Cell-weighted MM imputation for mixed data (Path A)

Source: R/imputeCellMM.R

Uses a cell-weighted MM-estimator for each variable regression: S-step on unweighted data (high breakdown), M-step with cell weights (fine-grained downweighting). This preserves the S-estimator's breakdown guarantee while incorporating cellwise information.

imputeCellMM(
  data,
  maxit = 50,
  eps = 0.005,
  alpha_weight = 4.685,
  init_weights = "mcd",
  uncert = "pmm",
  trace = FALSE
)

Arguments

data

data.frame with missing values

maxit

maximum outer IRMI iterations (default: 50)

eps

convergence tolerance (default: 5e-3)

alpha_weight

tuning constant for bisquare cell weights (default: 4.685)

init_weights

initial cell weight method: "mcd" or "univariate" (default: "mcd")

uncert

uncertainty method: "pmm", "normalerror", or "none"

trace

logical

Value

list with data_imputed, cellweights, converged, iterations

Author

Matthias Templ