paleoTS (version 0.3-1)

opt.GRW.shift: Functions for random walks with shifting parameters

Description

Functions to simulate and to infer a model with random walk dynamics, with parameter values that shift at one or more points in the sequence.

Usage

opt.GRW.shift(y, ng = 2, minb = 5, model = 1, pool = TRUE, silent = FALSE)

Arguments

y

a paleoTS object

ng

the number of different segments in the sequence

minb

the minimum number of samples to consider as a segment

model

options for variants of random walk to fit (see Details).

pool

if TRUE, pool phenotypic variances across samples

silent

if TRUE, do not print information on fitting to screen

Value

• A list including:
• value
  the log-likelihood of the optimal solution
• par
  parameter estimates
• K
  number of parameters in the model
• n
  the number of observations, equal to the number of evoltuionary transistions
• shift.start
  the index of the initial samples of each segment
• AIC
  Akaike information criterion
• AICc
  modified Akaike information criterion
• BIC
  Bayes (or Schwarz) information criterion
• shift.start
  index of each sample that starts a new segment
• all.logl
  log-likelihoods for all tested partitions of the series into segments
• GG
  matrix of indices of initial samples of each tested segment configuration; each column of GG corresponds to the elements of all.logl

Details

This model divides an evolutionary sequence into two or more non-overlapping parts called segments, and then fits some version of the random walk model to each segment separately. The model argument has four options: model=1, general random walk model, step variance shared across segments model=2, general random walk model, step mean shared across segments model=3, unbiased random walk, separate step variance for each segment model=4, general random walk, speparate step mean and variance for each segment

References

Hunt, G. 2006. Fitting and comparing models of phyletic evolution: random walks and beyond. Paleobiology32:578--601. Hunt, G. 2008. Gradual or pulsed evolution: when should punctuational explanations be preferred? Paleobiology34:In press.

See Also

sim.GRW.shift, opt.GRW, opt.RW.Mult

Examples

x<- sim.GRW.shift(ns=c(20,20), ms=c(0,1), vs=c(0.2, 0.2))
 plot(x)
 w.shift<- opt.GRW.shift(x, ng=2, model=1)
 print (w.shift$par)
 print (w.shift$shift.start)  # estimated first sample in second segment