This data file consists of six simulated predictors or variables with three class categories. For each class category the values are independently generated from the normal distribution with the mean µ1, µ2 and µ3 and the variances held at unity. The means are varied such that the problems range from near-separable problems, to near-random.
The data set corresponds to absolute (cells/mm2) or relative (percentage of the cell type in question of the entire inflammatory cell population) densities of 5 major inflammatory cell types in synovial tissue specimens from normal human joints (âNormalâ) and from patients with osteoarthritis (âOAâ), non-inflammatory orthopedic arthropathies (âOrth.Aâ), early unclassified arthritis (âEAâ), rheumatoid arthritis (âRAâ), and chronic septic arthritis (âSeAâ). An analysis of this data set with binary and multicategory ROC analysis has been published in Della Beffa PLOS One 2013, which also contains additional details about the data set. The dataset consists of 92 cases with 11 features and disease code.
providing 
.