varord: Variable orderings for linear regression.

Description

Gives variable orderings for linear regression in high-dimensional data by various approaches.

Usage

varord(x, y, prior.prob = NULL, ordering = c("bic1","prior","bic1+prior"))

Arguments

A matrix whose columns correspond to variables or genes and whose rows correspond to the observations.

A vector of response values for fitting a linear model to a subset of the variables in x.

prior.prob

A vector of prior probabilities corresponding to the variables (genes).

ordering

A character string specifying the method to be used for the ordering the variables.

"bic1": Variables are ordered in by the BIC for the univariate linear model with that variable as predictor. (Yeung et~al. 2011)
"prior": The variables are ordered according to the log odds of their prior values. (Lo et~al. 2011)
"bic1+prior": The variables are ordered according to sum of the univarite BIC values and the log odds of their prior values.

Value

A vector of integers corresponding to the variable indexes in the specified order.

References

K. Lo, A. E. Raftery, K. M. Dombek, J. Zhu, E. E. Schadt, R. E. Bumgarner and K. Y. Yeung (2012), Integrating External Biological Knowledge in the Construction of Regulatory Networks from Time-series Expression Data, BMC Systems Biology, 6:101. K. Y. Yeung, K. M. Dombek, K. Lo, J. E. Mittler, J. Zhu, E. E. Schadt, R. E. Bumgarner and A. E. Raftery (2011), Construction of regulatory networks using expression time-series data of a genotyped population, Proceedings of the National Academy of Sciences, 108(48):19436-41.

Examples

Run this code

data(dream4)

network <- 1

Time <- as.numeric(dream4ts100[[network]]$time)

xIndex <- which(Time != max(Time))
yIndex <- which(Time != min(Time))

gene <- "G1"

x <- dream4ts100[[network]][xIndex,-(1:2)]
y <- dream4ts100[[network]][yIndex,gene]

nvar <- 50
ord <- varord( x, y, ordering = "bic1")[1:nvar]

## Not run: 
# result <- iterateBMAlm( x = x[,ord], y = y)
# ## End(Not run)