Graduate Program: PhD in Biostatistics (2021)
Title & Institution: Thomas J. and Alice M. Tisch Assistant Professor of Biostatistics, Brown University
Location: Providence, RI
Arman Oganisian, PhD, is a 2021 graduate of the PhD in Biostatistics program, administered by the Graduate Group in Epidemiology and Biostatistics (GGEB) at the University of Pennsylvania. Before entering the doctoral program, Dr. Oganisian earned a BA in Quantitative Economics with a minor in Mathematics from Providence College in 2013, followed by an MS in Biostatistics from the University of Pennsylvania in 2018. As a PhD student, he was co-advised by Jason Roy, PhD, and Nandita Mitra, PhD, both faculty members in the Department of Biostatistics, Epidemiology and Informatics.
Today, Dr. Oganisian is the Thomas J. and Alice M. Tisch Assistant Professor of Biostatistics at Brown University.
We reached out to Dr. Oganisian to learn more about his current work and to invite him to reflect on his time as a PhD student in the Graduate Group in Epidemiology and Biostatistics (GGEB) at the University of Pennsylvania.
What is a typical day like in your current role as a faculty member at Brown University?
A typical day includes some meetings with research collaborators – mostly in the departments of epidemiology and health services – and students. I carve out long blocks of time for my own research and make time for an afternoon coffee run with colleagues here and there.
What do you value most about your current role?
In terms of personality, I’m very entrepreneurial. It turns out that, so far, my role rewards this trait. I often feel like I’m running a start-up – whether I’m trying to secure funding, building out and directing my research program, working with colleagues, or marketing the progress at academic conferences.
Why did you choose the Graduate Group in Epidemiology & Biostatistics program?
A really good visit/interview day swayed me. The faculty – whose research was inspiring in its own right – spent more time highlighting the work of their students. This left the impression that Penn was a place I could grow and do meaningful research with dedicated people. During the visit I had a particularly impactful conversation in which Jason Roy sold me on the causal inference reading group at Penn. I was curious about causal inference at the time so having this group was important to me. Finally, spending time with then-students Ali Valcarcel and Eric Oh after interviews at the now-defunct City Tap was influential. It made Penn feel like a place I could make kind, fun, and intellectually curious friends.
What was the most meaningful part of your experience in the program?
The causal inference reading group I mentioned earlier became what is now the Center for Causal Inference during my first year. At the time, it was still small enough to have weekly reading group meetings in a conference room. Attending and presenting at those meetings was an incredible source of growth as it gave me the opportunity to learn from accomplished researchers throughout my five years.
What faculty member, mentor, or course was most influential for you and why?
Nandita Mitra and Jason Roy shaped those years for me in a positive way and helped me develop skills that will pay dividends for the rest of my career. They helped me become an independent researcher by striking the perfect balance of being supportive while not being coddling. Towards the end of my doctoral training, Jason introduced me to researchers at the Children’s Hospital of Philadelphia (CHOP) who were working on some sequential treatment problems in pediatric cancer. This exposed me to a set of interesting statistical methods and partially motivated my decision to pursue an academic career to work on some open problems in this area.
In terms of courses: my favorite courses were Jinbo Chen’s statistical inference course and James Johndrow’s (Wharton) seminar in nonparametric and high-dimensional Bayes. I still have my notes from these classes.
What advice would you offer a current or aspiring student?
Advice 1: A roughly greedy search algorithm leads to pretty good career solutions – make sure you’re doing what excites you at every step and a rewarding career may emerge simply as a side-effect.
Advice 2: Follow Advice 1 subject to the constraint that you don’t immediately stop working on a problem when it no longer excites you. Every problem is exciting initially when we’re picking low-hanging fruit and feeling super smart. Have the grit and discipline to keep going even after the low-hanging fruit has been picked and you stop feeling smart.
Advice 3: Follow Advice 2 subject to the constraint that there is merit in recognizing a dead-end and not committing the sunk cost fallacy.
Advice 4: Don’t just take one person’s advice (mine could just be survivor bias) – take a weighted average of the advice from several people you trust.
What is on the horizon for you in terms of your career goals or research path?
I had a grant funded last year to work on developing Bayesian machine learning methods for estimating causal effects when we have missing covariate information. This is an important part of my program, which focuses broadly on Bayesian causal inference with incomplete information, so I plan to keep at it. We’ll see what problems catch my interest in the meantime!