Description

This data set contains five related simulated data sets, along with the Thresher and Reaper objects obtained by clustering the data sets and removing outliers.

Usage

Format

1. sigma: A list of length five; each entry is a covariance matrix used to simulate data.

2. savedSims: A list of length five; each entry is a SimThresher object obtained by simulating data from one of the covariance matrices and running the Thresher algorithm.

3. savedReap: A list of length five; each entry is a Reaper object obtained by applying the Reaper function.

Source

The simulated data sets were prepared by running the script Examples/makeSims.R that is installed along with the Thresher package. The five covariance matrices vary in the number of correlated subgroups (one or two) and whether they include both positively and negatively correlated variables, or just positively correlated ones. Each data set also includes two uncorrelated "noise" variables that should automatically be removed by the Reper-Thresher algorithms.

References

Wang M, Abrams ZB, Kornblau SM, Coombes KR. Thresher: determining the number of clusters while removing outliers. BMC Bioinformatics, 2018; 19(1):1-9. doi://10.1186/s12859-017-1998-9.