Bayesian statistics, a fascinating story
By Phuong Tran, Queensland University of Technology
In the third year of my mathematics degree, our lecturer introduced the class to an area of statistics called Bayesian statistics. Up until that point, I had a little idea about this branch of statistics as we were mostly taught about classical statistics throughout our undergraduate degree.
I was quickly drawn to the topic as our lecturer went on explaining some of the cool applications of Bayesian statistics. I learnt that in the Second World War, Bayesian statistics was used to break the enigma code and find German U-boats; in the Cold War, Bayesian statistics helped find a missing H-bomb and the U.S. and Soviet submarines; Bayesian methods were also applied to find a missing Air France plane in 2011.
At its heart, Bayesian statistics is about how to use new information to update our initial belief about something to get an improved belief. To me, this makes intuitive sense as in our own lives, we all learn from experience. From time to time, our opinions about people or events are either confirmed or adjusted whenever we have new information.
I did some further reading after that lecture and was amazed as the list of impressive applications of Bayesian statistics kept growing. Many of those applications intertwined with several significant historical events. On top of that, Bayesian statistics tells a fascinating story in its own history. It was discovered, dead, buried and rediscovered at various time points since the 18th century. Today, Bayesian statistical methods are widely used and highly praised by many practitioners.
I was obviously very attracted to the field of Bayesian statistics so I could not have been more excited when I received the opportunity to do a summer research in this area. My research looked at two application software packages that apply Bayesian statistical methods into analyzing data. With the help of my supervisor, Dr Christopher Drovandi, I looked at the algorithms underlying these tools and compared their performances in different situations. This research has brought me a step closer to what I really want to do, which is making great research ideas more easily accessible to the wider audience in the real world.
Not only did I learn so much more about an area I’m interested in, I gained so much joy through my summer research and became more aspiring to pursue further in this awesome area called Bayesian statistics!
McGrayne, S.B. 2011, The theory that would not die: how Bayes’ rule cracked the enigma code, hunted down Russian submarines, & emerged triumphant from two centuries of controversy, Yale University Press, New Haven [Conn.].
Phuong Tran was one of the recipients of a 2016/17 AMSI Vacation Research Scholarship.