Dorry Segev earned his MHS in biostatistics in 2008-09, concurrently with his PhD in Clinical Investigation from the Johns Hopkins Bloomberg School of Public Health. He is currently the Marjory K. and Thomas Pozefsky Professor of Surgery and Epidemiology, and Associate Vice Chair in the Department of Surgery at Johns Hopkins University.
Describe your current position and responsibilities in a way that will inform prospective students about career opportunities in biostatistics.
I'm a clinically active transplant surgeon but I also run a big research group looking at outcomes, disparities and allocation policy in solid organ transplantation.
How did Johns Hopkins Biostatistics prepare you for your career? What aspects of the program did you find most useful?
While I don't desire to develop new methods in biostatistics, I do desire to apply the most sophisticated methods that currently exist to my research. I have found that a fundamental knowledge of first principles, and how regression comes from these principles, helps me better understand the assumptions that statistical models make, how these might be violated in the work to which I apply the models, and what alternate approaches exist to account for, or explore, these violations. I deal with informative censoring, competing risks, multilevel models, and longitudinal data on a regular basis. Inferences in medical research are often misled by inappropriate modeling choices; I have published a number of papers now (in journals like JAMA) showing how this can occur and answering the questions correctly.
Can you describe your day-to-day life as a graduate?
My day-to-day is probably not the same as most graduates, since I'm also a clinician. I operate two days a week, but I do spend the rest of the week (4 days a week) doing research. I still analyze data even though I'm the "guy who runs the research group" -- hardly a day goes by that I don't open a statistical software package to do something. We have weekly research seminars where I (and some of the other experienced folks in my group) teach the grad students and more junior folks, where we explore statistical approaches to various challenging problems, and where we discuss ongoing research.
What is your favorite memory of your time at Johns Hopkins Biostatistics?
Learning that Hopkins Biostatistics had a creative side and a sense of humor -- through the Biostats Poetry -- was my favorite discovery. I mean, it's one thing to fit fancy regression models. But how many departments can sing about it!
Is there any other information about your experience at Hopkins that would be useful for recruiting prospective students and/or helping current students? This can include your experience in Baltimore.
Baltimore is actually a great city. I've been living here for 20 years. There are nice, safe, friendly neighborhoods in the city where you can walk to restaurants and stores. Lots of quirky people if you want to find them -- like D.C.'s younger sibling but without the "attitude" of D.C. Just 15 minutes from town are some of the most beautiful state parks for jogging, cycling, hiking, etc. Half an hour on the train and you're in D.C., 2 hours and you're in NYC. Can't beat that.
What has been your most satisfying job experience using your biostatistics background?
Showing my field how we've been led by inappropriate statistical models, and informing practice with good ones.
What reasons might you give to encourage a prospective student to get a master’s Biostatistics degree at Hopkins?
Biostatistics requires good statistics but also requires a good bio side. I'd bet that most programs have pretty decent statistics, but pretty lame bio. JHSPH is across the street from the top hospital in the world, with some unbelievably smart clinicians who want to work with biostatisticians -- who want to understand the real way to analyze data, who have interesting data that needs analysis, who are answering some of the most important questions in their field, and who want to collaborate. There's no better bio side anywhere else in the world. You combine that with some of the most successful biostats faculty anywhere, and there's no better place to learn or work.