I suggest folks read the cited research. It's eye-opening here, in a way that's very irritiating. This does not seem like particularly good science journalism.<p>Because of the road rage story in the lede, a whole lot of people are going to walk away from that piece thinking Statins -> Aggression.<p>The author even repeats it in a troubling way by linking to Golomb's research (their main source for this article I imagine) on statins and aggression:<p>"Since then, more direct evidence has emerged. Several studies have supported a potential link between irritability and statins, including a randomised controlled trial – the gold-standard of scientific research – that Golomb led, involving more than 1,000 people. It found that the drug increased aggression in post-menopausal women though, oddly, not in men."<p>You can see right there - it's plain as day. Randomised controlled trial, gold standard. The really astute scientists now know statins make people aggressive!<p>Except, EXCEPT... the study that Golomb DID found that statins overall lowered aggression... in men, and did not raise it in pre-menopausal women.<p>Again, the paper the journalist linked to shows the OPPOSITE of what the BBC piece claims it does.<p>The only reason the author found a subset of people that statins increase aggression in: they sliced and dice their data a bajillion different ways. They looked at age strata, baseline aggression, sleep-status, serotonin status, until they found a group -- post meno-pausal women -- in which the statin appeared to increase aggression. And that was only significant when they excluded one participant who had medically induced menopause!<p>"Among (postmenopausal) women, a borderline aggression-increase on statins became significant with exclusion of one younger, surgically-menopausal woman (N=310) β=0.70(SE=0.34)P=0.039"<p>When you adjust for multiple comparisons done (otherwise pretty sure you're just p-hacking) the result for women becomes statistically insignificant --which, given the number of ways they sliced the data, is not at all surprising!<p>"The sample size for women is half that for men, calculations did not power separately for women, and significance of findings for women would not be sustained under multiple comparison adjustment."<p>The overall thrust of 'Be a medical conservative, it's easy to cause treatment related harms you're not aware of' is a good one - there are many pharma companies pushing product on iffy claims. And a lot of research that shows how pharma trials minimize side effects and maximize results by surreptitiously excluding unhealthy trial participants.<p>The research in this piece is neither brilliant, nor awful... but given that the author appears to happily be quoted in a way that takes their research out of context, and seems to be the main source in an article that makes claims that their research does not support, really concerns me that they have their own flawed biases on statins ...