Automated model selection using parallel computation

Parallelized version of dredge.

pdredge(global.model, cluster = NULL, 
  beta = c("none", "sd", "partial.sd"), evaluate = TRUE, rank = "AICc", 
  fixed = NULL, m.lim = NULL, m.min, m.max, subset, trace = FALSE, 
  varying, extra, ct.args = NULL, deps = attr(allTerms0, "deps"),
  check = FALSE, ...)

Arguments

global.model, beta, rank, fixed, m.lim, m.max, m.min, subset, varying, extra, ct.args, deps, ...: see dredge.
evaluate: whether to evaluate and rank the models. If FALSE, a list of unevaluated calls is returned and cluster is not used.
trace: displays the generated calls, but may not work as expected since the models are evaluated in batches rather than one by one.
cluster: either a valid "cluster" object, or NULL for a single threaded execution.
check: either integer or logical value controlling how much checking for existence and correctness of dependencies is done on the cluster nodes. See ‘Details’.

Details

All the dependencies for fitting the global.model, including the data and any objects that the modelling function will use must be exported to the cluster worker nodes (e.g. via clusterExport). The required packages must be also loaded thereinto (e.g. via clusterEvalQ(..., library(package)), before the cluster is used by pdredge.

If check is TRUE or positive, pdredge tries to check whether all the variables and functions used in the call to global.model are present in the cluster nodes' .GlobalEnv before proceeding further. This will cause false errors if some arguments of the model call (other than subset) would be evaluated in the data environment. In that case is desirable to use check = FALSE (the default).

If check is TRUE or greater than one, pdredge will compare the global.model updated on the cluster nodes with the one given as an argument.

Note

As of version 1.45.0, using pdredge directly is deprecated. Use dredge instead and provide cluster argument.

Value

See dredge.

Author

Kamil Bartoń