Editorial

Abstract

Distribution électronique Cairn.info pour Académie de l'Entrepreneuriat et de l'Innovation. © Académie de l'Entrepreneuriat et de l'Innovation. Tous droits réservés pour tous pays.La reproduction ou représentation de cet article, notamment par photocopie, n'est autorisée que dans les limites des conditions générales d'utilisation du site ou, le cas échéant, des conditions générales de la licence souscrite par votre établissement. Toute autre reproduction ou représentation, en tout ou partie, sous quelque forme et de quelque manière que ce soit, est interdite sauf accord préalable et écrit de l'éditeur, en dehors des cas prévus par la législation en vigueur en France. Il est précisé que son stockage dans une base de données est également interdit.

Speleogenesis, geometry, and topology of caves: A quantitative study of 3D karst conduits

“…First, correlation coefficients were studied as well as their significance. Second, the parameters that showed significant differences from the KW test were selected for Principal Component Analysis (PCA), one of the most frequently used multivariate data analysis methods (Saporta, 2006). It projects observations from a p-dimensional space with p variables to a lower k-dimensional space (k < p) with k principal components while preserving the maximum amount of dispersion (i.e., variance) from the initial dimensions.…”

“…The samples for which γ = 1 (Fig. 14) were removed because these samples (i.e., 3 samples of the VB type) are outliers with respect to γ, and performing a PCA on the whole database would lead to an overcontribution of these particular samples in defining the F1 axis, which is not desirable for a PCA (Saporta, 2006). The seven input variables (see Table 2) have a mean contribution of 14.28%.…”

“…The Kaiser criterion (selecting axes for which a contribution is greater than the mean one) led to only two axes being selected. However, in order to reach ~ 80% of the total variance -as usually recommended (Saporta, 2006) -three axes were taken into consideration as axes F1-F2 represent 62.56% and the third axis represents 13.60% of the total variance, which is only slightly below the mean contribution. The total variance expressed by F1-F2-F3 then reaches 76.16%.…”