KRUSKALL WALLIS TEST IN SPSS

[Oscar M]

I notice that when using this test in SPSS, it will only allow scale variables
in the test field. Why is ordinal not 'good enough' as far as SPSS is
concerned - reading says that ordinal is acceptable with KW (i.e. does not
need to be interval / scale)? Any thoughts appreciated.

=====================
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]

That was a mistake and was fixed in Statistics 22.  You can temporarily change the measurement level to do this in test in V21 or use the NPAR TESTS with the K-W keyword.


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




From:        Mike ODriscoll <[hidden email]>
To:        [hidden email],
Date:        11/24/2013 07:16 AM
Subject:        [SPSSX-L] KRUSKALL WALLIS TEST IN SPSS
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

I notice that when using this test in SPSS, it will only allow scale variables
in the test field. Why is ordinal not 'good enough' as far as SPSS is
concerned - reading says that ordinal is acceptable with KW (i.e. does not
need to be interval / scale)? Any thoughts appreciated.

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

[Oscar M]

Interesting! Thanks a lot. So I am using V20 and I can change to scale variable in order to do the test.

 

could you give a bit more info please on ''NPAR TESTS with the K-W keyword''. do you mean using syntax - if so could you give a short example of this syntax?

 

Very impressed by level of knowledge in this group!

 

 

Thanks

On 24 November 2013 19:49, Jon K Peck <[hidden email]> wrote:

That was a mistake and was fixed in Statistics 22.  You can temporarily change the measurement level to do this in test in V21 or use the NPAR TESTS with the K-W keyword.


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




From:        Mike ODriscoll <[hidden email]>
To:        [hidden email],
Date:        11/24/2013 07:16 AM
Subject:        [SPSSX-L] KRUSKALL WALLIS TEST IN SPSS
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

I notice that when using this test in SPSS, it will only allow scale variables
in the test field. Why is ordinal not 'good enough' as far as SPSS is
concerned - reading says that ordinal is acceptable with KW (i.e. does not
need to be interval / scale)? Any thoughts appreciated.

=====================
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]

http://pic.dhe.ibm.com/infocenter/spssstat/v20r0m0/index.jsp?topic=%2Fcom.ibm.spss.statistics.help%2Fsyn_npar_tests_overview.htm

For the GUI, Analyze > Nonparametric Tests > Legacy Dialogs

Oscar M wrote

Interesting! Thanks a lot. So I am using V20 and I can change to scale
variable in order to do the test.

could you give a bit more info please on ''NPAR TESTS with the K-W
keyword''. do you mean using syntax - if so could you give a short example
of this syntax?

Very impressed by level of knowledge in this group!


Thanks



On 24 November 2013 19:49, Jon K Peck <[hidden email]> wrote:

> That was a mistake and was fixed in Statistics 22.  You can temporarily
> change the measurement level to do this in test in V21 or use the NPAR
> TESTS with the K-W keyword.
>
>
> Jon Peck (no "h") aka Kim
> Senior Software Engineer, IBM
> [hidden email]
> phone: [phone]
>
>
>
>
> From:        Mike ODriscoll <[hidden email]>
> To:        [hidden email],
> Date:        11/24/2013 07:16 AM
> Subject:        [SPSSX-L] KRUSKALL WALLIS TEST IN SPSS
> Sent by:        "SPSSX(r) Discussion" <[hidden email]>
> ------------------------------
>
>
>
> I notice that when using this test in SPSS, it will only allow scale
> variables
> in the test field. Why is ordinal not 'good enough' as far as SPSS is
> concerned - reading says that ordinal is acceptable with KW (i.e. does not
> need to be interval / scale)? Any thoughts appreciated.
>
> =====================
> 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]

You can do this in syntax using NPAR TESTS, e.g.,
NPAR TESTS /K-W=salary by group(0 1)
or you can find it in the dialog boxes by using
Analyze > Nonparametric Tests > Legacy Dialogs > k Independent Samples.
The Legacy Dialogs level is not present in older versions of Statistics.

