Carol,
I think you really do need 66 persons. So, two scenarios given a starting
sample size of 60. 1) The day after enrollment, six people drop out. 2) The
day before the study ends, six people drop out. Given that the actual data
generates the expected sample size, I think a power calculation will show
scenario 1 to have power less than 80 and scenario 2 to have power
fractionally less than if the six people had not quit on the day before the
last day.
Gene Maguin
>>I'm running Sample Power 2.0 for a survival calculation. My question is
about attrition.
Suppose you include an attrition of 10% and come up with a 60 patient study
that is powered at 80%. Do you really need 66 to get the power of .80? Or
will you have adequate power with 54 patients (a 10% attrition)?
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Locked
