Answers are grounded in this paper and cite their sources.
A dataset consisting of three column performance parameters obtained by testing eight reversed-phase HPLC columns with nine basic compounds and three mobile phases (methanol, acetonitrile and tetrahydrofuran) was assessed using chemometrics. The main aim was to investigate loss of information as the number of tests is reduced. Principal components analysis was performed on a full dataset using methanol as a mobile phase and procrustes analysis was used to compare numerically the scores plots as test compounds and individual test parameters were removed from the full dataset. The scores plots using different mobile phases were compared to determine whether the performance under one condition could predict that under another.
No takes yet. Share an insight, caveat, or question.
Brereton et al. (1999) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: