gnsc.train: gnsc.train
In smart: Sparse Multivariate Analysis via Rank Transformation

Description Usage Arguments Details Value Author(s) References See Also Examples

A function to conduct the Group Nearest Shrunken Centroid Classifier

1 2	gnsc.train(x, col.struc = NULL, row.struc = NULL, standardize = T, nlambda = NULL, lambda.max = 10, lambda = NULL, verbose = TRUE)

`x`	The train data matrix (variables in the rows, samples in the columns).
`col.struc`	The train class labels for samples, must have the same length as the column length of `x`.
`row.struc`	The train class labels for variables, must have the same length as the row length of `x`.
`standardize`	Logical value to determine whether to standardize the data. The defult value is TRUE.
`nlambda`	The number of thresholding parameters. The default value is 10.
`lambda.max`	The largest lambda value, given the thresholding parameters lambda is not provided by the user.
`lambda`	A sequence of positive numbers to control to determine the thresholding level.
`verbose`	If `verbose = FALSE`, tracing information printing is disabled. The default value is `TRUE`.

gnsc.train conducts a Group Nearest Shrunken Centroid Classifier.

An object with S3 class "gnsc" is returned:

`lambda`	A vector of the thresholds tried in the shrinkage
`nlambda`	The number of thresholds tried in the shrinkage
`yhat`	A matrix with the estimated sample lables for each thresholding level in each column
`errors`	The number of estimated errors for each threshold value
`nonzero`	The number of variables that survived the thresholding for each thresholding value
`...`	System reserved (No specific usage)

Fang Han, Han Liu
Maintainer: Fang Han<fhan@jhsph.edu>

1.Juemin Yang, Fang Han, Rafa Irizarry, and Han Liu. Gene Context Analysis on Large-scale Genomic Data. Technical Report, Johns Hopkins University, 2012
2.Robert Tibshirani, Trevor Hastie, Balasubramanian Narasimhan, and Gilbert Chu. Diagnosis of multiple cancer types by shrunken centroids of gene expression PNAS, 99: 6567-6572.

gnsc.cv

set.seed(120)
x <- matrix(rnorm(1000*20),ncol=20)
y <- sample(c(1:4),size=20,replace=TRUE)
z <- sample(c(1:10),size=1000,replace=TRUE)
fit=gnsc.train(x, col.struc=y, row.struc=z,lambda.max=5, nlambda=20)
fit
plot(fit)