It seems that you are talking about a different application of the test. In the multinomial regression I think the Wald test is evaluated with a Chi-squared distribution (I may need to check the details, too).
In the other case Chi-squared also applies to frequency tables and there the count per cell will have an effect on the results. For expected values, based on Cochran each Eij should be at least 1 and no more than 20% of them (Eij) should be less than 5.
Fermin Ornelas, Ph.D.
Management Analyst III, AZ DES
1789 W. Jefferson Street
Phoenix, AZ 85032
Tel: (602) 542-5639
E-mail:
[hidden email]
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On Behalf Of Stats Q
Sent: Monday, December 10, 2007 4:18 PM
To:
[hidden email]
Subject: Chi square goodness of fit
Could someone please shed some light on the following for me? I read that the chi-square goodness of fit test is a problem when the number of expected frequencies are low. I have this situation so am not relying on the GOF statistic. However, in multinominal regression SPSS gives another chi-square under the heading of "Likelihood ratio tests". Are these tests based on expected frequencies as well or can I use them?
Cheers!
_________________________________________________________________
Who's friends with who and co-starred in what?
http://www.searchgamesbox.com/celebrityseparation.shtml=======
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
NOTICE: This e-mail (and any attachments) may contain PRIVILEGED OR CONFIDENTIAL information and is intended only for the use of the specific individual(s) to whom it is addressed. It may contain information that is privileged and confidential under state and federal law. This information may be used or disclosed only in accordance with law, and you may be subject to penalties under law for improper use or further disclosure of the information in this e-mail and its attachments. If you have received this e-mail in error, please immediately notify the person named above by reply e-mail, and then delete the original e-mail. Thank you.
=====================
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
