roben (version 0.1.1)

GxESelection: Variable selection for a roben object

Description

Variable selection for a roben object

Usage

GxESelection(obj, ...)
# S3 method for Sparse
GxESelection(obj, burn.in = obj$burn.in, ...)
# S3 method for NonSparse
GxESelection(obj, burn.in = obj$burn.in, prob = 0.95, ...)

Value

an object of class `GxESelection' is returned, which is a list with components:

• method: method used for identifying important effects.

• effects: a list of names of selected effects.

• summary: a summary of selected effects.

• indicator: a matrix of indicators of selected effects.

Arguments

obj

roben object.

...

other GxESelection arguments.

burn.in

MCMC burn-in.

prob

probability for credible interval, between 0 and 1. e.g. prob=0.95 leads to 95% credible interval.

Details

For class `Sparse', the median probability model (MPM) (Barbieri and Berger, 2004) is used to identify predictors that are significantly associated with the response variable. For class `NonSparse', variable selection is based on 95% credible interval. Please check the references for more details about the variable selection.

References

Ren, J., Zhou, F., Li, X., Ma, S., Jiang, Y. and Wu, C. (2023) Robust Bayesian variable selection for gene-environment interactions. Biometrics, 79(2):684-694. tools:::Rd_expr_doi("10.1111/biom.13670"). PMID: 35394058.

Barbieri, M.M. and Berger, J.O. (2004). Optimal predictive model selection. Ann. Statist, 32(3):870–897

See Also

roben

Examples

data(GxE_small)
iter=5000
## sparse
fit=roben(X, Y, E, clin, iterations=iter)
selected=GxESelection(fit)
selected

# \donttest{
## non-sparse
fit=roben(X, Y, E, clin, iterations=iter, sparse=FALSE)
selected=GxESelection(fit)
selected
# }