This page documents the routine PDAF_diag_effsample of PDAF, which was introduced with PDAF V1.12.

This routine computes the effective sample size of a particle filter as defined in Doucet et al. 2001 p. 333.

The effective sample size is a diagnostic quantity used in particle filter. It is defined as the inverse of the sum of the squared particle filter weights:

n_eff = 1 / (Sum_i=1,N w_i^2)

where w_i is the weight of particle with index i and N is the number of particles. If all weights are identical, it is n_eff=N and a particle file analysis step will have no influence. If n_eff=1, a single particle contains all weight, such that the sample of particle collapeses.

The routine is typically called during the analysis step of a particle filter, e.g. in the analysis step of NETF and LNETF.

The interface is the following:

  SUBROUTINE PDAF_diag_effsample(dim_sample, weights, n_eff)

with the following arguments:

  • dim_sample : integer, intent(in)
    Number of particles
  • weights : real, intent(in), dimension(dim_sample)
    Weights of the particles
  • n_eff : real, intent(out)
    Effective sample size
Last modified 2 years ago Last modified on Dec 11, 2016, 7:04:13 PM