Design a site like this with
Get started

Where’s the Proof? Causation & Anecdotes

Where’s the Proof? Causation & Anecdotes

Sam Andrews has written an excellent overview of some of the biggest issues facing science communication. In particular, getting the public to understand that correlation does not always equal causation and that scientific evidence trumps anecdotes. 

#SoG+CuratorsChoice #science   #scienceeveryday  

Originally shared by Samantha Andrews

So what is all this science malarkey anyway?

The UK Science Council define science as ”the pursuit and application of knowledge and understanding of the natural and social world following a systematic methodology based on evidence”

As the Council explain, this methodology has some criteria…

”Scientific methodology includes the following:

Objective observation: Measurement and data (possibly although not necessarily using mathematics as a tool)


Experiment and/or observation as benchmarks for testing hypotheses

Induction: reasoning to establish general rules or conclusions drawn from facts or examples


Critical analysis

Verification and testing: critical exposure to scrutiny, peer review and assessment

Sounds all pretty straight forward doesn’t it?  A bit too straight forward perhaps.  We don’t all have a background in science so it’s not surprising that at times there is some confusion over what science is, how it is done, and what it can actually tell us about the natural and social world.  Fortunately for us, there have been three excellent open access articles have been published in The Conversation this week which address some of the issues for communicating science:

Where’s the proof in science?  There is none

Astrophysist Geraint Lewis from the The University of Sydney kicks of this fabulous trio by explaining one of the misconceptions of science: proof.  Yes that’s right, science doesn’t really prove anything.  So what does it do?  In his article, Geraint hands the last word over to Richard Feynman.  I think I will to:

”I have approximate answers and possible beliefs in different degrees of certainty about different things, but I’m not absolutely sure of anything.”

Clearing up confusion between correlation and causation

Correlations are all to do with relationships between different factors.  Like chocolate and Nobel Prize winners.  Take a look at the graph below, produced by Franz Messerli of Columbia University.  Apparently there is a correlation between chocolate consumption.  We can even put a number on this – a ‘P value’ to describe the ‘strength’ of the correlation.  In this case the value was 0.0001 – which means that “there is a less than one-in-10,000 probability of getting results like these if no correlation exists”  .  But as Mathematicians Jon Borwein and Michael Rose from the University of Newcastle (UON), Australia explain, correlation does not imply causation, which means that increasing your chocolate consumption won’t increase your chances of winning the Nobel Prize.

Why research beats anecdote in our search for knowledge

_”Certainty is seductive” writes Philosopher Tim Dean from the University of New South Wales, _”so we tend to cling to it.  We hunt for evidence that buttresses it, while ignoring or rejecting evidence that threatens to undermine it”.  Research, on the underhand, embraces uncertainty.  It isn’t about finding evidence to back your point of view, it’s about increasing our knowledge – and doing so with a scientifically backed evidence base.  For researchers, sometimes that means re-evaluating your point of view.  

Image:  From Franz Messerli’s paper Chocolate Consumption, Cognitive Function, and Nobel Laureates published in the New England Journal of Medicine.  Franz added a disclaimer to his paper, that he ”regular daily chocolate consumption, mostly but not exclusively in the form of Lindt’s dark varieties.” Unfortunately the paper is behind a paywall, but if you fancied a look you can find it here

#science #sciencesunday #scicomm


Join the Conversation


Leave a comment

Leave a Reply to Gizmo the Sane Cancel reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: