Working at the interface of statistics with applied and computational mathematics

Tagged: Statistics

Building Links in Mongolia

  , , , , , , , ,

📥  Statistical Applied Mathematics

In late November 2016, 10 keen students and academics made the long journey to Ulaanbaatar, the capital of Mongolia, for a research trip aiming to build links between Mongolia and the University of Bath.

Upon arriving in temperatures reaching -30 degrees Celsius, a few wondered what they had let themselves in for. Even Andreas Kyprianou, who knew Mongolia well, had never visited before in winter and was a tad apprehensive.


Left: the long journey from Bath to Ulaanbaatar, involving a stop off in Beijing. Right: arriving at Chinggis Khaan airport in Mongolia.

The aim of the trip was to help develop the Mongolian industrial mathematics and statistics capability. It was hoped this would help the country form evidence-based policies that will drive economic, industrial and environmental development. A team from the University of Bath was hence formed of individuals that could help build collaborative links between policy makers in Mongolia to generate high impact research activity, and deliver a course in statistics to provide training for young academics and workers. This included representatives from SAMBa, the Statistics group, IMI, IPR, and four postgraduate students.

The course was primarily run by the postgraduate students and had a large amount of interest with hundreds of applications. A suitable venue was identified which allowed for 130 participants from Mongolia to attend. The material began with motivational examples of the use of statistical analysis such as the use of clustering methods on electricity usage data to better predict electricity demand. The participants were introduced to statistical software R, and shown how to use it for initial data analysis and data visualisation. The course moved onto methods for hypothesis testing including how to pick the right test for different types of data. It concluded with methods for linear regression and clustering. Many of the participants had their own data from academic or public sector projects, and a lot of queries related to importing and analysing this data.

On the first day of the course, a TV crew recorded a report for the state TV channel MNB. A 3-minute long segment involving interviews was broadcast on the news on 22nd November 2016. At the time of writing, the report is available to view on the MNB website (22:00 mins).

Given the language barrier, it was found necessary to speak relatively slowly, and pause for a translation after every phrase. This was useful in developing the skill to speak in a concise articulate way, and to avoid using serpentine sentence construction (which I for one was previously guilty of when giving talks!).

Logistical challenges arose including intermittent WIFI access due to the large amount of people in the course. This was countered by the downloading of relevant materials including R software and packages onto many memory sticks for circulation.

Delivering the course was an enjoyable and extremely beneficial experience for us. The participants of the course were extremely friendly and it was genuinely a joy to work with them.


Top left: Poster advertising the statistics course. Top right: Robbie Peck assisting a course participant with the installation of the relevant statistical software. Bottom: Aoibheann Brady, Matt Thomas, Robbie Peck, and Adwaye Rambojun preparing and delivering the statistics course.

The other half of the University of Bath team took the lead in meeting policy makers to build future potential collaboration links. This included representatives from the National University of Mongolia, and the Ministries of Health, Energy, National Strategy. This proved fruitful with many different leads for collaboration with academic and public sector projects.

One potential collaboration involved looking at air pollution and tuberculosis records within Mongolia. The burning of untreated coal to fuel the large heating cost in Ulaanbaatar meant that the PM10 concentration in the city was relatively high. A possible direction would be to fit a model to pollution levels across space and time to ‘fill in the gaps’ where there are not records. One could then cross reference this with the tuberculosis records to measure any association between air pollution levels and tuberculosis diagnoses. It is hoped research such as this will have weight in influencing public policy through the links established with the public-sector workers we met.

Furthermore, Professor Gavin Shaddick ran a workshop in air pollution which began with talks from academics from Bath and Mongolia. This then followed the style of a SAMBa Integrative Think Tank by having cross discipline group discussions to identify problems and research questions, and then short presentations about directions one would take to tackle them. For each problem, a contact in Mongolia was identified to be the catalyst for future work in that area.


Top left: Meeting at the Public Health Institute. Top right: Julie Barnett in a discussion during a workshop on Epidemiology and Public Health. Bottom left: Andreas Kyprianou working through some ideas during a workshop on Ecology. Bottom right: Meeting at the Economics Research Institute.

Once the week had finished, we celebrated all the new potential future collaborations with a Mongolian feast. The food was particularly delicious, involving large amounts of tender meat and traditional Mongolian salads and sides. To our new Mongolian friends, we said “Баярлалаа!”, and hope to return to Mongolia in 2017 to ensure the successful development of the ongoing collaborations and to perform further training courses.


