A few months ago, I was invited by the Malaysian Medical Association (MMA) to join a panel discussion on future careers for young people.
I commend the MMA for organising an event that also explored careers beyond medicine and pharmacy. I always enjoy speaking with and teaching young people, but there is only so much one can cover in a panel discussion.
So, I am writing this to further share a skill set that I believe will be especially valuable for the younger generation.
Early statistics owed much to developments in the medical and biosciences, both in theory and in the way information was organised and presented. A few hundred years ago, if you were an observant follower of the emerging natural sciences or perhaps one of those barber-surgeons (!), you may gradually have noticed that the outcomes of certain procedures carried probabilities rather than certainties. Over time, repeated observation could lead you to conclude that increasing the number of leeches applied to a patient did not necessarily improve treatment outcomes.
This gradual shift from anecdotal certainty towards patterns, frequencies, and expected outcomes laid part of the intellectual foundation for statistical thinking. Medicine, or in earlier times, public health, perhaps more than many other disciplines, forced practitioners to confront uncertainty directly.
John Graunt was born in London in 1620, during a period when plague outbreaks were a recurring feature of urban life. To monitor mortality during these outbreaks, the City of London began intermittently recording burials as early as 1527. By 1570, the so-called “Bills of Mortality” had expanded to include baptisms; by 1629, causes of death were recorded, and later, age at death was added.
Graunt applied his mathematical ability to analyse the Bills of Mortality systematically. In his 1662 publication, he compiled and interpreted data from these records, producing one of the earliest examples of descriptive statistics. Today, Graunt is regarded as the founder of demography and perhaps the first epidemiologist.
If you are a public health professional or an economist, the population statistics you download today from the Department of Statistics Malaysia, such as birth rates, mortality rates, and population estimates, owe much to the intellectual foundations laid by Graunt’s work.
Unlike Graunt, James Lind, born in 1716, did receive formal medical training through a physician apprenticeship in Scotland. Lind conducted a 1747 scurvy experiment on board a ship, showing sailors consuming citrus fruits recovered better than those receiving other treatments, thus conducting one of the first clinical experiments.
Lind would not have used statistics in the modern mathematical sense, but his reasoning reflected an early form of statistical and experimental thinking. Rather than relying purely on anecdote or medical theory, Lind compared outcomes across groups.
Some sailors received cider, others vinegar, herbs, seawater, or medicinal pastes, while one group received citrus fruits. By observing that the sailors consuming oranges and lemons recovered much faster, Lind inferred that the treatment itself, rather than chance or individual constitution, was responsible for the improvement.
Today, the same underlying logic forms the basis of clinical trials, drug approvals, and the evaluation of treatment efficacy.
While Lind demonstrated how data and comparison could be used to identify effective treatments, later pioneers showed that statistics could also be a powerful tool for communication and public advocacy.
The next name is likely familiar to many: Florence Nightingale. Beyond nursing, she was also a pioneering statistician and expert in data storytelling. Her most famous contribution, the “rose diagram”, visually communicated statistical data in a powerful and accessible way.
During the Crimean War, she carefully recorded soldiers’ causes of death and used statistical analysis to show that poor sanitation and preventable diseases, not battle injuries, were the leading causes of death.
By presenting statistics in a more intuitive and accessible way, Florence Nightingale used her findings to advocate for public health reforms. Today, data storytelling remains an essential part of statistics, especially in education and advocacy. Conducting analysis is only half the task – the other half is communicating insights effectively to influence decision-makers and the communities directly affected by the data.
The contributions of Graunt, Lind, and Florence Nightingale are just a few examples of how medical science advanced through statistics. Their contributions were made possible by the growing availability of data collected in increasingly systematic ways.
Today, data is everywhere, and many tasks and decisions are improved by access to it. That is why basic understanding of data is important. You may be able to become a competent doctor, economist, or a tennis player without data analysis, but your understanding and decision-making can be greatly enhanced by the ability to think and analyse statistically.
Developing the ability to understand the underlying factors behind phenomena, trends, and human behaviour is especially important in fields where your decisions and recommendations carry influence. More importantly, in the world we live in today, and likely even more so in the future, your ability to understand data and statistics is an important skill for evaluating information critically and filtering out misleading or dubious claims.
As an economist, just this week I analysed demographic data showing the dynamics of population ageing in Malaysia, and another dataset comparing mortality rates between urban and rural districts in a particular state. I could easily have asked AI to retrieve the answers, but working through the data in a spreadsheet helps build intuition as you begin to see how the pieces connect and what drives the outcomes.
This is how I believe statistics should be learned, especially during the early stages of discovery. Once you understand the underlying theories, you can make far better use of AI and modelling tools. As educated individuals, your goal is not simply to get faster Google results, but to use technology to extend and deepen our existing capabilities.
Eventually, if you work at organisations such as the National Institutes of Health, or lead efforts addressing issues such as an ageing society or young people entering gig work, you will need a deep understanding of how data reflects the way people actually live.
As Malaysians, we are part of the communities behind the statistics, and that lived understanding is something no computer can fully understand.
So, go learn some statistics – a whole new world will open up to you, and it can take you further than you imagine.
The views expressed here are the personal opinion of the writer and do not represent that of Twentytwo13.