DMMD_Impute: An iterative algorithm to do imputation based on iterative...

In justicesuker/DMMD_Package: Double Matched Matrix Decomposition

An iterative algorithm to do imputation based on iterative DMMD method.

Description

An iterative algorithm to do imputation based on iterative DMMD method.

Usage

DMMD_Impute(
  X1,
  X2,
  init = c("mean", "unif", "normal"),
  r1 = NULL,
  r2 = NULL,
  rc = NULL,
  rr = NULL,
  angle_threshold = 90 * pi/180,
  variance1 = c("equal", "unequal"),
  variance2 = c("equal", "unequal"),
  method = c("PL", "ED"),
  tol = .Machine$double.eps^0.5,
  maxiter1 = 1000,
  maxiter2 = 1000
)

Arguments

X1	The first data matrix with NAs
X2	The second data matrix with NAs
init	The imputation method for initializing X1 and X2. Could be 'mean', 'unif' or 'normal'. Default 'mean'
r1	Total rank for X1. Default is NULL, meaning unknown, which will be estimated by rank estimation procedure determined by 'method'. Passed to DMMD_i function
r2	Total rank for X2. Default is NULL, meaning unknown, which will be estimated by rank estimation procedure determined by 'method'. Passed to DMMD_i function
rc	Joint column rank. Default is NULL, meaning unknown, which will be estimated by profile likelihood method. Passed to DMMD_i function
rr	Joint row rank. Default is NULL, meaning unknown, which will be estimated by profile likelihood method. Passed to DMMD_i function
angle_threshold	The threshold angle for principal angles. Principal angles greater than the threshold are not considered as joint signal. Default is 90 degree. Passed to DMMD_i function
variance1	Either "equal" or "unequal". Default is "equal". This argument is the variance assumption used in the profile likelihood method for determining the total rank. Passed to DMMD_i function
variance2	Either "equal" or "unequal". Default is "equal". This argument is the variance assumption used in the profile likelihood method for determining the joint rank. Passed to DMMD_i function
method	The method used for determining the total ranks r1 and r2. Either "PL" (profile likelihood) or "ED" (edge distribution). Default is "PL". Passed to DMMD_i function
tol	The tolerance used to determine convergence. Default is the square root of the machine precision. Passed to DMMD_i function
maxiter1	Maximum number of iterations allowed in the iterative imputation. Default is 1000
maxiter2	Maximum number of iterations allowed in each called DMMD_i function. Default is 1000

Value

A list with the following elements:

Imputed_X1	The final imputed and complete X1
Imputed_X2	The final imputed and complete X2

Examples

data = DoubleDataGen(n = 20, p = 16, rank = c(4, 3), rc = 2, rr = 1, nrep = 1)
X1_missing = data$X1[[1]]
X2_missing = data$X2[[1]]
X1_missing[1,1] = NA
X2_missing[3,2] = NA
result = DMMD_Impute(X1_missing, X2_missing)
result$Imputed_X1 - data$X1[[1]]

justicesuker/DMMD_Package documentation built on Aug. 6, 2022, 12:34 p.m.