Association ≠ Causation reminder on ‘racket sports reduce risk of death’ stories

Gary Schwitzer is publisher of  He tweets as @garyschwitzer and/or using our project handle @HealthNewsRevu.

Blank vintage warning metal sign with copy space standing in the middle of a grass field with stormy cloudscape. Rusty stains, two screws and wooden post. Photorealistic vector illustration. Layered EPS10 file with transparencies and global colors. Individual elements and textures. Related images linked below.

In 2017 we will have a regular column highlighting media messages that should have listened to our frequent reminder:

Association ≠ Causation.

In other words, they fail to remind readers and listeners about the clear limitations of observational studies that cannot prove cause and effect. Yet they often use causal language to describe the results of such research. We’ve offered readers a primer on this topic for years.

The big story of the day, erroneously reported in the following examples:

TIME commits the time-honored flaw with its headline, “These three sports will help you live longer.” (Time out: not proven.)

Reuters repeats the error with, “Want to delay death? Then swim, dance, or get on court, study says.” (No, it didn’t.)

The Guardian isn’t guarding against hype with its headline, “Health racquet: Tennis reduces risk of death at any age, study suggests.” (No proof of reduction)

HealthDay hedges its headline with a “may” inserted: “Tennis anyone? It may prolong your life” (Hedging with qualifiers not good enough in our view)

The Los Angeles Times leaped from the observational study to even offering advice: “For a long life, consider picking up a tennis racket.”

As that story explained, “The results, published Tuesday in the British Journal of Sports Medicine, are based on data from 43,705 women and 36,601 men who participated in the Health Survey for England or the Scottish Health Survey. These volunteers, whose average age was 52, told interviewers how often they exercised, what type of exercise they did and how intense their workouts were.”

Whenever you see stories that leap to conclusions based on questionnaires that rely on memory and self-reporting, as this research did, red flags should pop up.

Even the journal news release emphasized the following – which did not appear in any of the stories I saw in my quick scan this morning:

This is an observational study so no firm conclusions can be drawn about cause and effect, added to which the relatively short recall period, the ‘seasonality’ of certain sports, and the inability to track changes in levels of sports participation throughout the monitoring period, may all have had some bearing on the results, caution the researchers.

There will be many other stories about this observational study today. As you read them, remember this:  sometimes it makes sense to consider observational data when making public health recommendations. And maybe this is one of those times. But the quality of the evidence is the paramount consideration. And in the examples above I saw very little to no independent journalistic vetting of the quality – and limitations – of this study.  It is simply inaccurate for so many journalists to use causal language – with its implication of the certainty of the findings – to describe research that is far from certain.  That, in my view, is not only bad editorial judgment.  It is an ethical issue because it misleads people. And if you don’t know what the limitations are – or if you do know but choose not to include them – I submit that because you’re misleading people you probably should not report on this type of research at all.

You might also like

Comments (2)

Please note, comments are no longer published through this website. All previously made comments are still archived and available for viewing through select posts.

Tio Trom

November 30, 2016 at 10:51 am

Always great to read such articles. Please ‘debunk’ more such ‘sensationalistic news! I was thinking it would be so fantastic if you could build a browser extension and when people have it installed and visit a website that posts such news that you criticize, to automatically see the stars and critique you gave it. Similar to this extension – or just use that one.

Tio Trom

November 30, 2016 at 11:01 am

Also keep and eye on this website if you were not aware of – they do a similar work as yours.