Using the newer Analyze > Nonparametric Tests > Independent Samples (changing the measurement level if necessary) gives the same test results for K-W, but it includes some useful plots and other information.

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




From:        "mike O'Driscoll" <[hidden email]>
To:        Jon K Peck/Chicago/IBM@IBMUS,
Cc:        "SPSSX(r) Discussion" <[hidden email]>
Date:        11/25/2013 05:56 AM
Subject:        Re: [SPSSX-L] KRUSKALL WALLIS TEST IN SPSS

---

Interesting! Thanks a lot. So I am using V20 and I can change to scale variable in order to do the test.
 
could you give a bit more info please on ''NPAR TESTS with the K-W keyword''. do you mean using syntax - if so could you give a short example of this syntax?
 
Very impressed by level of knowledge in this group!
 
 
Thanks



On 24 November 2013 19:49, Jon K Peck <peck@...> wrote:
That was a mistake and was fixed in Statistics 22.  You can temporarily change the measurement level to do this in test in V21 or use the NPAR TESTS with the K-W keyword.


Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
peck@...
phone: [phone]




From:        Mike ODriscoll <odriscollfm@...>
To:        [hidden email],
Date:        11/24/2013 07:16 AM
Subject:        [SPSSX-L] KRUSKALL WALLIS TEST IN SPSS
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

I notice that when using this test in SPSS, it will only allow scale variables
in the test field. Why is ordinal not 'good enough' as far as SPSS is
concerned - reading says that ordinal is acceptable with KW (i.e. does not
need to be interval / scale)? Any thoughts appreciated.

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

[Art Kendall]

Bruce forgot to mention that you should exit the GUI via <paste> when you have the specifications you want.
On 11/25/2013 8:23 AM, Bruce Weaver [via SPSSX Discussion] wrote:

http://pic.dhe.ibm.com/infocenter/spssstat/v20r0m0/index.jsp?topic=%2Fcom.ibm.spss.statistics.help%2Fsyn_npar_tests_overview.htm

For the GUI, Analyze > Nonparametric Tests > Legacy Dialogs

Oscar M wrote

Interesting! Thanks a lot. So I am using V20 and I can change to scale
variable in order to do the test.

could you give a bit more info please on ''NPAR TESTS with the K-W
keyword''. do you mean using syntax - if so could you give a short example
of this syntax?

Very impressed by level of knowledge in this group!


Thanks



On 24 November 2013 19:49, Jon K Peck <[hidden email]> wrote:

> That was a mistake and was fixed in Statistics 22.  You can temporarily
> change the measurement level to do this in test in V21 or use the NPAR
> TESTS with the K-W keyword.
>
>
> Jon Peck (no "h") aka Kim
> Senior Software Engineer, IBM
> [hidden email]
> phone: [phone]
>
>
>
>
> From:        Mike ODriscoll <[hidden email]>
> To:        [hidden email],
> Date:        11/24/2013 07:16 AM
> Subject:        [SPSSX-L] KRUSKALL WALLIS TEST IN SPSS
> Sent by:        "SPSSX(r) Discussion" <[hidden email]>
> ------------------------------
>
>
>
> I notice that when using this test in SPSS, it will only allow scale
> variables
> in the test field. Why is ordinal not 'good enough' as far as SPSS is
> concerned - reading says that ordinal is acceptable with KW (i.e. does not
> need to be interval / scale)? Any thoughts appreciated.
>
> =====================
> 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
>
>
>

---

If you reply to this email, your message will be added to the discussion below:

http://spssx-discussion.1045642.n5.nabble.com/KRUSKALL-WALLIS-TEST-IN-SPSS-tp5723280p5723287.html

To start a new topic under SPSSX Discussion, email [hidden email]
To unsubscribe from SPSSX Discussion, click here.
NAML