Re: Update

[Alan Mead]

Andy,

The functionality works with subcommand option "CLUSTER" it's just reported incorrectly in the manual. This is my test script:

QUICK CLUSTER x y
  /CRITERIA=CLUSTERS(2)
  /PRINT=INITIAL CLUSTER.

I imagine the manual will be fixed in an upcoming release but I don't know when that will be.

Also, it might be worth noting that the only way to generate the syntax above is to choose Analyze > K-Means Cluster > ... and then to paste the syntax and add the PRINT subcommand manually.  That is, you can generate this from the dialog:

QUICK CLUSTER  x y
    /CRITERIA=CLUSTERS(2).

You need to put your cursor before the ending period and add the PRINT subcommand:

QUICK CLUSTER  x y
    /CRITERIA=CLUSTERS(2)
    /PRINT=CLUSTER.

I don't know how hard the GUI (PSPPIRE) code is to modify, but I'd like to take a look at configuring the PRINT subcommand in the dialog someday when I have a Linux machine that supports it (my Centos 6.x machine does not).

-Alan

On 12/16/2015 6:33 PM, Andy King wrote:

Thanks very much Alan - this is great news and hugely appreciated.

I am not yet super proficient with PSPP but I will have a look at this very soon and try to run it on my dataset - I may come back to you (if you don't mind) for a little guidance if I have trouble finding the right commands.

Please let me know if this patch gets added - do I need to wait for this before trailing this function?

Andy

-- 

Alan D. Mead, Ph.D.
President, Talent Algorithms Inc.

science + technology = better workers

+815.588.3846 (Office)
+267.334.4143 (Mobile)

http://www.alanmead.org

Announcing the Journal of Computerized Adaptive Testing (JCAT), a
peer-reviewed electronic journal designed to advance the science and
practice of computerized adaptive testing: http://www.iacat.org/jcat