[BioC] B statistic in limmaGUI

[Elizabeth Brooke-Powell]

Hi Sean,

Thanks for your help, and here is our final question on this matter. We are
interested in things that do not move. From our current understanding (maybe
completely wrong) that analogous to finding things that move (are
differentially expressed) should we ask for B values from some negative
value to the lowest B value?

Thanks again, 

Liz 

-----Original Message-----
From: Sean Davis [mailto:sdavis2 at mail.nih.gov] 
Sent: 19 August 2004 15:28
To: Elizabeth Brooke-Powell
Subject: Re: [BioC] B statistic in limmaGUI

I have yet to hear from anyone else regarding the "realistic" 
interpretation of the B-values, but negative B-values are not very 
interesting (they are more than likely not differentially expressed).  
Also, I don't know if there is any deep meaning in the minimum B value.

Sean

On Aug 19, 2004, at 9:09 AM, Elizabeth Brooke-Powell wrote:

> Hi Sean,
>
> Does +ve mean better then average odds that it is differentially 
> expressed
> and therefore does the more -ve mean that the odds are greater that it 
> is
> not differentially expressed? Is there some meaning that the lowest B 
> values
> tend to be about -6?
>
> Liz
>
>