That's a pretty big problem. Although at the time it was published it was ok, TODAY, I don't think a study with that problem would get published in NEJM without an intent to treat analysis. It also doesn't seem to rare that intent-to-treat and as-treated analysis often have reverse outcomes.
Via Marginal Revolution again, the RAND folks have a reply.
Your link to Cannon is broken. :)
Thanks for posting this, Robin. Let us try to take delight in discovering and disseminating evidence that weakens our arguments.
That's a pretty big problem. Although at the time it was published it was ok, TODAY, I don't think a study with that problem would get published in NEJM without an intent to treat analysis. It also doesn't seem to rare that intent-to-treat and as-treated analysis often have reverse outcomes.
TGGP, my cut medicine in half essay listed many studies. (And the link has been edited.)
Your link to John McDonough is broken. Get rid of the "" in the url.
What are the other studies that give a null result?