006. Brian also has three years of experience as a research assistant under Dr. Jim Neaton working with the statistical team for large (N>6000) international, randomized, multi-center trials comparing strategies for the management of antiretroviral therapy in HIV-infected patients (Community Programs for Clinical Research on AIDS). (Brian's C.V. in .pdf format)

Brian recently presented research “Power Priors for Adaptive Incorporation of Historical Information in Clinical Trials,” at the 2009 Bayesian Biostatistics Conference, in Houston, TX with Dr. Carlin.

Link to "Draft FDA Guidance on the Use of Bayesian Statistics for Medical Devices Trials", released for public comment in May 2006.

T.A.:

Publications:

  1. Hobbs, B.P. and Carlin, B.P., "Practical Bayesian design and analysis for drug and device clinical trials," J. Biopharmaceutical Statistics , 18, 54-80, 2008. software , slides

Projects in Statistics and Biostatistics:


Misc:

Astronomy Picture of the Day from NASA
R software
College football polls
Twin Cities events
Northrop events
Ted Mann Concert Hall events schedule

How can it be that mathematics, being after all a product of human thought which is independent of experience, is so admirably appropriate to the objects of reality? Is human reason, then, without experience, merely by taking thought, able to fathom the properties of real things.
- Albert Einstein

David Benjamin Hobbs: Oct. 11th, 1987 - Nov. 25th, 2007

A slideshow for David by Brian
You Never Know
David Hobbs Music Foundation

Brian Paul Hobbs
PhD Candidate
Division of Biostatistics
University of Minnesota
Contact me at: brianho@biostat.umn.edu