Sig testing in custom table

classic Classic list List threaded Threaded
5 messages Options
Reply | Threaded
Open this post in threaded view
|

Sig testing in custom table

GauravSrivastava
Hi All,

I am trying to do sig testing at 2 different level (5% & 10%) in same table. I am using below syntax but it only allow me to go with one level (either at 5% or 10%) at a time.

CTABLES
  /FORMAT EMPTY=BLANK MISSING='.'
  /SMISSING VARIABLE
  /VLABELS VARIABLES=$q2 s1 DISPLAY=LABEL
  /TABLE $q2 [C] BY s1 [C][COUNT F40.0, COLPCT.COUNT PCT40.1, TOTALS[COUNT F40.0]]
  /SLABELS POSITION=ROW
  /CATEGORIES VARIABLES=$q2  EMPTY=INCLUDE TOTAL=YES POSITION=AFTER
  /CATEGORIES VARIABLES=s1 [1, 2, 3, 4, 5, 6, 7] EMPTY=INCLUDE TOTAL=YES POSITION=AFTER
  /COMPARETEST TYPE=PROP ALPHA=0.05 ADJUST=BONFERRONI ORIGIN=COLUMN INCLUDEMRSETS=YES
    CATEGORIES=ALLVISIBLE.

Also it produce 2 table one with count & percentage and other for sig testing. Can any one suggest how to merge both the tables.

Please suggest.

Regards,
Gaurav
Reply | Threaded
Open this post in threaded view
|

Re: Sig testing in custom table

Jon K Peck
You can only do one significance level at a time in CTABLES.

CTABLES provides a way to have the tests appear in the main table.  Specify MERGE=YES on the COMPARETEST subcommand (or do this on the Test Statistics tab in the gui).  However, the format of the test results, which conforms to APA style, is sometimes not what people want.  As an alternative you can use the SPSSINC MERGE TABLES extension command, which requires the Python Essentials from the SPSS Community site (www.ibm.com/developerworks/spssdevcentral) can be used for a more traditional presentation.

HTH,

Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
[hidden email]
new phone: 720-342-5621




From:        GauravSrivastava <[hidden email]>
To:        [hidden email]
Date:        04/11/2012 01:58 AM
Subject:        [SPSSX-L] Sig testing in custom table
Sent by:        "SPSSX(r) Discussion" <[hidden email]>




Hi All,

I am trying to do sig testing at 2 different level (5% & 10%) in same table.
I am using below syntax but it only allow me to go with one level (either at
5% or 10%) at a time.

CTABLES
 /FORMAT EMPTY=BLANK MISSING='.'
 /SMISSING VARIABLE
 /VLABELS VARIABLES=$q2 s1 DISPLAY=LABEL
 /TABLE $q2 [C] BY s1 [C][COUNT F40.0, COLPCT.COUNT PCT40.1, TOTALS[COUNT
F40.0]]
 /SLABELS POSITION=ROW
 /CATEGORIES VARIABLES=$q2  EMPTY=INCLUDE TOTAL=YES POSITION=AFTER
 /CATEGORIES VARIABLES=s1 [1, 2, 3, 4, 5, 6, 7] EMPTY=INCLUDE TOTAL=YES
POSITION=AFTER
 /COMPARETEST TYPE=PROP ALPHA=0.05 ADJUST=BONFERRONI ORIGIN=COLUMN
INCLUDEMRSETS=YES
   CATEGORIES=ALLVISIBLE.

Also it produce 2 table one with count & percentage and other for sig
testing. Can any one suggest how to merge both the tables.

Please suggest.

Regards,
Gaurav


--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/Sig-testing-in-custom-table-tp5632074p5632074.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

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


Reply | Threaded
Open this post in threaded view
|

Re: Sig testing in custom table

GauravSrivastava
Hi Jon,

I have not found this feature in SPSS v.17 . Is this available in higher version only.

Is there any alternative to do this in v17. Please suggest.

Regards,
Gaurav

On Wed, Apr 11, 2012 at 6:14 PM, Jon K Peck <[hidden email]> wrote:
You can only do one significance level at a time in CTABLES.

CTABLES provides a way to have the tests appear in the main table.  Specify MERGE=YES on the COMPARETEST subcommand (or do this on the Test Statistics tab in the gui).  However, the format of the test results, which conforms to APA style, is sometimes not what people want.  As an alternative you can use the SPSSINC MERGE TABLES extension command, which requires the Python Essentials from the SPSS Community site (www.ibm.com/developerworks/spssdevcentral) can be used for a more traditional presentation.