My first conferences: A SAMBa story

  , , , , , ,

📥  Statistical Applied Mathematics

My first year at SAMBa has been quite an eventful one. I can definitely say that SAMBa has delivered on its promise to help me explore different areas of Mathematics. However, this post is not about maths at all (who are we kidding, it probably is), it rather concerns my experience of conference attendance. My very first one was a workshop on big models at the University of Warwick, which incidentally happens to be my undergraduate institution. The reason I went there was to see what the Institute of Data science was up to, and as expected, they were doing things that I was interested in. Statistics, applied mathematics, data science and machine learning.


Swisstech Convention Centre, Lausanne (courtesy of STCC)

My second conference was perhaps the most daunting one. In my quest to know more about uncertainty quantification (UQ), I took up a module with the local expert on it, Prof. Rob Scheichl. This led to the SIAM conference on uncertainty quantification in Lausanne. The venue was breathtaking, to say the least. It was in the Swisstech convention centre at the EPFL. I have never seen an auditorium with that much leg room during the plenary talks. To fund myself, I along with a fellow SAMBAlite, Gianluca, successfully applied for funding from MI-Net. Part of the deal of going there was to further inter university collaboration, and hence the day preceding the conference involved some informal chat with Fabio Nobile's research group. We exchanged ideas and research interests. The rest of the week involved us going to different sessions. They were quite daunting to be honest as most of the speakers were very, very good at what they did. This only increased my desire to actually start a research project and further my knowledge in a specialist area. The thing that I believe was most beneficial for me was to see the use of machine learning in UQ. This contributed to my decision to take up machine learning as my current research project as I could see that UQ would still be an option if I diverted away from it for a bit. I have to say though, my bilinguality helped a lot during the trip. I speak both French and English fluently, coming from a bilingual society (well, we're actually multilingual as most of us speak a third oriental language plus our local dialect, creole. Mauritius FTW right?).


Me, Gianluca and another SAMBa student Matt outside the conference in Lausanne

I went to my next conference after I had chosen my project (which is on automatic damage assessment in x-rays of Psoriatic Arthritis patients). It was a summer school on Gaussian Processes organised by the Machine Learning group at the University of Sheffield. It was the first year where they added the words "and uncertainty quantification" to it. I expected it to be full of computer scientists. To my surprise, the attendees were extremely diverse. There was an analytics team from formula 1; a guy working with Siemens (I think it was Siemens) on wind turbines; and wait for UQ lecturer from Warwick, Tim Sullivan (who is one of the most rigorous applied mathematicians I know) and my final year project supervisor, Mark Girolami. Uncertainty Quantification can mean many things! The summer school had practical sessions and talks from people who are very good at working with Gaussian Processes. One thing I got from the whole thing was that Gaussian Processes are used everywhere, from trying to optimise functions you cannot evaluate, to trying to fix the posteriors you get in Bayesian Inverse Problems. Is there a better alternative? Maybe. The search continues....


Antarctica as modelled using Markov Chain Monte Carlo, a key tool in Uncertainty Quantification (courtesy of the National Science Foundation)

The next conference I went to was very different from my two previous ones. It was actually one on Psoriatic Arthritis (PsA). No maths, just medical researchers and practitioners talking about, well, PsA. I did not get most of what was happening as they were talking about genes and things. They also mentioned "statistics" a lot of times. That was scary. I mean, really scary. When I asked them what kind of tests they were doing the answer was often "I don't know, I just press on a button in stata". It thus seemed to me that medical doctors in general need a better grasp of data science. Hence I tried to get some statistics training into their realm by suggesting we do a little session with consultants undergoing training. This was well received and it is hoped we can do it in the future during one of their training days.

You might be asking yourselves, how did you, a self proclaimed applied mathematician (please don't hate me, I know I did stats as a major) go to a medical workshop? Long story short: I was invited to a meeting in Bath on medical imaging, as I had now started working on this. There I met Prof. Neil McHugh, who works in pharmacology at the University of Bath. I mentioned my desire to know more about the PsA and he suggested I go there.

My English teacher always told me to put a concluding comment in my essays, and this is kind of an essay. The food at non-maths meetings, like the medical imaging one and the PsA one is way better. I had three course warm meals in both of them as opposed to the usual dried out sandwiches that repeat themselves n-times where n is the number of days the meetings stretch out for. Oh, and I'm writing this on a plane to Beijing where I transit before going to teach stats in Mongolia on SAMBa business. This one is for another time!


