rqPen (version 2.3)

qaSIS: Quantile Adaptive Sure Independence Screening

Description

Implements quantile adaptive screening as outlined by He, Wang and Hong

Usage

qaSIS(x,y,tau,linear=FALSE,...)

Value

Returns the ranking of important predictors, from highest to lowest.

Arguments

x

Matrix of predictors.

y

Vector of response values.

tau

Conditional quantile being modelled.

linear

If true linear screening will be done, otherwise splines will be fit to each column vector.

...

Additional items to be sent to bs function from splines package.

Author

Ben Sherwood

References

[1] He, X., Wang, L. and Hong, H. (2013). Quantile-Adaptive Model-free Variable Screening for High-dimensional Heterogeneous Data. The Annals of Statistics, 41, 342--369.

Examples

x <- pnorm(matrix(rnorm(800),nrow=100))
y <- 1 + 2*cos(2*pi*x[,1])+exp(2*x[,2]) + rnorm(100,sd=.1)
var_ranks <- qaSIS(x,y)