View source: R/util_variance_reduction.R
(SMC2 version) Generates additional particles given current ones, in order to reduce the variance of the associated particle estimators. Nc is the desired total number of particles to be used in the computation / estimation (so about Nc - Ntheta new particles are generated, used in the estimation, and then discarded). The generated particles are equally weigthed. Note that in the continuous observations case, the particles (theta,xt) target the posterior-filtering distribution p(theta, xt | y_1, ..., y_t), whereas in the discrete case, they must target the posterior-one-step-predictive distribution p(theta, xt | y_1, ..., y_(t-1)).
1 2 | get_additional_particles_smc2(Nc, thetas, normw, PFs, t, observations, model,
logtargetdensities, algorithmic_parameters, Ncx = NULL)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.