grid_search_2d {TwoTimeScales} | R Documentation |
Grid search for the optimal 2ts model
Description
grid_search_2d()
performs a grid search for the minimum
AIC or BIC of the two time scales model.
It finds the optimal values of log_10(rho_u)
and log_10(rho_s)
and
returns the estimated optimal model.
Usage
grid_search_2d(
lru,
lrs,
R,
Y,
Bu,
Bs,
Z = NULL,
Iu,
Is,
Du,
Ds,
Wprior = NULL,
ridge = 0,
optim_criterion = c("aic", "bic"),
control_algorithm = list(maxiter = 20, conv_crit = 1e-05, verbose = FALSE, monitor_ev =
FALSE),
par_gridsearch = list(plot_aic = FALSE, plot_bic = FALSE, return_aic = TRUE, return_bic
= TRUE, col = grey.colors(n = 10), plot_contour = FALSE, mark_optimal = TRUE,
main_aic = "AIC grid", main_bic = "BIC grid")
)
Arguments
lru |
A vector of |
lrs |
A vector of |
R |
A matrix (or 3d-array) of exposure times of dimension nu by ns (or nu by ns by n). |
Y |
A matrix (or 3d-array) of event counts of dimension nu by ns (or nu by ns by n). |
Bu |
A matrix of B-splines for the |
Bs |
A matrix of B-splines for the |
Z |
(optional) A regression matrix of covariates values of dimensions n by p. |
Iu |
An identity matrix of dimension nbu by nbu. |
Is |
An identity matrix of dimension nbs by nbs. |
Du |
The difference matrix over |
Ds |
The difference matrix over |
Wprior |
An optional matrix of a-priori weights. |
ridge |
A ridge penalty parameter: default is 0. This is useful when, in
some cases the algorithm shows convergence problems. In this case, set to a small
number, for example |
optim_criterion |
The criterion to be used for optimization:
|
control_algorithm |
A list with optional values for the parameters of the iterative processes:
|
par_gridsearch |
A list of parameters for the grid_search:
|
Value
An object of class h2tsfit
with the following elements:
-
optimal_model
A list containing the results of the optimal model. -
optimal_logrho
The optimal couple oflog_10(rho_u)
andlog_10(rho_s)
values. -
P_optimal
The optimal penalty matrix P. -
AIC
(ifpar_gridsearch$return_aic == TRUE
) The vector of AIC values. -
BIC
(ifpar_gridsearch$return_bic == TRUE
) The vector of BIC values.
References
Camarda, C. G. (2012). "MortalitySmooth: An R Package for Smoothing Poisson Counts with P-Splines." Journal of Statistical Software, 50(1), 1–24. https://doi.org/10.18637/jss.v050.i01