Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

Re: st: RE: quick question about -concord-


From   Ricardo Ovaldia <ovaldia@yahoo.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: RE: quick question about -concord-
Date   Fri, 13 Jan 2012 11:07:18 -0800 (PST)

Thank you Nick, and I am sorry that I did not give you and Dr. Steichen credit for this very nice program.

Regards,
Ricardo

Ricardo Ovaldia, MS
Statistician 
Oklahoma City, OK


--- On Fri, 1/13/12, Nick Cox <n.j.cox@durham.ac.uk> wrote:

> From: Nick Cox <n.j.cox@durham.ac.uk>
> Subject: st: RE: quick question about -concord-
> To: "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
> Date: Friday, January 13, 2012, 12:14 PM
> -concord- is a user-written program,
> last updated in SJ 10(4) 2010. Please remember to explain
> where user-written programs you refer to come from. Thomas
> Steichen was the senior author, but he's now retired, so I
> will speak as the young man on the team. 
> 
> You are right: -concord Y X, loa(noref)- plots Y - X vs (Y
> + X)/2. 
> 
> However, your reviewer may not be convinced just by the
> program author's say-so. 
> 
> There are easy demonstrations: 
> 
> sysuse auto
> gen mpgp2 = mpg + 2 
> concord mpg2 mpg, loa 
> 
> On Ricardo's hypothesis, and mine too, this graph should
> show a horizontal line at +2, and it does. 
> 
> However, the default wording on the axis plotting Y - X is
> "Difference of ... and ..." and could fairly be described as
> ambiguous. It was clearly intended to match the default
> wording of "Mean of ... and ...". Perhaps the thought was
> that for some of the likely readership + and - signs were a
> bit too mathematical. 
> 
> From what Ricardo says, I gather that he edited the graph
> away from this default wording, and he got it right. 
> 
> Nick 
> n.j.cox@durham.ac.uk
> 
> 
> Ricardo Ovaldia
> I used the program -concord- to generate Bland-Altman plots
> for a manuscript.
> The reviewer is saying that the differences (plotted on the
> yaxis) are inverted. That is, the title reads Y-X, but it
> really is X-Y.
> 
> My understanding is, and also from manually checking, that
> if I used the command:
> . concord  Y X,  loa(noref)
> 
> The y-axis is Y-X   and not X-Y.
> 
> I just need a confirmation that I am correct.
> 
> 
> *
> *   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/
> 

*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index