crosstabs sig test

[Jeffrey SMith-2]

Is there a crosstabs sig test that gives significance between particular
rows regardless of whether the overall chi2 is sig or not.

Sort of what I understand scheffe does for ANOVA.

or is there a way to do this using corresponding analysis?

Thanks,
Jeffrey

[Anthony Babinec]

If you have PRIOR hypotheses that you wish to test, you
might be able to create a subtable on which you can run a
chi-square independence test. Agresti's "Categorical Data
Analysis" has a discussion of partitioning chi-square.

If you want to run after-the-fact multiple comparisons,
SPSS Ctables can do this, assuming you have the module.
Since you are doing multiple testing, you might consider
a correction for multiple testing such as Bonferonni. Ctables
will do this for you.

Or, if you have the Classification and Regression Trees module,
you can use the CHAID approach.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Jeffrey SMith
Sent: Thursday, March 08, 2007 9:18 AM
To: [hidden email]
Subject: crosstabs sig test

Is there a crosstabs sig test that gives significance between particular
rows regardless of whether the overall chi2 is sig or not.

Sort of what I understand scheffe does for ANOVA.

or is there a way to do this using corresponding analysis?

Thanks,
Jeffrey

[Zdaniuk, Bozena-3]

Would someone be so kind and tell me how to suppress N reporting rows in
correlation tables? I don't want them in my output. Thanks so much.
Bozena

Bozena Zdaniuk, Ph.D.
Human Early Learning Partnership (HELP)
College for Interdisciplinary Studies
UBC - UVic - SFU - UNBC - TRU - UBCO
440 - 2206 East Mall, Vancouver BC  V6T 1Z3
Tel: [phone] / Fax: [phone]
www.earlylearning.ubc.ca

=====================
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

[Jon K Peck]

Using the extension command SPSSINC MODIFY TABLES, which is installed with Python Essentials in V19 or later plus the FormatCorrelations package, this syntax will do it.

CORRELATIONS
  /VARIABLES=x y z
  /PRINT=TWOTAIL NOSIG
  /MISSING=PAIRWISE.

SPSSINC MODIFY TABLES SUBTYPE='"Correlations"' SELECT=0 DIMENSION=ROWS PROCESS=PRECEDING
/styles customfunction=
"formatcorrmat.cleancorr(hidecounts=True, hidel=False, lowertri=False, hideinsig=1., emphasis=1.)".

This requires the Python programmability plugin, obtainable from SPSS Developer Central (www.spss.com/devcentral) and the other materials, which should be obtained from the new SPSS Community at
www.ibm.com/developerworks/spssdevcentral
Python Essentials will be available in the SPSS Community shortly.

This function can also hide one triangle, suppress redundant labels,  highlight large correlations and blank out insignificant ones, but some features are only available with V19.  The package also includes a dialog box interface.

HTH,

Jon Peck
Senior Software Engineer, IBM
[hidden email]
312-651-3435



From:        Bozena Zdaniuk <[hidden email]>
To:        [hidden email]
Date:        12/17/2010 03:57 PM
Subject:        [SPSSX-L] suppressing N in corr table output
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

Would someone be so kind and tell me how to suppress N reporting rows in
correlation tables? I don't want them in my output. Thanks so much.
Bozena

Bozena Zdaniuk, Ph.D.
Human Early Learning Partnership (HELP)
College for Interdisciplinary Studies
UBC - UVic - SFU - UNBC - TRU - UBCO
440 - 2206 East Mall, Vancouver BC  V6T 1Z3
Tel: [phone] / Fax: [phone]
www.earlylearning.ubc.ca

=====================
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

[<Joanne Tse>]

Hi,

 

UCLA Extension will be closed from 12/20/2010 to 1/2/2011.  I am sorry I cannot help you at this time, but I will reply to your email upon my return to the office on Monday, 1/3/2011.  If you would like to enroll in an UCLA Extension course, please visit www.uclaextension.edu.

 

Happy Holidays!

 

Thank you.

 

Joanne Han

Marketing Research Manager

UCLA Extension

www.uclaextension.edu

 

[Ruben Geert van den Berg]

Dear Bozena,

Alternatively, the FACTOR or REGRESSION commands can generate a correlation matrix containing only the correlations themselves. If you need a lot of them, OMS can distill them from the output for you.

Best,

Ruben

> Date: Fri, 17 Dec 2010 14:54:43 -0800
> From: [hidden email]
> Subject: suppressing N in corr table output
> To: [hidden email]
>
> Would someone be so kind and tell me how to suppress N reporting rows in
> correlation tables? I don't want them in my output. Thanks so much.
> Bozena
>
> Bozena Zdaniuk, Ph.D.
> Human Early Learning Partnership (HELP)
> College for Interdisciplinary Studies
> UBC - UVic - SFU - UNBC - TRU - UBCO
> 440 - 2206 East Mall, Vancouver BC V6T 1Z3
> Tel: [phone] / Fax: [phone]
> www.earlylearning.ubc.ca
>
> =====================
> 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