scMANOVAsimulation {semicontMANOVA}

Simulation of datasets for a semicontinuous scenarios

Description

Simulation of dataset of semicontinuous data coming from different groups, with specific marginal probabilities of a missing value, specific mean vectors and common covariance matrix.

Usage

scMANOVAsimulation(n, p, pmiss = 0, rho = 0, mu = NULL,
  sigma = NULL, only.data = TRUE)

Arguments

n

vector. The length corresponds to the number of groups, the elements to the number of observations in each group

p

scalar. Number of variables (columns)

pmiss

scalar or vector. Proportion of missingness in each group. If it is a scalar the same proportion is used in each group

rho

scalar. If sigma=NULL then sigma is set as a covariance matrix with covariance rho equal in every entries that is not on the main diagonal of sigma, and variance equal to 1

mu

NULL or vector or matrix. If NULL the mean of each group is set zero for all the variables, if vector the different groups have the same mean. If matrix each row corresponds to the mean vector of the corresponding group

sigma

NULL or matrix. If matrix it is a covariance matrix. If NULL the value of rho is used to build the covariance matrix

only.data

logical. If TRUE only the simulated data are reported

Value

If only.data=TRUE an object of class matrix is reported otherwise a list with the following components

x

matrix. The simulated dataset

y

matrix. A matrix with zero when the corresponding entry in x is zero and one otherwise

original

matrix. The simulated dataset without missing values

mu

matrix. Mean vectors, on for each group

sigma

matrix. Covariance matric

n

As in input

p

As in input

pmiss

vector. Proportion of missingness in each group

Author(s)

Elena Sabbioni, Claudio Agostinelli and Alessio Farcomeni

References

Elena Sabbioni, Claudio Agostinelli and Alessio Farcomeni (2024) A regularized MANOVA test for semicontinuous high-dimensional data. arXiv: http://arxiv.org/abs/2401.04036

See Also

scMANOVAestimation and scMANOVApermTest

Examples

  set.seed(1234)
  n <- c(5,5)
  p <- 20
  pmiss <- 0.1
  x <- scMANOVAsimulation(n=n, p=p, pmiss=pmiss)