fdata: Transform datasets for factor copula modeling

In eFCM: Exponential Factor Copula Model

Transform datasets for factor copula modeling

Description

Prepares and organizes datasets for use with the exponential Factor Copula Model (eFCM). The function converts raw station-level observations and their spatial coordinates into an "fdata" object, which contains the data, grid structure, and neighborhood information required for model fitting with fcm().

Usage

fdata(
  data,
  coord,
  grid = NULL,
  neigh = NULL,
  theta0 = NULL,
  cellsize = c(0.5, 0.5),
  parallel = TRUE,
  ncpus = 4,
  mc.set.seed = TRUE,
  ...
)

Arguments

data	A matrix or data.frame. Each column corresponds to a station, with rows containing observations (on the original scale).
coord	A two-column matrix or data frame of station coordinates (longitude and latitude), one row per station.
grid	Optional two-column matrix or data frame of grid locations (longitude, latitude) at which the model will be fitted. If NULL (default), a regular grid is generated based on cellsize.
neigh	Optional list of neighborhood station indices for each grid point. If NULL, neighborhoods are constructed using neighborhood_HT().
theta0	Optional matrix or data.frame with two columns: initial lambda and delta. Must match number of stations.
cellsize	Numeric vector of length 1 or 2, specifying longitude and latitude resolution.
parallel	Logical; if TRUE, run neighbourhood selection in parallel using pbmcapply. On Windows, pbmclapply will fall back to serial execution (progress still shown).
ncpus	Integer; number of worker processes when parallel = TRUE on Unix-alikes.
mc.set.seed	Logical; seed the RNG streams in workers (default TRUE). Effective on Unix-alikes; on Windows (serial fallback) it has no effect.
...	Additional arguments passed to neighborhood_HT().

Value

An object of class "fdata", which is a list with elements:

data	Original input data
coord	Coordinates of stations
grid	Grid points with assigned IDs
neigh	List of neighbor station indices per grid point
theta0	Initial values matrix
N	Number of stations

See Also

fcm(), neighborhood_HT()

Examples

# Load precipitation data for counterfactual scenarios
data("counterfactual")
data("LonLat")
coord = LonLat  # station coordinates (longitude-latitude)
cf_data <- fdata(counterfactual, coord, cellsize = c(1, 1))

eFCM documentation built on Sept. 9, 2025, 5:52 p.m.