=========================================================================
Date:         Mon, 10 Jul 2006 15:32:02 -0700
Reply-To:     dmartin@alineagroup.com
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         "Daniel E. Martin, Ph.D." <dmartin@alineagroup.com>
Organization: Alinea Group
Subject:      Calculation of totals including missing data in cross tabs
Content-Type: text/plain; charset="us-ascii"

Folks,

Hoping I can get help with this small problem. I have a database of survey
data (with several organizational divisions) , and am running cross tabs
with the following syntax:


USE ALL.

COMPUTE filter_$=(Group = 1 & Division = 44).

VARIABLE LABEL filter_$ 'Group = 1 & Division = 43 (FILTER)'.

VALUE LABELS filter_$ 0 'Not Selected' 1 'Selected'.

FORMAT filter_$ (f1.0).

FILTER BY filter_$.

EXECUTE .

The cross tabs below are breaking out the specific departments by items.

CROSSTABS

/TABLES=Department BY Informed Policies Answers Vent Team Enjoy Beliefs
ConflictBeliefs Walks Applied Recommend

Contribution Expected Safe Respect Ethics Net Email Honesty Teamimp Positive
Sensitive Insist Safteycom communication06

Teamwork06 Support06 OverallMclane

/FORMAT= AVALUE TABLES

/CELLS= COUNT ROW TOTAL

/COUNT ROUND CELL .

My problem is the item n and the totals are different. I realize this is due
to non response in the specific item, but I am looking to calculate the row
percentage by the actual # of surveys returned.

Thanks for your help!