Comparison of 432 Pseudomonas strains through integration of genomic, functional, metabolic and expression data. In: Scientific Reports, 6 , pp. 38699, 2016, ISSN: 2045-2322.
Dataset can be found here
Determining the number of components in principal components analysis: A comparison of statistical, crossvalidation and approximated methods. In: Chemometrics and Intelligent Laboratory Systems, 149 , pp. 99 - 116, 2015, ISSN: 0169-7439.
Data generated under a spiked model with normal distribution; Data for scheme A
Data with correlated variables – Peres-Neto simulation; Data for scheme B
Spectroscopic like data with varying levels of homoscedastic noise; Data for scheme C
Same as A but with skewed data distribution; Data for scheme D
Same as C but with heteroscedastic noise; Data for scheme E