Pairs data for Lung cancer, Stanford data set (LungStanford).
The original data set has many classes, of which we only used
two.
We compare 41 Adenocarcinomas to 16 Squamous cell carcinomas (SCC).
There were a few missing data values which were set to the
class-dependent average value.
The original data is:
original
The data we use is here: our data
This is a good sized data set, and only 484 pairs and 2 singles
are found.