CCuMRes: Bayesian Semiparametric Cure Rate Model with an Unknown...

In BGPhazard: Markov Beta and Gamma Processes for Modeling Hazard Rates

Bayesian Semiparametric Cure Rate Model with an Unknown Threshold and Covariate Information

Description

Posterior inference for the bayesian semiparmetric cure rate model with covariates in survival analysis.

Usage

CCuMRes(
  data,
  covs.x = names(data)[seq.int(3, ncol(data))],
  covs.y = names(data)[seq.int(3, ncol(data))],
  type.t = 3,
  K = 50,
  utao = NULL,
  alpha = rep(0.01, K),
  beta = rep(0.01, K),
  c.r = rep(0, K - 1),
  c.nu = 1,
  var.theta.str = 25,
  var.delta.str = 25,
  var.theta.ini = 100,
  var.delta.ini = 100,
  type.c = 4,
  a.eps = 0.1,
  b.eps = 0.1,
  epsilon = 1,
  iterations = 5000,
  burn.in = floor(iterations * 0.2),
  thinning = 3,
  printtime = TRUE
)

Arguments

data	Double tibble. Contains failure times in the first column, status indicator in the second, and, from the third to the last column, the covariate(s).
covs.x	Character. Names of covariables to be part of the multiplicative part of the hazard
covs.y	Character. Names of covariables to determine the cure threshold por each patient.
type.t	Integer. 1=computes uniformly-dense intervals; 2= partition arbitrarily defined by the user with parameter utao and 3=same length intervals.
K	Integer. Partition length for the hazard function.
utao	vector. Partition specified by the user when type.t = 2. The first value of the vector has to be 0 and the last one the maximum observed time, either censored or uncensored.
alpha	Nonnegative entry vector. Small entries are recommended in order to specify a non-informative prior distribution.
beta	Nonnegative entry vector. Small entries are recommended in order to specify a non-informative prior distribution.
c.r	Nonnegative vector. The higher the entries, the higher the correlation of two consective intervals.
c.nu	Tuning parameter for the proposal distribution for c. Only when type.c is 3 or 4.
var.theta.str	Double. Variance of the proposal normal distribution for theta in the Metropolis-Hastings step.
var.delta.str	Double. Variance of the proposal normal distribution for delta in the Metropolis-Hastings step.
var.theta.ini	Double. Variance of the prior normal distribution for theta.
var.delta.ini	Double. Variance of the prior normal distribution for delta. from the acceptance ratio in the Metropolis-Hastings algorithm for delta*.
type.c	1=defines c.r as a zero-entry vector; 2=lets the user define c.r freely; 3=assigns c.r an exponential prior distribution with mean 1; 4=assigns c.r an exponential hierarchical distribution with mean epsilon which in turn has a Ga(a.eps, b.eps) distribution.
a.eps	Double. Shape parameter for the prior gamma distribution of epsilon when type.c = 4.
b.eps	Double. Scale parameter for the prior gamma distribution of epsilon when type.c = 4.
epsilon	Double. Mean of the exponencial distribution assigned to c.r when type.c = 3.
iterations	Integer. Number of iterations including the burn.in to be computed for the Markov chain.
burn.in	Integer. Length of the burn-in period for the Markov chain.
thinning	Integer. Factor by which the chain will be thinned. Thinning the Markov chain reduces autocorrelation.
printtime	Logical. If TRUE, prints out the execution time.

Details

Computes the Gibbs sampler with the full conditional distributions of all model parameters (Nieto-Barajas & Yin, 2008) and arranges the resulting Markov chain into a tibble which can be used to obtain posterior summaries. Prior distributions for the regression coefficients Theta and Delta are assumend independent normals with zero mean and variance var.theta.ini, var.delta.ini, respectively.

Note

It is recommended to verify chain's stationarity. This can be done by checking each element individually. See CCuPlotDiag.

References

- Nieto-Barajas, L. E., & Yin, G. (2008). Bayesian semiparametric cure rate model with an unknown threshold. Scandinavian Journal of Statistics, 35(3), 540-556. https://doi.org/10.1111/j.1467-9469.2007.00589.x

- Nieto-barajas, L. E. (2002). Discrete time Markov gamma processes and time dependent covariates in survival analysis. Statistics, 2-5.

See Also

CCuPlotDiag, CCuPloth

Examples

# data(BMTKleinbook)
    # res <- CCuMRes(BMTKleinbook, covs.x = c("tTransplant","hodgkin","karnofsky","waiting"),
    #                covs.y = c("tTransplant","hodgkin","karnofsky","waiting"),
    #                        type.t = 2, K = 72, length = 30,
    #                        alpha = rep(2,72), beta = rep(2,72), c.r = rep(50, 71), type.c = 2,
    #                        var.delta.str = .1, var.theta.str = 1,
    #                        var.delta.ini = 100, var.theta.ini = 100,
    #                        iterations = 100, burn.in = 10, thinning = 1)

BGPhazard documentation built on Sept. 3, 2023, 5:09 p.m.