Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: Interpretation of the Bland-Altman method on Stata


From   "Seed, Paul" <paul.seed@kcl.ac.uk>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Interpretation of the Bland-Altman method on Stata
Date   Thu, 22 Nov 2012 21:05:09 +0000

Dear Emily, 

-baplot- clearly works with logged values; or at least produces numbers rather than error messages. 
When I said it was not designed for logged values, I meant that the output is not clear, 
and further calculations are needed to make sense of them.

It is clear that you used logs base e, not base 10.  
-baplot- treats the first variable as the new method and the second as the reference; 
so you might want to reverse the order.

The mean difference is based on 
               energy_log_r - energy_log_q
               = log( energypd_r)-  log( energypd_q)
               = log( energypd_r/energypd_q)
So exp(mean difference) =  energypd_r/energypd_q
Simple arithmetic converts this ratio to a % difference:

exp(-0.420) = 0.657
Because you are using logs this is the ratio of the geometric means.
The value using method r is only 66% of that found using method q.
A 34% reduction.  



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