Speed

dev/bench.R times each function against every package found that computes the same quantity, on fixed seeded inputs and at sizes met in practice, after checking that the two give the same values; where no package does, against a base-R implementation of the formula. The table it writes, with the machine and the date, is inst/bench/bench.md (and bench.csv); the bench workflow runs it again every week. The lists below are written by the same script from that table.

Faster, by at least a tenth, than every package that computes the same quantity, at every size timed: vodtst(), orrisk(), outtst(), dspbm(), dyadrt(), gtmp(), kinidx(), patidx(), mixlr(), cllr(), cllrmin(), lrcal(), eceplt(), expbnd(), misrd(), rtmhs(), incapr(), sellab(), losbnd(), sntbnd(), hzdsel().

Not faster than such a package at some size timed: incap().

No package found that computes the same quantity, so timed against a base-R implementation of the formula: lrpost(), dbsrch(), tipplt(), clrsmp(), proof(); of these, not faster than base R at some size: lrpost(), dbsrch().