I assume you're using the default listwise deletion of missing values for Regression. There may be more elegant solutions, but here's one way to filter the dataset to include only cases with non-missing values for all the variables in your regression analysis:
compute filtervar=not(missing(var1+var2+var3...+varn).
filter by filtervar.
frequencies variables=var1, var2, var3...varn.
where var1, var2, var3, etc. are the variables in your regression analysis.
This will filter out any cases with missing values for any specified variable because if any of the variables has a missing value the simple sum of all the variables for that case is also missing.
Here's a simple example, in which there is only one case for non-missing values for all variables:
data list list /x y z.
begin data
11,,13
21,22
31,32,33
end data.
compute filtervar=not(missing(x+y+z)).
filter by filtervar.
frequencies variables=x y z.
filter off.
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On Behalf Of Karen Lewis
Sent: Sunday, May 17, 2009 11:09 AM
To:
[hidden email]
Subject: clarification on previous post on obtaining descriptives
I want to get frequencies (e.g., %'s associated with my control variables-
male/female, catagories of income-to-needs ratio, maternal ed, %married,
etc.), but I don't think that I want to use descriptives on the 176
families in my dataset, as that number dwindles to 105 after I run my
regression.
=====================
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
=====================
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
