Date: Sun, 24 Jun 2007 16:06:29 -0300
Reply-To: Hector Maletta <hmaletta@fibertel.com.ar>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: Hector Maletta <hmaletta@fibertel.com.ar>
Subject: Re: recoding a second missing value
In-Reply-To: <467EBA2E.4@cornell.edu>
Content-Type: text/plain; charset="us-ascii"
You have to recode only the system missing values. For that, use
the syntax window to write the following command:
RECODE varname (SYSMIS=8).
That would do the trick, I expect, leaving the 9s untouched.
Another approach is temporarily designating the 9 as a valid value,
then do as you did before (only system-missing values would be recoded),
then restate the 9 (and the 8) as missing values.
Hector
-----Original Message-----
From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of
Govind Acharya
Sent: 24 June 2007 15:39
To: SPSSX-L@LISTSERV.UGA.EDU
Subject: recoding a second missing value
Hi all,
I have a very large data file (915 variables, 17,000 cases) and our
client wants the following: if it is truly missing, we have a 9.
But,
our software that reads the forms rendered a second missing data
that I
want coded as an 8 as a blank. That's fine, but now I am stuck
with
having to recode all of the blanks into an 8. When I use the
"Recode
into Same Variable" and use the option "System or User Missing" as
the
Old Value and enter the value of 8, it changes the blanks *and* the
9 to
an 8. That's not good! So, is there a way to do this using a
script or
drop down that can allow me to recode blank values as an 8 but
preserve
the 9 as it is? I suppose I could change the 9 to nonmissing and
then
make the 8 missing, then recode the blanks as an 8, but I frankly
don't
know how to do that in a script.
Thanks so much for any help you can provide!
Govind
--
-
Govind Acharya
Assistant Director/Senior Research Associate
Survey Research Institute, Cornell University
391 Pine Tree Rd.
Ithaca, NY 14850
phone: (607) 255-0375; fax: (607) 255-7118
http://www.sri.cornell.edu
|