EV: Calculate the parameter expectation values for a collection...
In JGCRI/gcamland: GCAM Land Allocation Module

Use the parameter sample values to compute expectation values for the parameters. The samples can be either MCMC samples or uniform samples. In the latter case, the values will be weighted by their posterior probabilities.

EV(
  samples,
  modelgroup = "expectation.type",
  reportvars = NULL,
  weighted = TRUE,
  lp = "lp_"
)

`samples`	Monte Carlo samples, given either as a grand table or a list of `ScenarioInfo` objects
`modelgroup`	Vector of names of columns that define the model groupings. The default is the single column `expectation.type`.
`reportvars`	Vector of names of variables for which to report expectations. The default is all parameter values.
`weighted`	If `TRUE`, weight the samples by their posterior.
`lp`	Name of the column containing the log posterior probability. Ignored if `weighted==FALSE`.

The input to this function can be given either as a grand table (q.v. grand_table_bayes) or as a list of ScenarioInfo objects. Generally this collection will have several model families represented, so the table is split according to the model type. The result will be a table of expectation values by model

JGCRI/gcamland documentation built on Oct. 6, 2020, 5:30 p.m.