Fisher exact test possible with CSTABULATE command?

[Shirin Nuesslein]

Hello, 

I am working with the CSTABULATE command for my complex sample. Is it possible to run the CSTBULATE /TEST subcommand in a way that gives me the Fisher's exact test of independence? It appears that the default option is a Pearson's chi-square test, and I don't see a way to modify this.

Is there a work around anyone is aware of?

Any pointers appreciated! 

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

[Rich Ulrich]

Fisher's Exact Test is for 2x2 tables.  That seems inconsistent with

your mention of "complex sample."

There are two or three "exact tests" based on permutations and

different criteria, but all the usual ones are employed on two-way

tables. That also seems inconsistent with complex samples.

--

Rich Ulrich

---

From: SPSSX(r) Discussion <[hidden email]> on behalf of Shirin Nuesslein <[hidden email]>
Sent: Wednesday, October 14, 2020 11:38 AM
To: [hidden email] <[hidden email]>
Subject: Fisher exact test possible with CSTABULATE command?

 

Hello, 

I am working with the CSTABULATE command for my complex sample. Is it possible to run the CSTBULATE /TEST subcommand in a way that gives me the Fisher's exact test of independence? It appears that the default option is a Pearson's chi-square test, and I don't see a way to modify this.

Is there a work around anyone is aware of?

Any pointers appreciated! 

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

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

[Bruce Weaver]

The documentation for CSTABULATE /TEST does lists the following options:

HOMOGENEITY. Test of homogeneous proportions. Available for one-way
frequency tables only.

INDEPENDENCE. Test of independence. Available for two-way crosstabulations
only.

ODDSRATIO. Odds ratio. Available for two-by-two crosstabulations only.

RELRISK. Relative risk. Available for two-by-two crosstabulations only.

RISKDIFF. Risk difference. Available for two-by-two crosstabulations only.

Source:
https://www.ibm.com/support/knowledgecenter/en/SSLVMB_26.0.0/statistics_reference_project_ddita/spss/complex_samples/syn_cstabulate_test.html




Rich Ulrich wrote
> Fisher's Exact Test is for 2x2 tables.  That seems inconsistent with
> your mention of "complex sample."
>
> There are two or three "exact tests" based on permutations and
> different criteria, but all the usual ones are employed on two-way
> tables. That also seems inconsistent with complex samples.
>
> --
> Rich Ulrich





-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
Sent from: http://spssx-discussion.1045642.n5.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

[Jon Peck]

And the Algorithms Doc gives all the details about these testsif you really want to know.

On Wed, Oct 14, 2020 at 4:21 PM Bruce Weaver <[hidden email]> wrote:

The documentation for CSTABULATE /TEST does lists the following options:

HOMOGENEITY. Test of homogeneous proportions. Available for one-way
frequency tables only.

INDEPENDENCE. Test of independence. Available for two-way crosstabulations
only.

ODDSRATIO. Odds ratio. Available for two-by-two crosstabulations only.

RELRISK. Relative risk. Available for two-by-two crosstabulations only.

RISKDIFF. Risk difference. Available for two-by-two crosstabulations only.

Source:
https://www.ibm.com/support/knowledgecenter/en/SSLVMB_26.0.0/statistics_reference_project_ddita/spss/complex_samples/syn_cstabulate_test.html




Rich Ulrich wrote
> Fisher's Exact Test is for 2x2 tables.  That seems inconsistent with
> your mention of "complex sample."
>
> There are two or three "exact tests" based on permutations and
> different criteria, but all the usual ones are employed on two-way
> tables. That also seems inconsistent with complex samples.
>
> --
> Rich Ulrich





-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
Sent from: http://spssx-discussion.1045642.n5.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

--
===================== 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