February 11 roundup

| | Comments (1)

1 Comments

When the correct test gets applied to the anti-convulsant data, Fisher's Test, the difference loses its statistical significance. I doubt the FDA committee members took eleventh grade statistics.

Anyone may enter the numbers here:

http://www.matforsk.no/ola/fisher.htm

Even without the correct test, the difference is not clinically meaningful. It is just gotcha by biased ideologues.

Leave a comment

Archives