logmeanexp: The log-mean-exp trick

In pomp: Statistical Inference for Partially Observed Markov Processes

Description

logmeanexp computes

log mean exp(x_i),

avoiding over- and under-flow in doing so. It can optionally return an estimate of the standard error in this quantity.

Usage

logmeanexp(x, se = FALSE)

Arguments

x	numeric
se	logical; give approximate standard error?

Details

When se = TRUE, logmeanexp uses a jackknife estimate of the variance in log(x).

Value

log(mean(exp(x))) computed so as to avoid over- or underflow. If se = FALSE, the approximate standard error is returned as well.

Author(s)

Aaron A. King

Examples

  ## generate a bifurcation diagram for the Ricker map
  pompExample(ricker)
  ll <- replicate(n=5,logLik(pfilter(ricker,Np=1000)))
  ## an estimate of the log likelihood:
  logmeanexp(ll)
  ## with standard error:
  logmeanexp(ll,se=TRUE)

pomp documentation built on July 18, 2017, 5:01 p.m.

Ensemble Kalman filters

pomp index

pomp low-level interface