BGPhazard (version 1.2.3)

GaPlotDiag: Diagnosis plots for lambda, u, c and epsilon

Description

Informative plots for hazard rate (lambda), latent variable (u), dependence variable (c) and the parameter of the hierarchical model epsilon.

Usage

GaPlotDiag(M, variable = "lambda", pos = 1)

Arguments

M

List. Contains the information given for lambda and u by GaMRes.

variable

Either "lambda", "u", "c" or "epsilon". Variable for which informative plot will be shown.

pos

Positive integer. Position of the selected variable to be plotted.

Details

This function returns a diagnosis plot for which the chain for the selected variable can be monitored. Diagnosis includes trace, ergodic mean, autocorrelation function and histogram.

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

GaMRes

Examples

# NOT RUN {
## Simulations may be time intensive. Be patient.

## Example 1
#  data(gehan)
#  timesG <- gehan$time[gehan$treat == "6-MP"]
#  deltaG <- gehan$cens[gehan$treat == "6-MP"]
#  GEX1 <- GaMRes(timesG, deltaG, K = 8, iterations = 3000)
#  GaPlotDiag(GEX1, variable = "lambda", pos = 2)
#  GaPlotDiag(GEX1, variable = "u", pos = 5)

## Example 2
#  data(leukemiaFZ)
#  timesFZ <- leukemiaFZ$time
#  deltaFZ <- leukemiaFZ$delta
#  GEX2 <- GaMRes(timesFZ, deltaFZ, type.c = 4)
#  GaPlotDiag(GEX2, variable = "lambda", pos = 2)
#  GaPlotDiag(GEX2, variable = "u", pos = 3)
# }