Did I really read this? Did you really write this?

The probability that the difference between the two datasets is due to random fluctuations — rather than an actual difference — is p=8%. In most studies, p should be less than 5% before we accept a significant difference between two datasets. But 8% is close enough to 5% that I conclude that the difference is marginally significant.

http://www.useit.com/alertbox/roi.html

“Marginally significant”? Sweet crackers, where did you go to school? How many question marks can I use in one post?

Advertisements