GenerateData: Generate data

In tpgarcia/stride: STRIDE: Robust powerful mixture models

Description

Produces data from different populations with the probability of belonging to a population. Also produces one discrete covariate and one continuous covariate.

Usage

GenerateData(n, p, m, qvs, censoring.rate, simu.setting)

Arguments

n	sample size, must be at least 1.
p	number of populations, must be at least 2.
m	number of different mixture proportions, must be at least 2.
qvs	a numeric matrix of size p by m containing all possible mixture proportions (i.e., the probability of belonging to each population k, k=1,...,p.).
censoring.rate	a scalar indicating the censoring proportion. Options are 0 or 40.
simu.setting	Character indicating simulation setting. Options are "Log-Normal-No-Covariates", "Log-Normal-With-Covariates", "HD-No-Covariates","HD-With-Covariates". Setting "Log-Normal-No-Covariates" and "Log-Normal-With-Covariates" refer to simulation setting 1 in Garcia and Parast (2020). "Log-Normal-No-Covariates" means the survival outcomes do NOT depend on the covariates, and "Log-Normal-With-Covariates" means the survival outcomes do depend on the covariates. Setting "HD-No-Covariates" and "HD-With-Covariates" refer to Simulation setting 2 in Garcia and Parast (2020), "HD-No-Covariates" means the survival outcomes do NOT depend on the covariates, and "HD-With-Covariates" means the survival outcomes do depend on the covariates.

Value

Returns a list containing

• x: a numeric vector of length n containing the observed event times for each person in the sample.

• delta: a numeric vector of length n that denotes censoring (1 denotes event is observed, 0 denotes event is censored).

• q: a numeric matrix of size p by n containing the mixture proportions for each person in the sample.

• ww: a numeric vector of length n containing the values of the continuous covariate for each person in the sample.

• zz: a numeric vector of length n containing the values of the discrete covariate for each person in the sample.

• true.group.identifier: numeric vector of length n denoting the population identifier for each person in the sample. This is only used simulation study to evaluate the prediction accuracy of our methods.

References

Garcia, T.P. and Parast, L. (2020). Dynamic landmark prediction for mixture data. Biostatistics, doi:10.1093/biostatistics/kxz052.

tpgarcia/stride documentation built on March 18, 2021, 3:42 p.m.