Extract model term selection frequencies.
This function takes a fitted bayesx object and returns selection frequency tables of
model terms. These tables are only returned using the stepwise procedure in combination with
the bootstrap confidence intervals, see function bayesx.control.
term.freqs(object, model = NULL, term = NULL, ...)
object |
an object of class |
model |
for which model the tables should be provided, either an integer or a character,
e.g. |
term |
character or integer. The term for which the frequency table should be extracted. |
... |
not used. |
Nikolaus Umlauf, Thomas Kneib, Stefan Lang, Achim Zeileis.
## Not run: ## generate some data set.seed(111) n <- 500 ## regressors dat <- data.frame(x = runif(n, -3, 3), z = runif(n, -1, 1), w = runif(n, 0, 1), fac = factor(rep(1:10, n/10))) ## response dat$y <- with(dat, 1.5 + sin(x) + rnorm(n, sd = 0.6)) ## estimate model b <- bayesx(y ~ sx(x) + sx(z) + sx(w) + sx(fac, bs = "re"), method = "STEP", CI = "MCMCbootstrap", bootstrapsamples = 99, data = dat) summary(b) ## extract frequency tables term.freqs(b) ## End(Not run)
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.