Make one prediction for one cross-validation run. This is a subroutine that is called by cvLDS, without any checks. You should not need to use this directly.
one_lds_cv(
z,
instPeriod,
mu,
y,
u,
v,
method = "EM",
num.restarts = 20,
ub = NULL,
lb = NULL,
num.islands = 4,
pop.per.island = 100,
niter = 1000,
tol = 1e-06,
use.raw = FALSE
)A vector of left-out points, indexed according to the intrumental period
indices of the instrumental period in the whole record
Mean of the observations
Catchment output, preprocessed from data
Input matrix for a single-model reconstruction, or a list of input matrices for an ensemble reconstruction.
Same as u.
By default this is "EM". There are experimental methods but you should not try.
The number of initial conditions to start the EM search; ignored if init is provided.
Upper bounds, a vector whose length is the number of parameters
Lower bounds
Number of islands (if method is GA; experimental)
Initial population per island (if method is GA; experimental)
Maximum number of iterations, default 1000
Tolerance for likelihood convergence, default 1e-5. Note that the log-likelihood is normalized by dividing by the number of observations.
Whether performance metrics are calculated on the raw time series. Experimental; don't use.
A vector of prediction.