How to Fall in Love (with Statistics)
Vera Schölmerich is an assistant professor in behavioral sciences and public health at Erasmus University Rotterdam. She is the instructor for a new free online course Deception Detox - how solid science can help you save the world.
High schools and universities aren't successfully getting students to understand and fall in love with research methods and statistics. In this post I argue why this is deeply worrisome, and suggest how to could fix this problem.
I managed to get through high school in the US and Germany with good grades but a low understanding of basic statistics and applied mathematics. I also found them a complete waste of time. I didn't think that statistics, and social science in general could actually contribute to tackling any real-life problems. Unfortunately, this didn't change during my 4 years at University. And even more unfortunate is my impression that I am not an exception but rather the norm.
I now teach research methods and statistics to students from all over the world at the Erasmus University Rotterdam in the Netherlands. Fresh out of high school, my students either haven't had any training in statistics or research methods, or like me, they did, and find it boring, tedious and irrelevant. Their actual comprehension of these subjects is low, and I don't think that this changes much throughout their time at university. I hope that my own students are an exception - but I'll get to that later.
A basic grasp and appreciation of research methods and statistics is vital in order to be able to distinguish fact from fiction. We need these tools in order to filter through the countless claims that we are confronted with in the media, from our politicians and our friends. Take President-elect Donald Trump's tweet about autism:
To make up our mind about whether Trump's claim makes sense or not, we would need - at least on an intuitive level - an understanding of the difference between correlation and causation. In a nutshell: just because two things seem to move together - such as a rise in vaccinations and a rise in autism diagnoses - doesn't mean that one thing caused the other.
To critically evaluate the multiple claims we are faced with on a daily basis, we also need to understand concepts such as the importance of conducting randomized controlled trials, significant versus substantial effects and standard deviation. And yet I see students donating to dubious charities who use pre-post tests to claim that they have made a smashing impact. I see students drinking carrot juice and telling me that correlational studies proved that it was good for your health, not realizing that they should be cautious of drawing causational conclusions from such study designs. I see students listening to classical music while studying as they read that this would "significantly" improve their grades, not realizing the difference between significant and substantial.
While I find it frustrating to see students waste their time and money, I have a deeper concern here. Our current students will become our future doctors, lawyers and policy-makers. These are people who will have a profound impact on our everyday lives and the state of our world, and they are not equipped with the basic tools to separate fact from fiction.
The root of the problem is that high schools and university programs tend to teach research methodology and statistics in a boring, technical way - or not at all. Most students are scared of these courses and don't see how these skills could help them in real-life. Scientists have been more successful at studying this phenomenon of 'statistics anxiety', but the problem has yet to be resolved.
So what can be done? I have drawn inspiration from my own life to come up with a solution. During my PhD program I was confronted with a very concrete problem I felt passionate about: why were so many babies dying in poor neighborhoods in Dutch cities? After some initial resistance, I had to give in and recognize that I needed statistics to evaluate whether programs to save babies from dying actually work. And this is where I fell in love with statistics as a tool to have serious impact on this world.
My co-lecturer Dr. Kellie Liket and I have developed an online course that tries to get students to also fall in love by replicating the sequence I experienced during my PhD. We first explore global challenges - such as poverty or climate change - and then discuss key approaches of statistics and research methods as they naturally arise. We try to present the material in a non-technical, easily accessible way that shows why it is relevant. This is a very different approach to the usual courses on these subjects, which typically immediately dive into the boring and technical bits, such as memorizing what a p-value stands for.
As we think that a wide audience could benefit from such a new approach to teaching, we have made our course freely accessible online. It's called 'Deception Detox - how solid science can help you save the world'. See this 10-minute video below to get an idea of how it works: Big Fat Problem
By failing to convey basic literacy in research methods and statistics to our students, we are producing professionals unable to use rigorous science to solve real-life problems. This needs to change. In the words of astrophysicist Neil deGrasse Tyson: "Science literacy is a vaccine against the charlatans of the world that would exploit your ignorance."
Dr. Vera Schölmerich is an assistant professor in behavioral sciences and public health at Erasmus University Rotterdam.