I had no intention of deprecating the contribution
of Bland and Altman. I agree with the assessment here.
I just wanted to put that contribution in historical
and logical context.
I still think that Bland-Altman plot is a poor name,
especially for interdisciplinary communication.
That said, I am not a medical statistician, but
evidently it is very well understood in medical
statistics, so that there is no practical point in
questioning the terminology in that field, even if
I were an insider. It would not be polite in any
case.
Ron�n here refers to "their paper", but there are
several. Here are some:
Altman, D.G. and J.M. Bland. 1983. Measurement in medicine: the analysis
of method comparison studies. The Statistician 32: 307--317.
Bland, J.M. and D.G. Altman. 1986. Statistical methods for assessing
agreement between two methods of clinical measurement. The
Lancet i: 307--310.
1995a. Comparing two methods of clinical measurement: a personal
history. International Journal of Epidemiology 24: S7--S14.
1995b. Comparing methods of measurement: why plotting difference against
standard method is misleading. The Lancet 346: 1085--1087.
1999. Measuring agreement in method comparison studies. Statistical
Methods in Medical Research 8: 135--160.
Nick
[email protected]
Ron�n Conroy
> On 6 Noll 2005, at 23:15, Nick Cox wrote:
>
> > As Bland and Altman have pushed the idea very
> > hard in their medical statistics texts and in several
> > papers in medical/medical statistical journals, the
> > terminology Bland-Altman plots seems to have become
> > widely used in those areas. (As usual, I would be
> > astonished if either had invented that term.)
>
> For a number of years, these plots didn't have a name (and still
> don't have any other widely recognised name). I would be curious to
> see what is the earliest published reference to them.
> Certainly, if B
> & A are at fault, it is in not giving their plot a catchy name.
>
> The importance of Bland and Altman's paper was that it discussed and
> dismissed several intuitively reasonable ways of assessing agreement
> between two measures, neither of which is a gold standard. The paper
> is a model of clarity and sense. Its influence was considerable in
> the medical literature, improving analysis and reporting very
> significantly.
>
> For that reason, I have no trouble crediting them. They may not have
> invented the plot (and didn't claim to do so) but they championed it
> as part of good practice and in doing so did a considerable service
> to the quality of published reports.
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
