Comparison of various tests for differences between the distribution of the downsampled data compared to the distribution of the full data set.

For this test, the Iris data set was used due to its computational speed and wide use in method development. The values represent the means and standard deviations of the mean square errors (MSE) of PCA-based reproduction of the remaining data from the downsampled data. The experiments were performed in 20 replicates starting with different seeds, and the means and standard deviations of the mean square errors of the data reproduction obtained during these replicates are shown. The similarity measures are sorted in ascending order by the ranks of the MSE obtained when the final sample is chosen from 10,000 random samples.