TwalkMove: Wrapper for step function

In BayesianTools: General-Purpose MCMC and SMC Samplers and Tools for Bayesian Statistics

Wrapper for step function

Description

Wrapper for step function

Usage

TwalkMove(
  Npar,
  FUN,
  x,
  Eval,
  x2,
  Eval2,
  at = 6,
  aw = 1.5,
  pn1 = min(Npar, 4)/Npar,
  Ptrav = 0.4918,
  Pwalk = 0.4918,
  Pblow = 0.0082,
  Phop = 0.0082
)

Arguments

Npar	Number of parameters
FUN	Log posterior density
x	parameter vector of chain 1
Eval	last evaluation of x
x2	parameter vector of chain 2
Eval2	last evaluation of x
at	"traverse" move proposal parameter.
aw	"walk" move proposal parameter.
pn1	Probability determining the number of parameters that are changed.
Ptrav	Move probability of "traverse" moves, default to 0.4918
Pwalk	Move probability of "walk" moves, default to 0.4918
Pblow	Move probability of "blow" moves, default to 0.0082
Phop	Move probability of "hop" moves

References

Christen, J. Andres, and Colin Fox. "A general purpose sampling algorithm for continuous distributions (the t-walk)." Bayesian Analysis 5.2 (2010): 263-281.

BayesianTools documentation built on Feb. 16, 2023, 8:44 p.m.