PCA.Analysis: PCA Analysis

In mbeccuti/Prova:

Description

PCAbarplot() is used to choice the dimension of the cluster mean space, h. The PCA method performs an accurate analysis to determine whether the means lie in a lower dimensional space, note that if h is equal to the number of cluster menus one, does not produce restriction on the mean space. To estimate h the Principal Component Analysis (PCA) is applied to the spline coefficients provided for each curves by the functional clustering model. It generates a bar plot indicating with how much percentage the principal components explain the variability in the data. Usually the components are choosen if the sum of the respective percentages is greater than 95 percent.

Usage

PCA.Analysis(data.matrix, save = FALSE, path = NULL)

Arguments

data.matrix	Matrix with 3 columns: curve ID, volume and time measures.
save	When TRUE (the default is FALSE), it is possible to save a plot that compares the density time grid and the growth curves plot in a pdf.
path	Path to save plot to (combined with filename).

Value

List containing the plot of the variances against the number of the principal component and the vector of percentages.

Examples

to write...

mbeccuti/Prova documentation built on May 20, 2019, 5:26 p.m.