partial_forder function

Functional ordering in parts

If the functional data doesn't comfortably fit in memory it is possible to compute functional ordering by splitting the domain of the data (voxels in a brain image), using partial_forder on each part and finally combining the results with combine_forder.

partial_forder(
  curve_set,
  measure = c("erl", "rank", "cont", "area"),
  alternative = c("two.sided", "less", "greater")
)

combine_forder(ls)

Arguments

• curve_set: A curve_set object, usually a part of a larger curve_set. (No missing or infinite values allowed.)
• measure: The measure to use to order the functions from the most extreme to the least extreme one. Must be one of the following: 'rank', 'erl', 'cont', 'area', 'max', 'int', 'int2'. Default is 'erl'.
• alternative: A character string specifying the alternative hypothesis. Must be one of the following: "two.sided" (default), "less" or "greater". The last two options only available for types 'rank', 'erl', 'cont' and 'area'.
• ls: List of objects returned by partial_forder

Returns

See forder

Examples

data("abide_9002_23")
res <- lapply(list(1:100, 101:200, 201:261), function(part) {
  set.seed(123) # When using partial_forder, all parts must use the same seed.
  fset <- frank.flm(nsim=99, formula.full = Y ~ Group + Sex + Age,
                  formula.reduced = Y ~ Group + Sex,
                  curve_sets = list(Y = abide_9002_23$curve_set[part,]),
                  factors = abide_9002_23$factors, savefuns = "return")
  partial_forder(fset, measure="erl")
})
combine_forder(res)

See Also

forder