Thank you so much for all your responses.
I am also receiving other responses directly sent to me.
It is generally said that:
“Retrospective power is not a good idea”.
I will prepare a summary and post it to allstat soon.
I think this is an important issue, especially since it is
“A very common … request from referees”.
Thanks,
KN
----- Original Message ----
From: Keramat Nouri <[log in to unmask]>
To: [log in to unmask]
Sent: Wednesday, October 8, 2008 12:50:53 PM
Subject: power
Dear all,
If a result is significant (say, p-value < 0.001).
Then, is there any point to ask “calculate power
retrospectively”?
Many thanks,
KN
|