EMVSplot: Spike-and-slab Dynamic Posterior Exploration
In EMVS: The Expectation-Maximization Approach to Bayesian Variable Selection

Description Usage Arguments Details Author(s) References See Also

View source: R/EMVSplot.R

EMVSplot procedure plots the solution path of the estimated regression coefficients (posterior modes) for different v0 values.

1	EMVSplot(result, plot_type=c("both","reg","gf"), omit.zeroes = FALSE)

`result`	List object outputed by the EMVS procedure
`plot_type`	Plot type: "both" for plotting both the regularization path together with the associated log g function, "reg" only for the regulaziation plot, "gf" only for the log g function.
`omit.zeroes`	Logical: `TRUE` or `FALSE`. If `TRUE`, only the selected coefficients are plotted, the remaining coefficients set to zero

Coefficients that are not thresholded out are depicted in blue, the rest in red. Log g function computed only for models with at most 1 000 predictors.

Veronika Rockova

Rockova, V. and George, E. I. (2014) EMVS: The EM Approach to Bayesian Variable Selection. Journal of the American Statistical Association

EMVS, EMVSsummary, EMVSbest

EMVS documentation built on Oct. 13, 2021, 5:09 p.m.