Dear Allstaters,
a reviewer commented about a manuscript I am writing a revision for,
that s/he wanted to see
"graphs of the actual correlations between" alcohol consumption and
lab-markers "with their respective r-values, p-values and number of
subjects per correlation"
instead of scatter plots. Scatter plots were given for male subjects
that had self-reported alcohol consumption > 0:
X axis: log(alcohol consumption),
Y-axis: log(lab-marker).
The logs were taken, because the distribution has very long right
tails.
Can anybody imagine what kind of graph the reviewer is expecting?
Thanks for any hints.
--
-----------------------------------------------------------------
Dietrich Alte (Statistician, Dipl.-Stat.)
University of Greifswald - Medical Faculty
Institute of Epidemiology and Social Medicine
Walther-Rathenau-Str. 48, D-17487 Greifswald, Germany
Phone +49 (0) 3834 - 86 77 13, fax +49 (0) 3834 - 86 66 84
Email [log in to unmask]
Institute http://www.medizin.uni-greifswald.de/epidem/
Study http://www.medizin.uni-greifswald.de/epidem/ship.htm
-----------------------------------------------------------------
|