A helper function to extract a covariance matrix.
# S4 method for pmcmcd_pomp
covmat(object, start = 1, thin = 1, expand = 2.38, ...)# S4 method for pmcmcList
covmat(object, start = 1, thin = 1, expand = 2.38, ...)
# S4 method for abcd_pomp
covmat(object, start = 1, thin = 1, expand = 2.38, ...)
# S4 method for abcList
covmat(object, start = 1, thin = 1, expand = 2.38, ...)
# S4 method for probed_pomp
covmat(object, ...)
an object extending ‘pomp’
the first iteration number to be used in estimating the covariance matrix.
Setting thin > 1 allows for a burn-in period.
factor by which the chains are to be thinned
the expansion factor
ignored
When object is the result of a pmcmc or abc computation,
covmat(object) gives the covariance matrix of the chains.
This can be useful, for example, in tuning the proposal distribution.
When object is a ‘probed_pomp’ object (i.e., the result
of a probe computation), covmat(object) returns the
covariance matrix of the probes, as applied to simulated data.
Other extraction methods:
coef(),
cond.logLik(),
eff.sample.size(),
filter.mean(),
filter.traj(),
forecast(),
logLik,
obs(),
pred.mean(),
pred.var(),
saved.states(),
spy(),
states(),
summary(),
timezero(),
time(),
traces()