Quote:
Originally Posted by 1thing2add
What the good doctors' analysis demonstrates is that their conclusions can be reproduced with no less than 95% reliabilty by another researcher. No one, including you, has shown how their analytical methods are flawed to support your ultimate claim that their confidence intervals of 95% are in error. Please show them the error of their ways!
|
I was about to explain, again, why making statements like
Quote:
|
"What the good doctors' analysis demonstrates is that their conclusions can be reproduced with no less than 95% reliabilty by another researcher."
|
is misleading, but then I looked again at the conclusions:
Quote:
|
Conclusions. Uninsurance is associated with mortality. The strength of that association appears similar to that from a study that evaluated data from the mid-1980s, despite changes in medical therapeutics and the demography of the uninsured since that time.
|
and realised there is probably no point. Most of what we have been arguing about is what was in the press release (which I hope you will remember I don't rate as a source of information) rather than the meager portion of the actual article we have seen. The actual conclusions you quoted say only that there is an association between uninsurance and mortality and that his association appears to have not changed in the last 20+ years. I think most, if not all, here will agree there is some kind of association between uninsurance and death.
In fact, it is rather interesting that the published article/conclusions do not state that
"lack of health insurance causes 44,789 excess deaths annually." or that this is due to a failure to enact a system of universal health care. Perhaps the journal would not allow the publication of such a statement since it is not sufficiently supported by either the data or the analysis presented in the article?