Bridging “the gap” in Mongolian Mathematics: a Q&A with Andreas Kyprianou

  , , , , ,

📥  Statistical Applied Mathematics

Mongolia is a country nestled between Russia and China, 6 and half times bigger than the UK but with a population 21 times smaller. It is the most sparsely populated country in the world (with 45% of the population living in the capital Ulaanbaatar). Mongolia has a rich history including the powerful rule of Genghis Khan, who created the Mongol Empire – the largest contiguous empire in history. But how much do you know about Mongolia in the present day? Have you been there? Do you know anyone who has? It seems somewhat a forgotten place, but recent activity from the University of Bath’s department of Mathematics aims to change that.

SAMBa co-director, Andreas Kyprianou has a long-standing relationship with Mongolia and now this is bearing fruit in terms of building a research base for the future. This relationship is growing even further and as that will have an impact on my job managing the SAMBa centre for doctoral training, and may even mean I get to visit Mongolia someday, I wanted to find out from Andreas how it all started and how he sees things developing in the future.


Andreas modelling various Mongolian outfits

Tell us a bit about yourself and your academic career.

I did my undergraduate studies in Oxford and moved to Sheffield for a PhD, graduating in 1996. After a brief stint as a temporary lecturer at the London School of Economics, I went to work for Shell as a Mathematician in their research laboratories in Rijswijk, The Netherlands. However, Shell was not for me so I left after about a year and a half, finding my way back to academia in late 1998.

After a short stint at the University of Edinburgh I was offered a five-year research fellowship back in the Netherlands, at Utrecht. A growing family brought me back to the UK in 2005 to Readerships at Heriot-Watt University, and then the University of Bath in 2006. I became a Professor in 2008.

Moving to Bath was a massive career boost. The probability group was in excellent shape and ready to grow. I enjoyed very much the aspirations of the Department and the University. We founded Prob-L@B (Probability Laboratory at Bath) in 2007, which has more than doubled in size in the last 10 years with a strong focus on doctoral and postdoctoral research infrastructure. This experience led me to taking up a role in bidding for the EPSRC funded CDT SAMBa. This was founded in 2014, and I now co-direct the centre.

When did you first travel to Mongolia? What made you decide to go?

I first went to Mongolia in 1998 after leaving Shell. Although things turned out well career wise, at that time it was unclear what lay beyond my resignation that summer. I recall handing in my security pass at Shell and going straight to the airport, from where I flew to China - not quite sure what would happen next! I travelled in China for a short while, but when I found that it was possible to catch a train to Ulaanbaatar from Beijing, nothing could stop me getting on that train. I still have memories of being a lone traveller on the night train to Ulaanbaatar and waking up at 6 a.m. to the wonder of seeing the Gobi Desert with wild camels running along the side of the track. At the same time, I was scared at what I would find in Ulaanbaatar. I knew nothing about this country and its people, beyond that it had undergone quite significant economic and social collapse since the fall of communism in 1990. However, from the minute I stepped off the train, I fell in love with Mongolia and I ended up staying quite a lot longer than expected.


The Beijing to UlaanBaator train (

How did your relationship with Mongolia develop over the years?

I have been married to a Mongolian for 16 years. I met her on the steps of the central post office in Ulaanbaatar the day before I left Mongolia that first time and now, many years later, we live happily with our three daughters in Bath. Because of this, Mongolia has become a big part of my life. Over the last 20 years, I have been back to Mongolia many times and have witnessed dramatic social and economic changes, both for my own extended family and also the Mongolian nation as a whole.

When did you first start working with the maths department at the National University of Mongolia (NUM)?

It was through my niece, who studied Mathematics and Economics at NUM. I visited her a few years ago, when she was in the middle of her masters’ studies, and she asked me to come and give some lectures and meet her teachers. It was then that I met several academics at the Department of Mathematics, including Tsogzolmaa Saizmaa (or Tsoogii). She described the plight of Mongolian mathematics to me. It was an impressive story and I learnt of the solid foundations of the mathematical community of Mongolia, supported by the old Soviet system, with good connections to Novosibirsk and Moscow. However, following the fall of communism, there was a “gap” in the continuum of expertise that now needs rebuilding. Having seen with my own eyes the difficulties that Mongolia has experienced, I quickly agreed to help Tsoogii and her colleagues to somehow put Mongolian mathematics back on the map.


Andreas with Tsoogii and his neice, Tungaa

So what did you do?

