Re: st: RE: correlated data

[David Airey <david.airey@vanderbilt.edu>]

.

I like this cogent article on methods comparison. You'll find sections  
in it describing why paired t-tests and Pearson correlation  
coefficients are not so good for methods comparison statistics.

<http://biopharminternational.findpharma.com/biopharm/data/articlestandard/biopharm/032002/7276/article.pdf 
>

-Dave


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/