ROSALI-SIM/Modules/ado/plus/c/concord.hlp

{smcl}
{* 6oct2004/23aug2005/14may2006/9aug2007}
{hline}
{hi:help concord} {right:(SJ7-3: st0015_4)}
{hline}

{title:Title}

{p2colset 5 16 18 2}{...}
{p2col:{hi:concord} {hline 2}}Concordance correlation coefficient and associated measures, tests, and graphs{p_end}
{p2colreset}{...}


{title:Syntax}

{p 8 17 2}
{cmd:concord}
{it:vary} {it:varx}
{ifin}
{weight}
[{cmd:,}
{cmd:by(}{it:byvar}{cmd:)}
{cmdab:s:ummary}
{cmdab:le:vel(}{it:#}{cmd:)}
{cmd:ccc}[{cmd:(noref} {it:ccc_options}{cmd:)}]
{cmd:loa}[{cmd:(noref} {cmdab:reg:line} {it:loa_options}{cmd:)}]
{cmd:qnormd}[{cmd:(}{it:qnormd_options}{cmd:)}]]


{title:Description}

{p 4 4 2}
{cmd:concord} computes Lin's (1989, 2000) concordance correlation coefficient
for agreement on a continuous measure obtained by two persons or methods. (The
measure was introduced earlier by Krippendorff (1970).) The concordance
correlation coefficient combines measures of both precision and accuracy to
determine how far the observed data deviate from the line of perfect
concordance (i.e., the line at 45 degrees on a square scatter plot). Lin's
coefficient increases in value as a function of the nearness of the data's
reduced major axis to the line of perfect concordance (the accuracy of the
data) and of the tightness of the data about its reduced major axis (the
precision of the data).  The Pearson correlation coefficient, r, the
bias-correction factor, C_b, and the equation of the reduced major axis are
reported to show these components.  Note that the concordance correlation
coefficient, rho_c, can be expressed as the product of r, the measure of
precision, and C_b, the measure of accuracy.

{p 4 4 2}
{cmd:concord} also provides results for Bland and Altman's
limits-of-agreement, "loa", procedure (1986). The loa, a data-scale assessment
of the degree of agreement, is a complementary approach to the
relationship-scale approach of Lin.

{p 4 4 2}
Finally, two other results are reported:

{p 8 8 2}
1. The correlation between difference and mean. In one interpretation
this is a test statistic for a null hypothesis of equal variances given
bivariate normality (Pitman 1939; also see Snedecor and Cochran 1989, 192-193).
Alternatively, it is an exploratory diagnostic.
A value near zero implies concordance.

{p 8 8 2}
2. An F test of equality of means and variances. Note that this too
assumes bivariate normality (Bradley and Blackwood 1989).
See also Hsu (1940) and Reynolds and Gregoire (1991).
Nonsignificance implies concordance.

{p 4 4 2}
The user provides the pairs of measurements for a single property as
observations in variables {it:vary} and {it:varx}.  Frequency weights may be
specified and used. Missing values (if any) are deleted in a casewise manner.

{p 4 4 2}
Various associated graphs may be obtained through options.
See below for explanations of the options {cmd:ccc}, {cmd:loa}, and 
{cmd:qnormd}.


{title:Options}

{p 4 8 2}
{cmd:by(}{it:byvar}{cmd:)} produces separate results for groups of
observations defined by {it:byvar}.

{p 4 8 2}
{cmd:summary} requests summary statistics.

{p 4 8 2}
{cmd:level(}{it:#}{cmd:)} sets the confidence level % for the CI; default is
{cmd:c(level)}.

{p 4 8 2}
{cmd:ccc} requests a graphical display of the data and the reduced major axis
of the data. The reduced major axis or SD line goes through the intersection of
the means and has slope given by the sign of Pearson's r and the ratio of the
standard deviations. The SD line serves as a summary of the center of the data.

{p 8 8 2}
{cmd:ccc()} suboption {cmd:noref} suppresses the reference line of
perfect concordance, y=x.

{p 8 8 2}
{cmd:ccc()} may also be specified with other options, which should
be options of {helpb scatter}. For example, the scheme may be changed by a
call such as {cmd:ccc(scheme(lean1)}.

{p 4 8 2}
{cmd:loa} requests a graphical display of the loa, the mean difference, and
the data presented as paired differences plotted against pair-wise means.

{p 8 8 2}
{cmd:loa()} suboption {cmd:noref} suppresses the reference line of perfect
average agreement, y=0.

{p 8 8 2}
{cmd:loa()} suboption {cmd:regline} adds a regression line to the loa plot
fitting the paired differences to the pair-wise means.

{p 8 8 2}
{cmd:loa()} may also be specified with other options, which should normally
be options of {helpb scatter}.  For example,
the reference line of perfect average agreement was generated as
{cmd:loa(yline(0, lstyle(refline)) yscale(range(0)) ylabel(0, add))}.

{p 4 8 2}
{cmd:qnormd} requests a normal plot of differences.

{p 8 8 2}
{cmd:qnormd()} may also be specified with options, which should
be options of {helpb scatter}. For example,
{cmd:qnormd(title(Normal plot of differences))} adds a title to the graph.


{title:Comments}

{p 4 4 2}
Lin (2000) reported typographical errors in his original 1989 paper
that affected calculation of the standard error of rho_c. These corrections
were included in {cmd:concord} in version 2.2.7 (January 2002) when the erratum
was brought to the attention of the program authors by Dr. Benjamin Littenberg.
We thank Dr. Littenberg.

