Date:         Thu, 13 Oct 2011 10:19:18 -0400
Reply-To:     William Shakespeare <shakespeare_1040@HOTMAIL.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         William Shakespeare <shakespeare_1040@HOTMAIL.COM>
Subject:      Pilot study

I have a large database (>100k subjects) which I'm going to use to answer
several research questions.  Normally, with a prospective study I'd run a
pilot to obtain the necessary data for sample size calculation.  However,
that's not possible here. Would it be acceptable to draw a sample from my
database and derive pilot data from it as long as I exclude all those data
from subsequent analyses?