HTH,

Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
[hidden email]
new phone: 720-342-5621




From:        GauravSrivastava <[hidden email]>
To:        [hidden email]
Date:        04/11/2012 01:58 AM
Subject:        [SPSSX-L] Sig testing in custom table
Sent by:        "SPSSX(r) Discussion" <[hidden email]>




Hi All,

I am trying to do sig testing at 2 different level (5% & 10%) in same table.
I am using below syntax but it only allow me to go with one level (either at
5% or 10%) at a time.

CTABLES
 /FORMAT EMPTY=BLANK MISSING='.'
 /SMISSING VARIABLE
 /VLABELS VARIABLES=$q2 s1 DISPLAY=LABEL
 /TABLE $q2 [C] BY s1 [C][COUNT F40.0, COLPCT.COUNT PCT40.1, TOTALS[COUNT
F40.0]]
 /SLABELS POSITION=ROW
 /CATEGORIES VARIABLES=$q2  EMPTY=INCLUDE TOTAL=YES POSITION=AFTER
 /CATEGORIES VARIABLES=s1 [1, 2, 3, 4, 5, 6, 7] EMPTY=INCLUDE TOTAL=YES
POSITION=AFTER
 /COMPARETEST TYPE=PROP ALPHA=0.05 ADJUST=BONFERRONI ORIGIN=COLUMN
INCLUDEMRSETS=YES
   CATEGORIES=ALLVISIBLE.

Also it produce 2 table one with count & percentage and other for sig
testing. Can any one suggest how to merge both the tables.

Please suggest.

Regards,
Gaurav


--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/Sig-testing-in-custom-table-tp5632074p5632074.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

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



CG
Reply | Threaded
Open this post in threaded view
|

Automatic reply: Sig testing in custom table

CG

I am out of the office until February 15.  For immediate assistance please contact Jessica Jaramillo ([hidden email]). Thank you.

Reply | Threaded
Open this post in threaded view
|

Re: Sig testing in custom table

Jon K Peck
In reply to this post by GauravSrivastava
Having the significance indicators in the main table in CTABLES was a feature added in SPSS 18.  However, the MERGE TABLES approach should work with V17 if you have or can obtain the Python programmability plugin for V17.  IBM cannot distribute that anymore.

HTH

Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
[hidden email]
new phone: 720-342-5621




From:        Gaurav Srivastava <[hidden email]>
To:        Jon K Peck/Chicago/IBM@IBMUS
Cc:        [hidden email]
Date:        04/16/2012 02:14 AM
Subject:        Re: [SPSSX-L] Sig testing in custom table




Hi Jon,

I have not found this feature in SPSS v.17 . Is this available in higher version only.

Is there any alternative to do this in v17. Please suggest.

Regards,
Gaurav

On Wed, Apr 11, 2012 at 6:14 PM, Jon K Peck <peck@...> wrote:
You can only do one significance level at a time in CTABLES.

CTABLES provides a way to have the tests appear in the main table.  Specify MERGE=YES on the COMPARETEST subcommand (or do this on the Test Statistics tab in the gui).  However, the format of the test results, which conforms to APA style, is sometimes not what people want.  As an alternative you can use the SPSSINC MERGE TABLES extension command, which requires the Python Essentials from the SPSS Community site (
www.ibm.com/developerworks/spssdevcentral) can be used for a more traditional presentation.

HTH,


Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM

peck@...
new phone: 720-342-5621





From:        
GauravSrivastava <srivastgaurav@...>
To:        
[hidden email]
Date:        
04/11/2012 01:58 AM
Subject:        
[SPSSX-L] Sig testing in custom table
Sent by:        
"SPSSX(r) Discussion" <[hidden email]>




Hi All,

I am trying to do sig testing at 2 different level (5% & 10%) in same table.
I am using below syntax but it only allow me to go with one level (either at
5% or 10%) at a time.

CTABLES
 /FORMAT EMPTY=BLANK MISSING='.'
 /SMISSING VARIABLE
 /VLABELS VARIABLES=$q2 s1 DISPLAY=LABEL
 /TABLE $q2 [C] BY s1 [C][COUNT F40.0, COLPCT.COUNT PCT40.1, TOTALS[COUNT
F40.0]]
 /SLABELS POSITION=ROW
 /CATEGORIES VARIABLES=$q2  EMPTY=INCLUDE TOTAL=YES POSITION=AFTER
 /CATEGORIES VARIABLES=s1 [1, 2, 3, 4, 5, 6, 7] EMPTY=INCLUDE TOTAL=YES
POSITION=AFTER
 /COMPARETEST TYPE=PROP ALPHA=0.05 ADJUST=BONFERRONI ORIGIN=COLUMN
INCLUDEMRSETS=YES
   CATEGORIES=ALLVISIBLE.

Also it produce 2 table one with count & percentage and other for sig
testing. Can any one suggest how to merge both the tables.

Please suggest.

Regards,
Gaurav


--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/Sig-testing-in-custom-table-tp5632074p5632074.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to

LISTSERV@... (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