stabsel {bamlss} | R Documentation |
Performs stability selection based on gradient boosting.
stabsel(formula, data, family = "gaussian", q, B = 100, thr = .9, ...) ## Plot selection frequencies. ## S3 method for class 'stabsel' plot(x, show = NULL, pal = function(n) gray.colors(n, start = 0.9, end = 0.3), ...)
formula |
A formula or extended formula. |
data |
A |
family |
A |
q |
An integer specifying how many terms to select in each boosting run. |
B |
An integer. The boosting is run B times. |
thr |
Cut-off threshold for selection. |
x |
A object of class stabsel. |
show |
Number of terms to be shown. |
pal |
Color palette for different model terms. |
... |
Not used yet in |
A object of class stabsel.
Thorsten Simon
## Not run: ## Simulate some data. d <- GAMart() n <- nrow(d) ## Add some noise variables. for(i in 4:9) d[[paste0("x",i)]] <- rnorm(n) f <- paste0("~ ", paste("s(x", 1:9, ")", collapse = "+", sep = "")) f <- paste(f, "+ te(lon,lat)") f <- eval(parse(text = f)) f <- list(update(f, num ~ .), f) ## Run stability selection. sel <- stabsel(f, data = d, q = 6, B = 10) plot(sel) ## Estimate selected model. b <- bamlss(sel$formula.new, data = d) plot(b) ## End(Not run)