loocv_neg: A Negative Network Predication Function

In oliverychen/network.predication: Brain Network Predication of Behavior via LOOCV

Description

Use negative brain network to predicate behavior via feature selection and LOOCV

Usage

loocv_neg(x, y, threshold = 0.01)

Arguments

x	x is a n by p matrix consisting n subjects and p features.
y	y is a n by 1 vector consisting behavior measurement.
threshold	threshold is a number (e.g. 0.01) specifying the significant feature to retain

Details

The codes take two variables x and y, where x is a n by p matrix consisting n subjects and p features, and y is a n by 1 vector consisting behavior measurement. The codes then conduct (1) feature selection, and (2) leave-one-subject-out cross-validation using selected features of x on predication of y.

Value

cor	correlation between observed and predicated behavior
p	p-value (significance) of the correlation between observed and predicated behavior
significant.negative.edges	significant edges predicative of behavior in the negative network

Author(s)

Oliver Y. Chén

Examples

require(Hmisc)
set.seed(1)
X <- matrix(rnorm(40000, 10, 5),40,1000) ### 40 subjects and 1000 features
Y <- rnorm(40, 20, 15) ### 40 subjects' observed behavior
neg.out <- loocv_neg(x=X, y=Y, threshold=0.01)
str(neg.out)

oliverychen/network.predication documentation built on May 30, 2019, 7:03 p.m.