Statistics can be confusing.
This is from a report on research showing that exposure to antibiotics early in childhood did not lead to ADHD (although there is a “but” at the end.):
“Risk of developing ADHD was estimated using Cox proportional hazards regression in a high-dimensional propensity score–matched cohort (n = 69,738) and a sibling cohort (n = 67,671). ADHD risk was not associated with antibiotic exposure in the matched-cohort (hazard ratio = 1.02, 95% confidence interval: 0.97, 1.08) or in the sibling cohort (hazard ratio = 0.96, 95% confidence interval: 0.89, 1.03). In secondary analyses of the matched cohort, ADHD risk increase was observed in those exposed to 4 or more antibiotic courses or a duration longer than 3 weeks. These associations were not observed in the sibling cohort. We concluded that antibiotic exposure in the first year of life does not pose an ADHD risk on a population level.”
A recent journal column questioned the use of the traditional p-value, saying that a low p-value does not mean that the findings are valid, but only that the research was well done. I could not understand the discussion of this either.
Science can be confusing:
I continue to see, even among scientists, some confusion:
- Correlation is not the same as cause. The incidence of diagnosed ADHD in US children has risen in the past twenty years. So has the US military budget. It seems unlikely that one caused the other, but there is a correlation.
- When there is correlation and it does seem related, it can be difficult to distinguish cause and effect. The US is involved in long term wars; the military budget has been rising. Which one caused the other? Think about it.
- Not proven is not the same as proven not. The new fad for evidence based medicine is a good thing, but it is not the only thing. ( The insurance companies like to use this to deny claims.)
- There can be a confusion about objective and subjective conclusions. Years ago I was bothered by a scientific paper titled “Schizophrenia Has A Poor Prognosis.” I wrote a letter to the editor, and the researchers responded that they were ‘sorry if Dr. Puryear was bothered by our findings.’ I wasn’t bothered by their findings. They had published their data, which was whatever it was – ‘after x years, y percent of patients are still psychotic’. Then they had made a subjective leap to state their conclusion, in their title.
Sometimes this stuff gives me a headache, but the scientific community is working to correct the problems outlined in these two articles. Science is better than nonsense.
@addstrategies #adhd #add @dougmkpdp
p value – more articles
Bonus Suggestion O the Day:
If you are going to get a massage, you may want to avoid eating a lot of prunes or drinking a lot of coffee beforehand. Just saying.