pred_var: Prediction variance

In kidusasfaw/pomp: Statistical Inference for Partially Observed Markov Processes

Description

The variance of the prediction distribution

Usage

## S4 method for signature 'pfilterd_pomp'
pred.var(object, vars, ...)

Arguments

object	result of a filtering computation
vars	optional character; names of variables
...	ignored

Details

The prediction distribution is that of

Xt | Y1=y1*,…,Y(t-1)=y(t-1)*,

where Xt, Yt are the latent state and observable processes, respectively, and yt* is the data, at time t.

The prediction variance is therefore the variance of this distribution

Var[Xt | Y1=y1*,…,Y(t-1)=y(t-1)*].

See Also

Other particle filter methods: bsmc2, cond.logLik, eff.sample.size, filter.mean, filter.traj, mif2, pfilter, pmcmc, pred.mean

kidusasfaw/pomp documentation built on May 20, 2019, 2:59 p.m.