Hi,
I think "spearman" is the right command:
. spearman x y
Number of obs = 100
Spearman's rho = 0.6155
Test of Ho: x and y are independent
Prob > |t| = 0.0000
You get the correlation coefficient with r(rho) if you want to process it
further.
. ret list
scalars:
r(N) = 100
r(rho) = .6154575457545756
r(p) = 9.50421231184e-12
Peter
Am Sonntag, 4. März 2007 12:03 schrieb Vanessa Mahlberg:
> Hallo,
>
> I?ve got a (maybe very simple) question:
>
> I would like to calculate the split-half reliability (Spearman/Brown)
> for a whole scala (including 14 items).If I use the spearman?s rank
> correlation I always get a kind of intercorrelation matrix...but I just
> want to have a single value that the Spearman Brown reliability for my
> whole is e.g. .95. (I want to compare this value with the one given by
> theoretical litterature).
>
> It would be very kind if somebody could give me some advice concerning
> the right stata command.
>
> Thanks and a nice weekend
> Vanessa
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
--
Peter Parzer
Universitätsklinikum Heidelberg
Zentrum für Psychosoziale Medizin
Klinik für Kinder- und Jugendpsychiatrie
Blumenstraße 8, D-69115 Heidelberg
Tel. +49-6221-566938, Fax. +49-6221-566941
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
