Date: Tue, 1 Dec 1998 10:23:31 -0500
Reply-To: "Van Kirk, Jeff" <VanKirk@PSYCHIATRY.UCHC.EDU>
Sender: "SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>
From: "Van Kirk, Jeff" <VanKirk@PSYCHIATRY.UCHC.EDU>
Subject: Re: norms for data checking/verification
Content-Type: text/plain; charset="iso-8859-1"
Peter: We have always double entered. We deal with relatively small
datasets (n<100, usu.) and are looking for relatively small effect
sizes. Consequently, the data values for each case/subject are crucial.
A data entry error could destroy an effect which really exists or,
alternatively, show us one that doesn't. The expense of avoiding this
problem is miniscule compared to the ramifications of error. We have
found that the DE module (DOS version) is a reliable tool. Different
individuals enter and verify. Hope this helps. Jeff
Jeffrey R. Van Kirk
Department of Psychiatry, MC-2103
University of Connecticut Health Center
263 Farmington Ave.
Farmington, CT 06030
ph: 860-679-3613 fax: 860-679-1316
From: Peter A. Vanable [SMTP:pvanable@YODA.BSD.UCHICAGO.EDU]
Sent: Tuesday, December 01, 1998 9:55 AM
Subject: norms for data checking/verification
Hello -- As many of you know, SPSS DE has a 'verify' mode,
allowing users to
do a second pass of data entry, where the computer beeps at the
user if the
value entered the second time around doesn't match what was
first time. This feature provides some added confidence that
errors are being kept to a minimum.
For a number of years, our research group has had staff members
feature, at considerable time and cost to various projects. In
other colleagues here, I am finding that double entering of
data is fairly
unusual, i.e., most people just enter the data once and hope for
My questions are:
1) How many of you actually go to the trouble of double entering
(either using the "verify" mode or simply by having data entered
the spread sheet mode)?
2) Do others feel that the added benefit of double entering
costs in terms of the time it takes to do a second pass?
3) Assuming data re-entry/verification is done, how important is
it that a
different person enter the data the second time around.
I will appreciate any feedback on these questions... thanks very
- Peter Vanable
Peter Vanable, Ph.D.
The University of Chicago
Department of Psychiatry
5841 S. Maryland Avenue, M/C 3077
Chicago, IL 60637
773-702-1541 (U of C)