SPSS 16.0.0 error: Two step cluster: Options

[MahaMil]

Hi,
I am new to SPSS and I am performing a two-step clustering on some continuous data.  A strange error message is popping up when I open menu Analyze>>Classify>>TwoStepCluster>>Options.  I need to enable "Outlier treatment" on the Options menu.  However, when enabling it, and click continue, I get an error message:  "The file named 'C:\Documents and Settings\'myusername'\My Documents\' does not exist. Please enter a valid file name".  I cannot see anywhere to enter a valid file name.  Can anyone help?
Thanks & Regards,

[E. Bernardo]

I used chisquare to test the null hypothesis that the two ordinal variables with 4 categories each are uncorrelated.  The chisquare is non-significant (p>.05).  The gamma coefficient is .341 and highly significant (p<.05).  Why gamma is significant while chisquare is insignificant.  I confused about this.  I appreciate any comments.

 

Thank you.

Eins

[Julius Sim]

Hello,

If by chi-square you mean the Pearson chi-square, this test is designed
for nominal variables and takes no account of the ordinal ranking of the
categories in the variables, whereas gamma is a symmetric measure of
association for ordinal variables. Hence you are liable to get
contradictory conclusions regarding the null hypothesis of no association.
You need to use the chi-square test for trend (linear by linear
association in SPSS) to test for association in two ordinal variables.

Best wishes,

Julius

> I used chisquare to test the null hypothesis that the two ordinal
> variables with 4 categories each are uncorrelated.  The chisquare is
> non-significant (p>.05).  The gamma coefficient is .341 and highly
> significant (p<.05).  Why gamma is significant while chisquare is
> insignificant.  I confused about this.  I appreciate any comments.
>
> Thank you.
> Eins
>
>

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

[Henrik Lolle-2]

If the association is monotone, then Gamma is a more powerful test than
a chisquare test. But it sounds a bit strange that the value of Gamma
is .34 and is highly statistical significant when the p-value from the
chisquare test is above .05. How many cases do you have in your table?

Best,
Henrik

Quoting Eins Bernardo <[hidden email]>:

> I used chisquare to test the null hypothesis that the two ordinal
> variables with 4 categories each are uncorrelated.  The chisquare is
> non-significant (p>.05).  The gamma coefficient is .341 and highly
> significant (p<.05).  Why gamma is significant while chisquare is
> insignificant.  I confused about this.  I appreciate any comments.
>
> Thank you.
> Eins
>
>

************************************************************
Henrik Lolle
Department of Economics, Politics and Public Administration
Aalborg University
Fibigerstraede 1
9220 Aalborg
Phone: [phone]
************************************************************

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

[Sarraf, Shimon Aaron]

I will be out of the office until Friday, Jan. 28th. If you need immediate assistance, please call 812-856-5824. I will respond to your e-mail as soon as possible.

 

Thank you,

Shimon Sarraf

Center for Postsecondary Research

Indiana University at Bloomington

 

[E. Bernardo]

Thank you so much for your comment, Henrik.  The sample size is n = 77.

Kindly elaborate "the association is monotone"?

--- On Mon, 1/24/11, Henrik Lolle <[hidden email]> wrote:

From: Henrik Lolle <[hidden email]>
Subject: Re: Chisquare and gamma coefficient
To: "Eins Bernardo" <[hidden email]>
Cc: [hidden email]
Date: Monday, 24 January, 2011, 12:10 PM

If the association is monotone, then Gamma is a more powerful test than
a chisquare test. But it sounds a bit strange that the value of Gamma
is .34 and is highly statistical significant when the p-value from the
chisquare test is above .05. How many cases do you have in your table?

Best,
Henrik

Quoting Eins Bernardo <einsbernardo@...>:

> I used chisquare to test the null hypothesis that the two ordinal
> variables with 4 categories each are uncorrelated.  The chisquare is
> non-significant (p>.05).  The gamma coefficient is .341 and highly
> significant (p<.05).  Why gamma is significant while chisquare is
> insignificant.  I confused about this.  I appreciate any comments.
>  
> Thank you.
> Eins
>
>

************************************************************
Henrik Lolle
Department of Economics, Politics and Public Administration
Aalborg University
Fibigerstraede 1
9220 Aalborg
Phone: [phone]
************************************************************

[lucameyer]

If you sample size is 77 and you have 8 cells in your table you might get an unstable result. SPSS CTABLES should print the following warning:  "More than 20% of cells in this subtable have expected cell counts less than 5. Chi-square results may be invalid." similar warning should be printed by FREQUENCIES

As an alternative you should into NPAR TESTS.

HTH,
Luca

Luca Meyer
www.lucameyer.com

[lucameyer]

I have tried to replicate your error on v19 but I did not get it, could it be an installation problem of your version? It looks like the software is referring to a not customized path...Unfortunately I do not have any longer v16 to try it on....

Luca

Luca Meyer
www.lucameyer.com

[E. Bernardo]

What about exact test in SPSS?

--- On Wed, 1/26/11, lucameyer <[hidden email]> wrote:

From: lucameyer <[hidden email]>
Subject: Re: Chisquare and gamma coefficient
To: [hidden email]
Date: Wednesday, 26 January, 2011, 8:12 AM

If you sample size is 77 and you have 8 cells in your table you might get an
unstable result. SPSS CTABLES should print the following warning:  "More
than 20% of cells in this subtable have expected cell counts less than 5.
Chi-square results may be invalid." similar warning should be printed by
FREQUENCIES

As an alternative you should into NPAR TESTS.

HTH,
Luca

Luca Meyer
www.lucameyer.com


--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/SPSS-16-0-0-error-Two-step-cluster-Options-tp3353123p3357519.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

[Art Kendall]

Are you sure that the file with exactly that name exists? 
Did you paste the syntax from your earlier steps?
Where did you specify the file?

Art Kendall
Social Research Consultants

On 1/22/2011 2:34 PM, MahaMil wrote:

Hi,
I am new to SPSS and I am performing a two-step clustering on some
continuous data.  A strange error message is popping up when I open menu
Analyze>>Classify>>TwoStepCluster>>Options.  I need to enable "Outlier
treatment" on the Options menu.  However, when enabling it, and click
continue, I get an error message:  "The file named 'C:\Documents and
Settings\'myusername'\My Documents\' does not exist. Please enter a valid
file name".  I cannot see anywhere to enter a valid file name.  Can anyone
help?
Thanks & Regards,
http://spssx-discussion.1045642.n5.nabble.com/file/n3353123/untitled.bmp



--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/SPSS-16-0-0-error-Two-step-cluster-Options-tp3353123p3353123.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

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