LOO: Leave One Out

In DEMOVA: DEvelopment (of Multi-Linear QSPR/QSAR) MOdels VAlidated using Test Set

Description

Calculate the robustness of the equation using the leave one out method.

Usage

LOO(mydata, n)

Arguments

mydata	Dataframe containing names and values of response and descriptors
n	Numbers of selected descriptors of the regression (determined using Select_MLR)

Value

return Q2, the coefficient that measure the robstness

References

1. Gramatica, P. Principles of QSAR Models Validation: Internal and External. Qsar & Combinatorial Science 2007, 26, 694-701.
2. Golbraikh, A.; Tropsha, A. Beware of Q(2)! Journal of Molecular Graphics & Modelling 2002, 20, 269-276.

Examples

# First run Select_MLR to define n

# LOO(mydata,dim(MLR)[2])

DEMOVA documentation built on May 2, 2019, 2:09 a.m.