combineCollapsing: Combining the best collapsings from factors collapsed...

In senhu/FCBMA: Factor collapsing with Bayesian model averaging for regression models

Description

When collapsing factors individually for the reason of computational intensity, this functions searches across the best results from each individual factor and find the best combinations across all factors

Usage

combineCollapsing(all.collapsings, varia.list, model)

Arguments

all.collapsings	a list of list of all collapsing results for each factor
varia.list	a vector of all factors collapsed
model	full model

Value

the best combinations

Examples

r1 <- FCBMA(model = mod1,
            varia.list = c("Make"),
            method = "SA",
            transition.method = "ChangeOne")
res1 <- Extract.SA.Res(r1, threshold.val = 0.95)$State

r2 <- FCBMA(model = mod1,
            varia.list = c("Zone"),
            method = "SA",
            transition.method = "ChangeOne")
res2 <- Extract.SA.Res(r2, threshold.val = 0.95)$State

r3 <- FCBMA(model = mod1,
            varia.list = c("Kilometres"),
            method = "SA",
            transition.method = "ChangeOne")
res3 <- Extract.SA.Res(r3, threshold.val = 0.95)$State
z <- CombineCollapsing(all.collapsings = list(unlist(Res1$Accept.States, recursive = F),
                                              unlist(Res2$Accept.States, recursive = F),
                                              unlist(Res3$Accept.States, recursive = F)),
                                varia.list=c("Make", "Zone", "Kilometres"),
                                model=mod1)

senhu/FCBMA documentation built on Aug. 6, 2019, 4:56 p.m.