[R] T-test to check equality, unable to interpret the results.

[Steve Lianoglou]

Hi Bert,

On Sep 16, 2009, at 4:06 PM, Bert Gunter wrote:
<snip>
> Finally, "statistically different" is a meaningless phrase.


I'm not sure if you're quoting that to point out something in  
particular you're taking exception to, but I never said that. I did  
mention "statistical significance" with respect to a test, though,  
which is not meaningless, as far as I know.

> I would not bother with this were it not for the fact that Steve's  
> apparent
> confusion -- or at least imprecise statements -- is widespread among
> scientists, in my experience, and leads to frequent misapplications  
> and
> misinterpretations of significance testing. The woes of Stat 101  
> training.
</snip>

As noted in my message, I didn't claim to be a "real" statistician,  
but I'm not all that confused, either: I made it a point to mention  
that I was intentionally sacrificing rigor for intuition. I guess, by  
definition, this leads to some imprecise statements with varying  
degrees of vagary. In my view they seemed like rather small pot holes  
on the path to a workable understanding of some use of a t-test,  
apparently the pot holes were larger than measured: sorry.

Thanks for wearing the stats prof hat, though. It's good that someone  
stepped up to lay down the law.

With white flag raised,

-steve

--
Steve Lianoglou
Graduate Student: Computational Systems Biology
   |  Memorial Sloan-Kettering Cancer Center
   |  Weill Medical College of Cornell University
Contact Info: http://cbio.mskcc.org/~lianos/contact