Talk:Anecdotal evidence/Archive1
Gripe about Sample Size Equals One statement[edit]
I believe this statement misrepresents the reason anecdotes don't make good statistical models. Small sample size is an issue, but a sample size of one is an unbiased estimator of a population parameter IF the individual was selected at random. In my view the problem with anecdotes is self-selection bias so maybe I'll add something to that effect. The 'get an F' thing is funny, though. Jorge 19:54, 16 February 2009 (EST)
Lemon[edit]
Even though we're supposed to be "de-CPing" it seems a shame not to have the crowning Andy anecdote:
“”Chief Justice Warren Burger, who later lamented hostility to religion, wrote the Lemon decision for the Court but admitted privately in a dinner conversation with Andrew Schlafly in late 1991 that Burger never intended for it to be applied in the broad manner that it was.
|
| —Footnote 9 Burger/Schlafly dinner conversation |
06:08, 14 June 2010 (UTC) 
Error[edit]
I'm not entirely sure what this is meant to say, but I suspect it's some kind of error. It's 2AM, so it might be caused by my fatigue, but here it is:
"Therefore, if someone who is on the medication dies, you cannot tell if they would have died anyway without it - you can't prove that the medical intervention worked, or not, from the one case study."
Here the anecdote is related to the anecdote. If you understand the medication, why it works and how it works, then you can be rather sure that no medical intervention certainly would have lead to death in this case, if the patient apparently was unable to survive the injury/illness despite the medical intervention. -195.240.170.18 (talk) 00:13, 19 August 2011 (UTC)