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: Use of conccord and sdline for Model II Regression


From   michet@rpi.edu
To   statalist@hsphsun2.harvard.edu
Subject   st: Use of conccord and sdline for Model II Regression
Date   Sat, 10 Nov 2012 9:34:16 -0500

Hello Statalisters:

I am beginning an project that requires regression analysis of parameters 
that are measured with error.  Specifically, this project involves
evaluating data from an ecological monitoring program which means that
all the data collected is measured and therefore has associated error.
Based on this it seems appropriate to use a Model II regression analysis.  

I have searched both the help and Statalist files and I cannot find a
built-in Stata routine specific for Model II regressions.  However, I did 
find two user created programs, concord and sdline that may be appropriate:
 
-sdline- a scatter plot and fit line for reduce major axis analysis
 -concord- a user created program that produces the reduced major axis
slope and intercept as depicted below.

. concord so4norm phaireq  (these are just dummy variable for example
purposes only)

Concordance correlation coefficient (Lin, 1989, 2000):

 rho_c   SE(rho_c)   Obs    [   95% CI   ]     P        CI type
---------------------------------------------------------------
 0.009     0.005    1929     0.000  0.019    0.042   asymptotic
                             0.000  0.019    0.042  z-transform

Pearson's r =  0.046  Pr(r = 0) = 0.042  C_b = rho_c/r =  0.205
Reduced major axis:   Slope =     1.179   Intercept =    -3.398

Difference = so4norm - phaireq

        Difference                 95% Limits Of Agreement
   Average     Std Dev.             (Bland & Altman, 1986)
---------------------------------------------------------------
    -2.317       1.159                 -4.588     -0.045

Correlation between difference and mean = 0.163

Bradley-Blackwood F = 3984.600 (P = 0.00000)

My specific question is:

Are the -concord- and -sdline- user created programs which address
reduced major axis analysis, all that is available for Model II
regressions within Stata and if not, what other routines are available
that I did not see in searching the archives?

I am using Stata/IC 11.2 and I run this on the Windows 7 operating system.

Thank you for your consideration of this matter.

Toby Michelena


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


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