View Single Post
Old 03-28-2014, 01:08 PM   #1
blakeoft
Member
 
Location: Connecticut

Join Date: Oct 2013
Posts: 79
Default CummeRbund csVolcano() alpha and p-value questions

I've got a couple questions about csVolcano().

I've tried plotting with alpha = 0.05, and showSignificant = TRUE. When I look at the red data points, the lowest they go is about 2.75. But then -log_10(0.05) is about 3 (far enough from 2.75 that I know it isn't right). Then I tried alpha = 0.01, and the lowest red points are around 3.7. -log_10(0.01) is around 4.6 though. Is the y axis not really -log_10(p value)? Or maybe I'm just misunderstanding the relationship of alpha and p value. I was under the impression that if the p value is less than alpha, then we reject the null hypothesis, i.e. accept that there is significant change. Is this correct?

Thanks,
Blake
blakeoft is offline   Reply With Quote