I agree.
It would be helpful if we reserved the term 'replicate' for procedure
(duplicating the procedures of earlier research)
and reserved 'confirm' for the _outcome_ of replication -- achieving or not
achieving the same results.
At 1:12 PM -0500 10/24/99, Al Cone wrote:
>Paul,
>Methinks this is the reason for using "confirm/failure to confirm." Thus, a
>"failure to replicate" means that experimenter two did not follow the
>procedures of experimenter one: while "a failed replication" implies that
>experimenter two DID follow the procedures of experimenter one, but did NOT
>confirm the findings of experimenter one. That way one doesn't get all
>twisted up about "replication" meaning two (or more?) things. This may not
>be exactly the way McGuigan has been phrasing it for 30 plus years, but it's
>close.
>
>Al
>-----Original Message-----
>From: Paul Brandon [mailto:[EMAIL PROTECTED]]
>Sounds like a distinction between "a failure to replicate" and "a failed
>replication".
* PAUL K. BRANDON [EMAIL PROTECTED] *
* Psychology Dept Minnesota State University, Mankato *
* 23 Armstrong Hall, Mankato, MN 56001 ph 507-389-6217 *
* http://www.mankato.msus.edu/dept/psych/welcome.html *
