Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: Multivariate pattern analysis: a method and software to reveal, quantify, and visualize predictive association patterns in multicollinear data

Fig. 1

Flow diagram of the repeated Monte Carlo resampling algorithm used to validate the PLS models. This automatic procedure only needs three user defined inputs: i the number of repetitions, ii the maximum number of components in PLS models, and, iii the fraction of the distribution of the root mean squared prediction errors (RMSEPs) for the PLS model with lowest median that is higher than the median RMSEP for the model with one PLS component less. This fraction must be lower than 0.5 in order to protect against overfitting

Back to article page