"It is important to care for the details in statistics": Hans Rudolf Künsch looks back on his IMS Presidency


  • Author: Statistics Views
  • Date: 01 Nov 2013
  • Copyright: Image appears courtesy of Seminar für Statistik, ETH Zurich, Switzerland

Hans Rudolf Künsch is Professor of Mathematics at ETH Zürich. He is the Past President of the Institute of Mathematical Statistics, having recently handed over the reigns to Professor Bin Yu. His main research covers areas from probability theory, theoretical statistics with bootstrap methods to applications in environmental models.

Künsch worked as a research student at the University of Tokyo with a scholarship grant from the Japanese government. After completing his PhD at ETH Zürich, with a dissertation project on 'Reellwertige Zufallsfelder auf einem Gitter: Interpolationsprobleme, Variationsprinzip und statistische Analyse' ('Real-valued random fields on a lattice: Interpolationsprobleme, variational principle and statistical analysis'), he returned to research work in Japan, at the University of Tokyo and the Institute of Statistical Mathematics.

StatisticsViews talked to Professor Künsch during the Joint Statistical Meetings this August before he gave the IMS Presidential Address, which was published here in the IMS Bulletin in September.

thumbnail image:

Video interview

Further questions

1. You also were a researcher and postdoc in Japan from 1976-1977 and 1982-1983. What led you to Japan in the first place?

Curiosity! When I went the first time, I was not sure whether I wanted to do a PhD or take up teaching or join a company. I also wanted to see more of the world and at that time, it was very difficult to spend a semester or two of your studies at another university. Nowadays, of course it is much easier. Japan sounded fascinating. I did not know much about the country but it was a great experience.

2. Your lecture here at JSM 2013 focusses on the 300th anniversary of the publication of Ars Conjectandi. Despite significant advances in the field, it is still celebrated as a seminal founding work in probability and stochastic studies. What are the main points that you wish to bring across?

The book, in a way, has a result which we consider now to be really trivial. However, it was the first work which led the basis for applying probability outside the world of pure games of chance. In games of chance, you can find out probabilities just by symmetry arguments and Bernoulli showed, without symmetry assumptions, you can learn from experience. It’s the old idea of inductive thinking which is the point that is still valid today. Questions like what does probability mean, where do we get the probabilities we need to start our computations – I concentrate on this difficulty of inductive versus deductive inference for the theme of my lecture.

3. What has been the most exciting development that you have worked on in statistics during your career?

I have found it very interesting to work on the bootstrap method. I like it when you hear ideas for the first time and think it’s crazy, surely that cannot work: You do not have enough data so you create data. Then the fog clears and I was able to make a contribution as to how you can adapt bootstrap if you have dependence in the form of stationary time series or random fields.

The other interesting work which I took part in was sequential Monte Carlo methods where you do not try to simulate from one given distribution, but your target is a sequence of distributions and you try to adapt your sample as this target changes.

4. What do you think the most important recent developments in the field have been? What do you think will be the most exciting and productive areas of research in statistics during the next few years?

One interesting development is the connection with biology. From my point of view, I am interested in environmental models,where there is this connection with partial-differential equations and the problem is how can you incorporate uncertainty into it.

From a more theoretical point of view, the exciting research area for me are the questions being asked in terms of how can you face the curse of dimensionality, the assumptions you need to make, like sparsity. I find these ideas very exciting as they play a role in the applications I have mentioned.

5. What do you see as the greatest challenges facing the profession of statistics in the coming years?

Big Data has been around under different names. People have called it before ‘massive data sets’. In my area in environmental models, Big Data was already present in the 1980s as satellite measurements, but what has changed are the traces we have from ICT – Facebook, Google etc. Big Data is a challenge but I think the challenge is to use good theory in dealing with this data. It’s not enough just to have data; you need some ideas or concept as to how to handle the data.

6. Are there people or events that have been influential in your career?

Peter Huber, my first teacher and I owe a lot to my PhD supervisors, Hans Föllmer and Frank Hampel. I have met many people who I have admire. For instance, Don and Stu Geman for their work on image analysis, or David Donoho whose work I have followed as I am interested in robust statistics which is where he started before moving onto wavelets and other areas. He has done great work and he richly deserved the Shaw Prize.

Related Topics

Related Publications

Related Content

Site Footer


This website is provided by John Wiley & Sons Limited, The Atrium, Southern Gate, Chichester, West Sussex PO19 8SQ (Company No: 00641132, VAT No: 376766987)

Published features on StatisticsViews.com are checked for statistical accuracy by a panel from the European Network for Business and Industrial Statistics (ENBIS)   to whom Wiley and StatisticsViews.com express their gratitude. This panel are: Ron Kenett, David Steinberg, Shirley Coleman, Irena Ograjenšek, Fabrizio Ruggeri, Rainer Göb, Philippe Castagliola, Xavier Tort-Martorell, Bart De Ketelaere, Antonio Pievatolo, Martina Vandebroek, Lance Mitchell, Gilbert Saporta, Helmut Waldl and Stelios Psarakis.