Date: Wed, 28 Jul 2010 10:08:36 -0400
Reply-To: Gene Maguin <firstname.lastname@example.org>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: Gene Maguin <email@example.com>
Subject: Re: LVCF
Content-Type: text/plain; charset="us-ascii"
It sounds like what you want to do has two parts to it. One part is
documentation and the second is the actual carry forward and replacement.
There is a way to do the replacement through syntax. There is also an spss
command, RMV, that can do missing value replacement. The documentation part,
at least as I envision it, is pretty simple to do. But, if you truly have
two cases with missing values on two variables, I wonder why you don't just
do the replacement and documentation by hand. Scan down the data file to
find the problem, look backward or to the left, depending how your dataset
is organized, to find the replacement value and then write four lines of
code to replace the values and, simultaneously, document the replacement.
If your dataset is too long or wide to do the missing value search by
scanning, then you might use this code to find the problem case(s).
Select if (missing(x1) or missing(z27)).
List caseid x1 z27.
Please reply on list if you want more.
>>I have a databases where each case has several data points from 3
different data collection points in time. I have very little missing data,
ie just a couple of variables for a couple of cases. However, I would like
to carry the baseline value forward to the missing data point at the later
time point. Also, I would like to do this in such a way that I can log it
in the syntax file and have it saved for checking and reproducing. Thanks
for any assistance
To manage your subscription to SPSSX-L, send a message to
LISTSERV@LISTSERV.UGA.EDU (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
For a list of commands to manage subscriptions, send the command