complexityPrior: Complexity prior distribution

In beast: Bayesian Estimation of Change-Points in the Slope of Multivariate Time-Series

Description

This function computes the complexity prior distribution on the number of change-points, defined as f(\ell) = P(\ell_n = \ell)\propto e^{-α\ell\log(bT/\ell)}, a, b > 0; \ell = 0,1,2,…. Note that this distribution has exponential decrease (Castillo and van der Vaart, 2012) when b>1+e, so we set b=3.72.

Usage

complexityPrior(Lmax = 20, gammaParameter, nTime)

Arguments

Lmax	maximum number of change-points (default = 20).
gammaParameter	positive real number, corresponding to α.
nTime	positive integer denoting the total number of time-points.

Value

logPrior

Prior distribution values in the log-scale.

Author(s)

Panagiotis Papastamoulis

References

Castillo I. and van der Vaart A (2012). Needles and Straw in a Haystack: Posterior concentration for possibly sparse sequences. The Annals of Statistics, 40(4), 2069–2101.

beast documentation built on May 2, 2019, 1:19 p.m.