Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

David Spiegelhalter of BUGS fame:

"So a total of 50,000 bottles of gin among these 1,600 people is associated with one extra health problem. Which still indicates a very low level of harm in drinkers drinking just more than the UK guidelines."

https://medium.com/wintoncentre/the-risks-of-alcohol-again-2...

The WHO is fear mongering.

Maybe it is good health politics, people are scared of alcohol and people will have a better live.

Maybe it would be better to communicate the risks more quantitavily. Not everyone is stupid.



The way these risks are reported often makes this mistake. A statistically significant difference is reported as a "significant" difference, which means something different to lay people.

For example, if a change in diet increases the chances of getting a specific cancer from 1 in 1000 to 1.5 in 1000, that very well may be statistically significant. But, your odds of not getting that cancer go from 99.9% to 99.85%, which most people would not consider to be a meaningful difference.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: