estimNC: Estimate the Number of Components for Data Imputation

In GonzalezIgnacio/HandlingMissRows: Handling Missing Individuals in Multi-Omics Data Integration

Description

estimNC estimates the number of MFA components for data imputation. This function is called internally by MIMFA and is not usually called directly by a user.

Usage

estimNC(X, minNC=0, maxNC)

Arguments

X	a numeric matrix.
minNC	minimum number of components to consider, by default 0.
maxNC	maximum number of components to test.

Details

Partially borrowed from the estim_npc function in the FactoMineR package, estimNC estimates the number of MFA components for data imputation using the generalized cross-validation approximation method.

Value

Return the number of MFA components to use in data imputation.

References

Josse, J. and Husson, F. (2012). Selecting the number of components in PCA using cross-validation approximations. Computational Statistics and Data Analysis, 56, 1869-1879.

GonzalezIgnacio/HandlingMissRows documentation built on Jan. 17, 2020, 6:29 p.m.