g3_leaveout | R Documentation |
Perform a leave-one-out analysis. This involves running a set of optimisations, each one of which has a component (or set of components) turned off (i.e. weight = 0).
g3_leaveout(
gd,
outdir = "LOCV",
model,
params,
grouping = list(),
use_parscale = TRUE,
method = "BFGS",
control = list(),
serial_compile = FALSE,
mc.cores = parallel::detectCores()
)
gd |
Directory to store output |
outdir |
Directory name within gd to store run outputs |
model |
A G3 model, produced by g3_to_tmb() or g3_to_r() |
params |
Initial parameters to use with the model, this should be a TMB parameter template i.e. attr(tmb_model, 'parameter_template') |
grouping |
List of component names to group together. This allows you to leave out multiple components at a time, e.g. length and age-length distributions from a particular fleet |
use_parscale |
Logical indicating whether optim(control$parscale) should be used |
method |
The optimisation method, see |
control |
List of control options for optim, see |
serial_compile |
g3_tmb_adfun will be run in serial mode (i.e., not in parallel), potentially helping with memory issues |
mc.cores |
The number of cores to use, defaults to the number available |
g3_leaveout
performs a leave-one-out analysis.
A list of optimised parameter data frames (one for each group)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.