MultiDiscreteRNG (version 0.1.0)

simBinaryCorr.GPD: Compute intermediate binary correlations for multivariate generalized Poisson data

Description

This function implements Step 2 of the algorithm to calibrate the intermediate latent-normal correlation matrix used to generate correlated binary variables for generalized Poisson (GPD) margins. For each pair of variables, it iteratively updates the latent correlation so that, after (i) generating correlated binary data via generate.binaryVar and (ii) mapping back to GPD outcomes via BinToGPD, the empirical correlation of the resulting GPD pair matches the user-specified target correlation in CorrMat. The calibrated pairwise latent correlations are then assembled into a full intermediate matrix, which is adjusted to be positive definite if needed.

Usage

simBinaryCorr.GPD(
  GPD.theta.vec,
  GPD.lambda.vec,
  CorrMat,
  no.rows,
  steps = 0.025
)

Value

intermediate multivariate binary Correlation matrix

Arguments

GPD.theta.vec

vector of theta values

GPD.lambda.vec

vector of lambda values

CorrMat

specified Correlation matrix

no.rows

number of observations for generating Multivariate Binary data

steps

Fraction of difference between the current and target matrix to be added in each iteration.

Examples

lambda.vec <- c(0.1, 0.13)
theta.vec <- c(7, 40)
M<- c(0.3, 0.3)
N <- diag(2)
N[lower.tri(N)] <- M
cmat<- N + t(N)
diag(cmat) <- 1

# In real-data simulation, no.rows is often set to 100000 in this intermediate step
# for more accurate calibration.
binObj <- simBinaryCorr.GPD(
  GPD.theta.vec  = theta.vec,
  GPD.lambda.vec = lambda.vec,
  CorrMat        = cmat,
  no.rows        = 20000,
  steps          = 0.025)