Re: next version of PSPP

[John Darrington]

Both CORRELATIONS and RELIABILITY are in the version 0.7.x (aka "master"). 
If you want to try it out I suggest that you download a tarball from
http://pspp.benpfaff.org/~blp/

The RELIABILTY command is not complete.  But it does calculate Cronbach's
Alpha which is what most people seem to want it for.

J'


On Fri, Nov 13, 2009 at 09:37:39AM -0600, Alan Mead wrote:
> Jason Stover wrote:
>> I'm not sure about the time frame, but among the new statistical
>> procedures will be GLM. What kinds of analyses do you most need?
>>   
>
> Are correlations available yet?  (Last week, my student just showed me  
> his PSPP installation and "Analyze > Correlations" was not an option.) 
>
> I have taught both statistics and research methods at the undergraduate  
> level and PSPP is completely useless to me until it includes the  
> computation of (simple, Pearson) correlations.  About a year ago, I  
> tried to figure out what the problem was and emails I dug out of the  
> mailing list archives seemed to suggest that the PSPP team was waiting  
> for some background plumbing to make the calculation of correlation  
> matrices efficient.  Efficient would be nice, but while that "right-way"  
> plumbing were being implemented, it sure would be nice to have an  
> inefficient, naive implementation today.  After all, the actual SPSS  
> (i.e., PASW) is getting progressively slower with each version... a  
> naive implementation in PSPP might well be faster than PASW 17.  (This  
> is of such importance to me that I installed GSL to write my own PSPP  
> patch but I got distracted by C and gsl and started writing a program to  
> perform latent semantic analysis.)
>
> I'm honestly shocked that no one else has mentioned correlations in this  
> thread... Is there a build switch that does enable some naive  
> implementation of correlations?  Or they've been implemented and I  
> missed it?  [I've got to be honest, I don't bother installing new  
> versions because until basic descriptive stats are implemented (like the  
> ability to generate the correlation matrix of variables that would be  
> submitted to GLM or Factor) PSPP is simply unusable.]
>
> Also, Reliabilities ('Analyze > Scale > Reliabilities') would also be  
> useful for me.
>
> -Alan
>
>
> -- 
> Alan D. Mead, Ph.D. Assistant Professor, Institute of Psychology
> Scientific Adviser, Center for Research and Service
> Illinois Institute of Technology
> 3101 South Dearborn, 2nd floor
> Chicago IL 60616
>
> Skype: alandmead
> +312.567.5933 (Campus)
> +815.588.3846 (Home Office)
> +312.567.3493 (Fax)
>
> http://mypages.iit.edu/~mead
> http://www.center.iit.edu
> http://www.alanmead.org
>
> I slept and dreamt that life was joy.
> I awoke and saw that life was service.
> I acted and behold, service was joy.
> -- attributed to Rabindranath Tagore 
>

     begin:vcard
     fn:Alan Mead
     n:Mead;Alan
     email;internet:address@hidden
     tel;work:312.567.5933
     tel;home:815.588.3846
     x-mozilla-html:TRUE
     version:2.1
     end:vcard
     

     _______________________________________________
     Pspp-users mailing list
     address@hidden
     http://lists.gnu.org/mailman/listinfo/pspp-users


-- 
PGP Public key ID: 1024D/2DE827B3 
fingerprint = 8797 A26D 0854 2EAB 0285  A290 8A67 719C 2DE8 27B3
See http://pgp.mit.edu or any PGP keyserver for public key.

signature.asc
Description: Digital signature