[R] I have a question on nomograms.

Gabor Grothendieck ggrothendieck at gmail.com
Fri Mar 26 03:54:03 CET 2010


On Thu, Mar 25, 2010 at 10:43 PM, Frank E Harrell Jr
<f.harrell at vanderbilt.edu> wrote:
> (Ted Harding) wrote:
>>
>>  http://www.nomogram.org
>>
>> They call this sort of interface "nomogram" too, and you can have
>> a go at the one they offer for bladder cancer. This is not a
>> graphical nomogram in the sense that you describe, rather it is
>> a form-filling interface with boxes into which you insert
>> information, and then press the button.
>
> It is very curious that a site named nomogram.org would not contain a single
> nomogram.  I have pointed this out to the author of the site, who maintains
> that disagreements with dictionaries are inconsequential.
>

It is strange although I think that in certain areas of medicine its
common to use the term nomogram to mean the model underlying the
nomogram as opposed to its graphical representation.

For example, in the following discussion the authors seem to be using
nomogram  merely to denote any model that does not involve forming
discrete levels of the inputs in the way that forming risk groups
(high risk group, low risk group, etc.) would:

http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2777059/



More information about the R-help mailing list