Together with a group of enthusiastic colleagues, both from Mongolia and other countries, I organised an enormous workshop on stochastic processes and applications. Although I met Tsoogii in 2012, it took until 2015 to get the necessary funding in place and to build the organisation necessary to hold such a large event. One of the central aims was to provide a panorama of modern topics in probability theory for the local audience. But the most beneficial and lasting outcome was the opportunity to create personal contacts between young Mongolians and the global community. We chose the theme of probability not just because both Tsoogii and I share an interest in this field of mathematics but also because NUM has a history of work in probability theory that dates back to the origins of the department in the 1940s. We raised nearly 60K Euros for the workshop and it was attended by around 120 individuals, the majority of which were students, from 20 countries.

Tsoogii is joining SAMBa on a Schlumberger Foundation fellowship in 2016, can you describe how that came about?

Tsoogii was a top student and, when graduating from her Masters some years ago, she was very keen to pursue a PhD in probability theory. This was at a time that Mongolia was going through significant economic difficulties and opportunities in Mongolia were few and far between. At this time, her husband was offered a scholarship to study for a PhD in Korea and she went with him. Unfortunately, she was not able to get a scholarship to do a PhD in Mathematics in Korea but, not wanting to waste her time there, she accepted a scholarship to do a PhD in computing science alongside her husband. When they returned to Mongolia, Tsoogii took up a position in the Department of Mathematics which she has held since 2010. However, her dream of pursuing research in probability theory remained. Hosting the SAMBa Centre for Doctoral Training meant that we could give Tsoogii the opportunity to pursue a PhD in this field here in Bath. However, funding students from outside of the EU to undertake a PhD is not easy. Luckily we discovered the Schlumberger Faculty for the Future fellowship scheme which supports women from developing countries to undertake a PhD abroad with the aim that they return to their home countries to build up research groups. This was an absolutely perfect fit for Tsoogii! Sure enough, from a competitive field of over 1000 applicants, she was one of 49 fellows awarded funding. This means that Tsoogii can now address both her personal ambitions; to get a PhD in probability theory and to ensure the continuation of probability theory in Mongolia. We are super excited about welcoming her to SAMBa in September and look forward to helping her to realise these goals.

What have you enjoyed about working with NUM?

Mongolia is a very remote country. Nonetheless, there is a generation of younger Mongolian mathematicians who are very aware of developments in the rest of the world and don’t want to miss out. It’s often easy to forget how privileged we are in the West, and the opportunities we take for granted so it is great to be able to share some of those opportunities with researchers at NUM. It’s wonderful to support young people who are prepared to work really hard to achieve their goals.

National University of Mongolia

The National University of Mongolia

How do you see Mongolian mathematics growing in the future?

Globalisation is generally accepted as a good thing for scientific research and Mongolia provides an ideal example of a country that could benefit significantly from increased connectivity, building on the opportunities afforded by the internet and social media. I believe that Mongolian mathematicians can form closer ties with their counterparts around the world, and take advantage of the many opportunities that exist in terms of doctoral and postdoctoral training. Tsoogii returning to Mongolia with a SAMBa PhD should have real impact in helping to deliver this.

There are many research opportunities in Mongolia that align with our research agenda in Bath and more widely in the UK. As with many countries and institutions, Mongolians are increasingly finding that they have an abundance of data which could be used to answer substantive questions, and inform policy decisions, across a number of fields. The foundation for interaction is now established and I am now working jointly with SAMBa and the Bath Institute for Mathematical Innovation (IMI) to initiate a number of collaborative projects.

The director of the IMI, Jonathan Dawes, has recently visited Mongolia and met researchers at NUM. Since his visit, Jonathan and I have worked closely with Gavin Shaddick (deputy director of IMI and co-director of SAMBa) to identify some very clearly defined projects in data science and statistics, focusing on air pollution, healthcare, agriculture and mining. These projects ensure there will be a building of Mongolian research capacity and will enable growing confidence in manipulating big data. They will provide a springboard to working collaboratively with Mongolian mathematicians and scientists, whilst developing a wider programme of future research and lasting collaboration. I hope that in the future we will see the delivery of real life impact on local communities from these interactions.

What are your favourite things about Mongolia?

The people, fermented horse milk, and eating dumplings in small little cafes; preferably all three combined.

Tell us something we probably don’t know about Mongolia.

Mongolia sent a man into space in 1981. Jügderdemidiin Gürragchaa spent a total of 7 days, 20 hours and 42 minutes in space on the Soviet Salyut 6 space station.