logL.joint.GRW {paleoTS} | R Documentation |
Returns log-likelihood for general random walk (logL.joint.GRW
), unbiased random walk (logL.joint.URW
), stasis (logL.joint.Stasis
) and OU (logL.joint.OU
) models.
logL.joint.GRW(p, x) logL.joint.URW(p, x) logL.joint.Stasis(p, x) logL.joint.OU(p, x)
p |
a vector of parameters |
x |
a paleoTS object |
For the general random walk, p = c(anc, mstep, vstep)
; for an unbiased random walk, p = c(anc, vstep)
; for the stasis model, p = c(theta, omega)
, and for the OU model p = c(anc, vstep, theta, alpha)
. In general, users will not be access these functions directly, but instead use the optimization functions, which use these functions to find the best-supported parameter values.
The log-likelihood of the parameter estimates (p
), given the data (x
).
Because these functions parameterize the models differently, their log-likelihoods are not comparable to those that do not use the joint parameterization.
Gene Hunt
Hunt, G. 2006. Fitting and comparing models of phyletic evolution: random walks and beyond. Paleobiology32:578–601.
Hunt, G., M. Bell & M. Travis. 2008. Evolution towards a new adaptive optimum: phenotypic evolution in a fossil stickleback lineage. Evolution 62:700-710.
x<- sim.GRW(ns=20, ms=0, vs=1) L1<- logL.joint.GRW(p=c(0,0,1), x) # actual parameters L2<- logL.joint.GRW(p=c(0,10,1), x) # should be a bad guess cat(L1, L2, "\n")