[R] OT Sorta: Odds Are, It's Wrong...

[Marc Schwartz]

On Mar 15, 2010, at 12:21 PM, Ted Harding wrote:

> On 15-Mar-10 16:22:13, Marc Schwartz wrote:
>> Hi all,
>> I thought that readers of R-Help might find the following article at
>> ScienceNews of interest:
>> 
>>  Odds Are, It's Wrong
>>  Science fails to face the shortcomings of statistics
>>  By Tom Siegfried
>>  March 27th, 2010; Vol.177 #7 (p. 26)
>> 
>> http://www.sciencenews.org/view/feature/id/57091/title/Odds_are,_its_wro
>> ng
>> 
>> Regards,
>> Marc Schwartz
> 
> If you changed your Subject to "Odds R, it's wrong", arc, you might get
> more on-topic, Marc. Or at least increase people's subjective beliefs
> that it was OT.

Yep, that was just way too obvious, wasn't it...Arrrrr...

I plead low serum glucose level this morning, after having some fasting blood work drawn...  :-)


> That's not a bad article, as such things go!
> 
> I was reminded of reading, many moons ago in a book[1] by John Ziman[2],
> words to the effect that[3]:
> 
>  "If your experiment gives a result significant at the 5 per cent
>   level, then 1 in 20 of your colleagues is entitled to disblieve
>   you."
> 
> [1]
> Ziman, John (1968).
> Public Knowledge: Essay Concerning the Social Dimension of Science.
> Cambridge University Press. ISBN 0-521-06894-0.
> 
> [2]
> http://en.wikipedia.org/wiki/John_Ziman
> 
> [3]
> I don't have the book immediately to hand (though I have it somewhere),
> so cannot vouch that the above is verbatim. However, it's not far off,
> and the final clause very probably is verbatim.


In turn, that reminds me of Stephen Senn's writing in Dicing with Death: Chance, Risk and Health:

"We can predict nothing with certainty but we can predict how uncertain our predictions will be, on average that is."

Regards,

Marc