BeMRes {BGPhazard}

Markov Beta Model

Description

Posterior inference for the Bayesian non-parametric Markov beta model for discrete survival times.

Usage

BeMRes(
  times,
  delta = rep(1, length(times)),
  alpha = rep(1e-04, K),
  beta = rep(1e-04, K),
  c.r = rep(0, K - 1),
  a.eps = 0.1,
  b.eps = 0.1,
  type.c = 4,
  epsilon = 1,
  iterations = 2000,
  burn.in = floor(iterations * 0.2),
  thinning = 5,
  printtime = TRUE
)

Arguments

times

Numeric positive vector. Failure times.

delta

Logical vector. Status indicator. TRUE (1) indicates exact lifetime is known, FALSE (0) indicates that the corresponding failure time is right censored.

alpha

Nonnegative vector. Small entries are recommended in order to specify a non-informative prior distribution.

beta

Nonnegative 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 consecutive failure times.

a.eps

Numeric. Shape parameter for the prior gamma distribution of epsilon when type.c = 4.

b.eps

Numeric. Scale parameter for the prior gamma distribution of epsilon when type.c = 4.

type.c

Integer. 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 epsilon; 4=assigns c.r an exponential hierarchical distribution with mean epsilon which in turn has a a Ga(a.eps, b.eps) distribution.

epsilon

Double. Mean of the exponential distribution assigned to c.r

iterations

Integer. Number of iterations including the burn.in and thining 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 is to reduces autocorrelation.

printtime

Logical. If TRUE, prints out the execution time.

Details

Computes the Gibbs sampler given by the full conditional distributions of u and Pi (Nieto-Barajas & Walker, 2002) and arranges the resulting Markov chain into a tibble which can be used to obtain posterior summaries.

Note

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

References

- Nieto-Barajas, L. E. & Walker, S. G. (2002). Markov beta and gamma processes for modelling hazard rates. Scandinavian Journal of Statistics 29: 413-424.

See Also

BePlotDiag, BePloth

Examples

## Simulations may be time intensive. Be patient.

## Example 1
#  data(psych)
#  timesP <- psych$time
#  deltaP <- psych$death
#  BEX1 <- BeMRes(timesP, deltaP, iterations = 3000, burn.in = 300, thinning = 1)

## Example 2
#  data(gehan)
#  timesG <- gehan$time[gehan$treat == "control"]
#  deltaG <- gehan$cens[gehan$treat == "control"]
#  BEX2 <- BeMRes(timesG, deltaG, type.c = 2, c.r = rep(50, 22))