Even though, according to the exact numerical p-values, there is insufficient evidence rejecting the null hypothesis when comparing model Clean_ac to model Clean for two descriptor sets, a clear trend across all three descriptor sets can be observed: Clean_ac performs worse than most of the best-performing models.
← all excerpts
Effect of Data Quality and Data Quantity on the Estimation of Intrinsic Solubility: Analysis Based on a Single-Source Data Set.
1
—
—