top of page

Correlation or causation?

Updated: Mar 10, 2023

If you enjoy reading this blog, please leave a star rating on WealthTender. Thank you!

"Every single person who confuses correlation and causation ends up dying" - Hannah Fry, mathematician, author, and radio and television presenter

Data is too often presented in an unfair, unclear and misleading way

I recently challenged two senior investment professionals in relation to things they had said publicly that I disagreed with. They were both "copied" but neither disputed my challenges. What was perhaps more interesting, and certainly more depressing, were the comments I received from third parties.

In the case of the first, surprise was expressed that I had challenged the professional in question. Little about the points I had made. I had been extremely careful to make sure that my points were fact based, but it was still a bit galling that the attention seemed to be elsewhere.

In the case of the other, I had pointed out that a chart had been presented in a misleading way. It used two vertical (y) axes, one for each line, but they did not correspond. This is something that statisticians warn about, and that regulators pounce on when it appears in public (renowned statistician David Spiegelhalter devoted a large part of his excellent book, The Art of Statistics, to the matter).

However, I received comments from individuals, themselves senior financial professionals, that betrayed a worrying lack of understanding about the need to be careful when communicating complicated investment concepts to retail investors/non experts. The fact is that making only a suggestion that there is causation as the aforementioned chart did is not good enough. It is important that one must also provide the logical explanation for it. If indeed it exists, that is.

With this latter remark in mind, it's time for something a bit more lighthearted.

I don't know who Tyler Vigen is, but he or she must have spent many many hours trawling through disparate data series looking for pairs where there was a high degree of correlation, creating charts, and putting them on a website, Spurious Correlations.

Tyler assumed the high correlations were spurious. But what if they weren't? Below are Tyler's charts, together with my entirely logical explanations for them. I have done five, and would welcome your suggestions for the rest (or indeed better ones for my five). There will be a prize, and it might even correlate with the best entry!

By the way, there are two explanations for each chart - it would be utterly irresponsible of me to assume a particular direction of causation.

Finally, thank you, Tyler, for your fabulous website. And thank you, Hannah, for your brilliant quote at the beginning of this post.

A. More math doctorates awarded means a greater understanding of the link between greenhouse gases and atmospheric temperature, of the need for clean energy, and thus of the need to stockpile uranium...

B. Uranium stored at US nuclear power plants produces dangerous radiation which turns people into math geeks...

A. The best place to practice spelling is outdoors...where the venomous spiders live...

B. It has been proven that spider venom enhances memory. While it won't have done those who died any good, it did help the survivors...

A. Americans who buy Japanese cars later feel they have betrayed their country. With that comes a great sense of remorse that leads them to...

B. Suicide attempts by crashing of motor vehicle tend to be more successful in bigger, heavier cars that have more momentum. This leads to a perception that bigger, heavier cars are more dangerous and an increase in demand for smaller Japanese cars...

A. The older the winner of the Miss America competition, the more she is admired by older generations who are more familiar with steam engines and thus how hot vapours, objects etc can be used to get rid of their annoying spouse...

B. The more murders by steam, hot vapours and hot objects, the more finger print evidence gets destroyed, the fewer crimes get solved, the greater the demand for youngsters to become crime stoppers, and the fewer youngsters there are to enter Miss America competitions, thus favouring older entrants (ok this is particularly absurd but then so too is collecting data about steam, vapour, hot object murders).

A. The more cheese people people eat, the weirder their dreams, the more they toss around in their sleep, and the more likely they are to get fatally entangled in their bedsheets...

B. The more entangled bedsheet deaths, the greater the fear of going to bed, the more people stay up snacking, which for many means higher consumption of cheese slices...

The views expressed in this communication are those of Peter Elston at the time of writing and are subject to change without notice. They do not constitute investment advice and whilst all reasonable efforts have been used to ensure the accuracy of the information contained in this communication, the reliability, completeness or accuracy of the content cannot be guaranteed. This communication provides information for professional use only and should not be relied upon by retail investors as the sole basis for investment.

© Chimp Investor Ltd

1,142 views0 comments

Related Posts

See All


bottom of page