{p 4 4 2}Kevan Polkinghorne pointed out a problem with {cmd:loa()}. 
Mark Marshall pointed out a problem with {cmd:by()} under Stata 9. 

{p 4 4 2}
Dunn (2004) contains a bibliography on related work.
Cox (2004) discusses other graphical approaches to this and related
problems. Cox (2006) discusses concordance correlation and 
other numerical and graphical methods for assessing agreement
with various scientific examples. 


{title:Saved results}

{p 4 4 2}
The following items are returned in {cmd:r()}, if the {cmd:by()} option was
not used:

{p 8 18}{cmd:r(N)}{space 9}number of observations compared{p_end}
{p 8 18}{cmd:r(rho_c)}{space 5}concordance correlation coefficient rho_c{p_end}
{p 8 18}{cmd:r(se_rho_c)}{space 2}standard error of rho_c{p_end}
{p 8 18}{cmd:r(asym_ll)}{space 3}lower CI limit (asymptotic){p_end}
{p 8 18}{cmd:r(asym_ul)}{space 3}upper CI limit (asymptotic){p_end}
{p 8 18}{cmd:r(z_tr_ll)}{space 3}lower CI limit (z-transform){p_end}
{p 8 18}{cmd:r(z_tr_ul)}{space 3}upper CI limit (z-transform){p_end}
{p 8 18}{cmd:r(C_b)}{space 7}bias-correction factor C_b{p_end}
{p 8 18}{cmd:r(diff)}{space 6}mean difference{p_end}
{p 8 18}{cmd:r(sd_diff)}{space 3}standard deviation of mean difference{p_end}
{p 8 18}{cmd:r(LOA_ll)}{space 4}lower loa CI limit{p_end}
{p 8 18}{cmd:r(LOA_ul)}{space 4}upper loa CI limit{p_end}
{p 8 18}{cmd:r(rdm)}{space 7}correlation between difference and mean{p_end}
{p 8 18}{cmd:r(Fdm)}{space 7}F from Bradley-Blackwood test{p_end}


{title:Examples}

{p 4 8 2}
{cmd:. concord rater1 rater2}

{p 4 8 2}
{cmd:. concord rater1 rater2 [fw=freq]}

{p 4 8 2}
{cmd:. concord rater1 rater2, summary ccc}

{p 4 8 2}
{cmd:. concord rater1 rater2, summary ccc(noref)}

{p 4 8 2}
{cmd:. concord rater1 rater2, level(90) by(grp)}

{p 4 8 2}
{cmd:. concord rater1 rater2, loa(regline noref)}

{p 4 8 2}
{cmd:. concord rater1 rater2, qnormd(title(Normal plot))}


{title:Authors}

{p 4 4 2}
Thomas J. Steichen, Winston-Salem, NC, USA, steichen@triad.rr.com

{p 4 4 2}
Nicholas J. Cox, Durham University, UK, n.j.cox@durham.ac.uk


{title:References}

{p 4 8 2}
Bland, J. M., and D. G. Altman.  1986. Statistical methods for assessing
agreement between two methods of clinical measurement. {it:Lancet} I:
307{c -}310.

{p 4 8 2}
Bradley, E. L., and L. G. Blackwood. 1989. Comparing paired data:
a simultaneous test for means and variances. {it:American Statistician}
43: 234{c -}235.

{p 4 8 2}
Cox, N. J. 2004. Graphing agreement and disagreement.
{it:Stata Journal} 4: 329{c -}349.

{p 4 8 2}
------. 2006. 
Assessing agreement of measurements and predictions in geomorphology. 
{it:Geomorphology} 76: 332{c -}346. 

{p 4 8 2}
Dunn, G. 2004.
{it: Statistical Evaluation of Measurement Errors: Design and Analysis of Reliability Studies.}
London: Arnold.

{p 4 8 2}
Hsu, C. T. 1940. On samples from a normal bivariate population.
{it:Annals of Mathematical Statistics} 11: 410{c -}426.

{p 4 8 2}
Krippendorff, K. 1970. Bivariate agreement coefficients for reliability of data.
In Borgatta, E.F. and G.W. Bohrnstedt (eds)
{it:Sociological Methodology}. San Francisco: Jossey-Bass, 139{c -}150.
[a.k.a. {it:Sociological Methodology} 2: 139{c -}150]

{p 4 8 2}
Lin, L. I-K. 1989. A concordance correlation coefficient to evaluate
reproducibility. {it:Biometrics} 45: 255{c -}268.

{p 4 8 2}
------. 2000. A note on the concordance correlation coefficient.
{it:Biometrics} 56: 324{c -}325.

{p 4 8 2}
Pitman, E. J. G. 1939. A note on normal correlation.
{it:Biometrika} 31: 9{c -}12.

{p 4 8 2}
Reynolds, M., and T. G. Gregoire. 1991. Comment on Bradley and Blackwood.
{it:American Statistician} 45: 163{c -}164.

{p 4 8 2}
Snedecor, G. W., and W. G. Cochran. 1989. {it:Statistical Methods.}
Ames, IA: Iowa State University Press.


{title:Also see}

{p 4 13 2}
STB:  STB-43 sg84; STB-45 sg84.1; STB-54 sg84.2; STB-58 sg84.3

{psee}
SJ:{space 3}SJ2-2 st0015; SJ4-4 st0015_1; SJ5-3: st0015_2; SJ6-2: st0015_3
{p_end}