How a Stats Legend Got His Start | Stats + Stories Episode 105 / by Stats Stories


Yoav Benjamini is the Nathan and Lily Silver Professor of Applied Statistics at the Department of statistics and Operations Research at Tel Aviv University. He is a co-developer of the widely used and cited False Discovery Rate concept and methodology. He received the Israel Prize for research in Statistics and Economics, is a member of the Israel Academy of Sciences and Humanities, and has been elected to receive the Karl Pearson Prize of ISI this summer.

+ Full Transcript

John Bailer: How do you become a statistician? You start out thinking you're going to study one thing, and then you end up studying something else. Today, we're going to talk on our Stats and Short Stories episode with Yoav Benjamini. The Karl Pearson prize-winner this year for his work on false discovery rates and other outstanding contributions. I'm John Bailer, I’m Chair of the Department of Statistics at Miami University and I'm one of the panelists on the Stats and Stories podcast. I'm joined by other panelists Rosemary Pennington and Richard Campbell from the Departments of Media, Journalism, and Film. We also have, joining us remotely, Yoav Benjamini. The Nathan & Lily Silver Professor of Applied Statistics at Tel Aviv University. He was going to be an Urban Planner and do operations research, but then he saw the light. He became engaged and called to a career in statistics. So Yoav thank you for joining us and can tell us a little bit about what led you to this career in statistics?

Yoav Benjamini: Well, urban planning was already the middle of my travel to statistics, because I started with physics and mathematics. So I was contemplating to maybe instead, do architecture. So I finished my B.A. with physics and mathematics and then came an outside event and this was the 73-year war in Israel. I was enlisted as a reserve for more than half a year into the army. I lost half a year and then mathematics opened a specialty semester for the people who were enlisted. I said okay, I'll do a bachelor in mathematics and continue the contemplation later on. I finished my master's in game-theory with Professor Allman, spending two years proving uniqueness in the existence of some solution, and after this, I decided that's not what I'm going to do in the future. So I come back about my original idea of going back to architecture but now it was mathematics now beyond operation research with urban planning is one of the things. Where do you study such a thing? Well, maybe there are three universities. I heard that Princeton is very flexible with their statistical department. Both me and my wife wanted a degree we went to Princeton. And then at Princeton, I took courses in Urban Planning and so on, and then took a course from John Tukey. I knew Tukey from my math education. There is a Tukey's dilemma, which is equivalent to the dilemma of choice, a very fundamental result. In the first class, John stands at the board and started to talk about results from papers, and says, "Well you know how to judge what the distribution of the numbers is?" And we said no, and he said stem and leaf and then said “you don't know stem and leaf?”, and we start to get numbers from us and throw them on the board. And stem and leaf and then he does and I realize that this great mathematician finds interest in making plots on the board. And he finds it very important. He was talking about exploratory analysis and so on and that caught me. My interest- I was also working with meteorological data and that really captured me and changed my career into becoming a statistician and began very interested in applied statistics. Interestingly, I didn't work with John Tukey on my thesis. I worked with Richard Bloomfield, and it wasn't on multiple compression at all. But I did study from him – it was a special privilege to be a student of John Tukey. He'd written my thesis which was on the t-test and its conservativeness, but really taking this- actually three courses from him, was really a special experience and really brings you into statistics. It captures you into statistics.

Richard Campbell: So, one of the things I've learned from doing this podcast is that one common thread that ties journalists and statisticians together is that we tend to be more generalists. We're expected to know a lot about a lot of different things, and you certainly are an example of that. Do you have an area of research that's particularly interesting to you right now as you pick and choose? You talk a lot about your work and the use of your work in astronomy and drug research and genomes, is there an area that's most interesting to you now?

Benjamini: Well for the last 20 years I had a very close collaboration with a zoologist at Tel Aviv University and we were exploring exploratory behavior by rats and mice and so on. It started when he came for consulting, arguing that the rats can count to eight, and asked us, statisticians, to prove it. That brought me into deep looking into what he was doing. And it was wonderful. It is an example for those of you who know it's a wonderful example of uniform distribution with upper bound which has to be estimated, something we teach and never have a good example of. This work has brought us to publish major papers. I think our joint papers are one of the most cited papers in animal phenotyping. I've given talks in that area, and even have patents in this area. I unveiled a very deep structure in exploratory behavior starting at the home base and going out and returning and resynthesize, everything is done computational is measurable and now these things were taking it to a new place. Similar experiments with babies, human babies at the age of crawling and we see the same type of behavior in normal babies, and we don't see it in babies which have a problem of developmental problems, such as autism and others. This whole area of research that's been going on for 25 years. I think one-third of my publications are in this area. So much joyful work in such an applied area. And bringing out statistical methodologies, and the methodologies from there.

Bailer: Well, that's outstanding. You've had such tremendous impact. It's been great. Well, I'm afraid that's all the time we have for this episode of Stats and Short Stories. Yoav, thanks for being here.

Benjamini: You are most welcome. It's been a pleasure to talk with you.

Bailer: It's been a true honor and pleasure for us. Stats and Stories is a partnership between Miami University's departments of Statistics, and Media, Journalism and Film, and the American Statistical Association. You can follow us on Twitter or Apple podcast or other places you find podcasts. If you'd like to share your thoughts on our program send your email to or check us out at Be sure and listen for future episodes of Stats and Stories where we explore the statistics behind the stories and the stories behind the statistics.