Tests for the existence of a hiatus between two parameters.
Usage
hiatus(x, y, ...)
# S4 method for PhasesMCMC,missing
hiatus(x, level = 0.95)
# S4 method for numeric,numeric
hiatus(x, y, level = 0.95)
# S4 method for EventsMCMC,missing
hiatus(x, level = 0.95)
Arguments
- x, y
A
numeric
vector. Ify
is missing,x
must be anPhasesMCMC
or anEventsMCMC
object.- ...
Currently not used.
- level
A length-one
numeric
vector giving the confidence level.
Details
Finds if a gap exists between two dates and returns the longest interval that satisfies \(P(x < HiatusInf < HiatusSup < y | M) = level\)
The hiatus between two successive phases is the longest interval that satisfies \(P(Phase1Max < IntervalInf < IntervalSup < Phase2Min | M) = level\) (this assumes that the phases are in temporal order constraint).
Methods (by class)
hiatus(x = PhasesMCMC, y = missing)
: Hiatus between successive phases.hiatus(x = numeric, y = numeric)
: Returns a length-threenumeric
vector (upper and upper boundaries, and hiatus duration, if any).hiatus(x = EventsMCMC, y = missing)
: Hiatus between successive events.
Examples
## Coerce to MCMC
eve <- as_events(events, calendar = "CE", iteration = 1)
eve <- eve[1:10000, ]
## Test for anteriority
older(eve)
#> E1 E2 E3 E4
#> E1 0.0000 0e+00 0.4925 0.0000
#> E2 1.0000 0e+00 1.0000 0.9996
#> E3 0.5075 0e+00 0.0000 0.0000
#> E4 1.0000 4e-04 1.0000 0.0000
## Test for hiatus
hia <- hiatus(eve)
as.data.frame(hia)
#> lower upper duration
#> E2-E1 -1601.050 -1059.8006 541.24908
#> E4-E1 -1062.599 -1045.3355 17.26366
#> E2-E3 -1603.779 -803.1067 800.67205
#> E4-E3 -1067.123 -793.8029 273.32032
#> E2-E4 -1599.473 -1408.9400 190.53260