Hi all,
In our Bland Altman plots, we found a proportional bias between two nonuniform differences. Bland and Altman explained how to change it in their paper but I was wondering if anyone knows how to do this kind of calculation in Excel, SPSS or MedCalc?
Thanks in advance.
Not sure what your question is, but there only three simple calculations:
the logarithm, the average, and the difference.
In Excel these are LOG(), MEAN() and "-",
e.g. log(A1), MEAN(A1;A2), A2-A1
Dear Elif,
if you dare to use a different statistical software solution ("R"), you would find the "mcr" package most convenient, providing a function called "MCResult.plotDifference", that can be parametrized ("plot.type") as follows:
"Integer specifying a specific Bland-Altman plot modification (default is 3). Possible choices are:
1 - difference plot X vs. Y-X with null-line and mean plus confidence intervals.
2 - difference plot X vs. (Y-X)/X (relative differences) with null-line and mean.
3 - difference plot 0.5*(X+Y) vs. Y-X with null-line and mean plus confidence intervals.
4 - difference plot 0.5*(X+Y) vs. (Y-X)/X (relative differences) with null-line.
5 - difference plot rank(X) vs. Y-X with null-line and mean plus confidence intervals.
6 - difference plot rank(X) vs. (Y-X)/X (relative differences) with null-line and mean.
7 - difference plot sqrt(X*Y) vs. Y/X with null-line and mean plus confidence intervals calculated with help of log-transformation.
8 - difference plot 0.5*(X+Y) vs. (Y-X) / (0.5*(X+Y)) with null-line."
You will find the package and its documentation here:
https://cran.r-project.org/web/packages/mcr/index.html
Dear Elif İnan-Eroğlu wondering if you figured out how to do this in SPSS? Assuming you're trying to create something similar to Figure 8 in attached PDF?
Hi Elif İnan-Eroğlu, a few lines of Python can solve this. If you still need to solve, I can help you next week.
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS