Consequences of sample size, variable selection, and model validation and optimisation, for predicting classification ability from analytical data

147 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Harnessing the complexity of metabolomic data with chemometrics (2014, background): “In that perspective, the selection of the most relevant/predictive variables and the application of dimensionality reduction techniques can reduce the size of the fused data [35].”
Partial least squares discriminant analysis: taking the magic away (2014, methodology): “The ﬁ rst is to create a null or random dataset and follow all the methods through using this dataset [3,11], to see if there is any separation, and if this looks signi ﬁ cant, the methodology almost certainly over ﬁ ts the model.”
Multivariate Analysis in Metabolomics. (2012, background): “Importantly, either the complete absence of variable selection or an overly aggressive variable selection may lead to inadequate separation or over-fitting of the dataset, respectively [92, 93].”