Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: R: Spearman's rank correlation coefficient - power calculation


From   "Carlo Lazzaro" <carlo.lazzaro@tin.it>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: R: Spearman's rank correlation coefficient - power calculation
Date   Thu, 19 Jun 2008 09:19:25 +0200

Dear Theo,
the following one is a temptative answer to your message.

I assume I have 20 observations ordered in ranks (degrees of freedom (d_f) are 20-20=18, according to the hypothesis test formula for Spearman's rank correlation coefficient).
Ho to be tested is rho=0.
I have calculated a random Spearman's ranK correlation coefficient, t (ts) and then the p-value.
....................begin example......................
set obs 1
g r_Spearman=1*uniform()
g d_f=(20-2)
g ts= r_Spearman*[(20-2)/(1-(-r_Spearman^2))]^.5
g p_value=ttail(d_f, ts)
...................end example.......................

HTH and Kind Regards,

Carlo
-----Messaggio originale-----
Da: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] Per conto di Theo Serge
Inviato: giovedì 19 giugno 2008 8.24
A: statalist@hsphsun2.harvard.edu
Oggetto: st: Spearman's rank correlation coefficient - power calculation

Dear Statalist, 

I would be grateful if you could help me on a problem:

Having submitted an article to a Journal, the reviewers asked me for power calculation on a Spearmanʼs rank correlation coefficient.

This happened although I had been very careful with the interpretation of negative findings in the manuscript. Moreover, Spearmanʼs rank correlation coefficient was the appropriate choice for the univariate analysis performed, due to a variety of underlying factors.

To my knowledge, there is no command through which STATA can perform power calculations on Spearmanʼs rank correlation coefficients.

Please inform me if there is a way to overcome this difficulty. Are there any commands I am not familiar with? Would programming STATA be of value? 

What would be the optimal approach to this issue? The need for power calculations in Spearman's rank correlation coefficients seems justified.

I thank you in advance.

T.S.
University of Athens, Greece






      
___________________________________________________________ 
Χρησιμοποιείτε Yahoo!; 
Βαρεθήκατε τα ενοχλητικά μηνύματα (spam); Το Yahoo! Mail 
διαθέτει την καλύτερη δυνατή προστασία κατά των ενοχλητικών 
μηνυμάτων http://login.yahoo.com/config/mail?.intl=gr 


*
*   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/



*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index