A US National Health Care System? Message Board

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Politics : A US National Health Care System?

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

To: Lane3 who wrote (6335)	3/13/2009 12:39:56 PM
From: TimF	Read Replies (1) of 42652

I agree that observational studies should be very heavily discounted as evidence for causation (also if their is causation you have to consider which way it goes, hypothetically people with heart problems may have less energy and thus put less effort in to their personal grooming, and thus shave less often). Not sure I'd say they are totally useless other than generating hypotheses, esp when the correlations are extremely strong, the groups observed very large, and the time period is also long, but they shouldn't normally be given a lot of weight. Correlation may suggest causation, but it is very true that it doesn't mean or imply causation. I think I posted to you once about how major league pitchers who's names started with K had more strikeouts that the average. And since K means "strikeout" some people thought this interesting. But the percentage over average is very small, and K is not the top letter for names/strikeout percentages, or in the top 5 and I think maybe not in the top 10, its more about people jumping to notice interesting coincidences than any serious connection. And even if K was number 1, that wouldn't seriously imply causation.

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next