The variance of the prediction distribution
# S4 method for pfilterd_pomp
pred.var(object, vars, ...)result of a filtering computation
optional character; names of variables
ignored
The prediction distribution is that of $$X(t_k) \vert Y(t_1)=y^*_1,\dots,Y(t_{k-1})=y^*_{k-1},$$ where \(X(t_k)\), \(Y(t_k)\) are the latent state and observable processes, respectively, and \(y^*_k\) is the data, at time \(t_k\).
The prediction variance is therefore the variance of this distribution $$\mathrm{Var}[X(t_k) \vert Y(t_1)=y^*_1,\dots,Y(t_{k-1})=y^*_{k-1}].$$
More on sequential Monte Carlo methods:
bsmc2(),
cond.logLik(),
eff.sample.size(),
filter.mean(),
filter.traj(),
kalman,
mif2(),
pfilter(),
pmcmc(),
pred.mean(),
saved.states(),
wpfilter()
Other extraction methods:
coef(),
cond.logLik(),
covmat(),
eff.sample.size(),
filter.mean(),
filter.traj(),
forecast(),
logLik,
obs(),
pred.mean(),
saved.states(),
spy(),
states(),
summary(),
timezero(),
time(),
traces()