LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous (more recent) messageNext (less recent) messagePrevious (more recent) in topicNext (less recent) in topicPrevious (more recent) by same authorNext (less recent) by same authorPrevious page (April 1999)Back to main SPSSX-L pageJoin or leave SPSSX-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:   Thu, 15 Apr 1999 15:56:49 -0400
Reply-To:   "Bassoriello, Franco (JUS)" <Franco.Bassoriello@JUS.GOV.ON.CA>
Sender:   "SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>
From:   "Bassoriello, Franco (JUS)" <Franco.Bassoriello@JUS.GOV.ON.CA>
Subject:   Crosstabulations
Comments:   cc: "melbatoastie@hotmail.com" <melbatoastie@hotmail.com>
Content-Type:   text/plain

Dear List Serve Members

I have some questions regarding crosstabulation tables.

With CrossTabulations missing data becomes important does it not. I have 800 cases and there will be some missing data. What percentage of missing data is acceptable. I know the number of cells that have less than 5 responses should be kept to a minimum.

How many are we allowed before our conclusions are dismissed?

When should we start collapsing categories to increase our cell numbers?

Yates correlation is used when there are low cell counts. I hear this is not a popular procedure to massage the data.

I have not tried SPSS Exact Tests yet but I imagine this should help with small sample sizes. I will do this also.

Ciao

Franco Giuliano Bassoriello

Mailto:Franco.Bassoriello@jus.gov.on.ca

Back to: Top of message | Previous page | Main SPSSX-L page
listserv.uga.edu
Enterprise Information Technology Services
The University of Georgia
listhelp@uga.edu