Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!
Get Started for Free

CuPlotDiag

Diagnosis plots for Lambda, U, C, Mu, Pi, Z and Epsilon


Description

Diagnostics plots for hazard rate (Lambda), latent variable (U), dependence variable (C), mean of cure threshold (Mu), cure proportion (Pi), cure threshold (Z) and the parameter of the hierarchical prior (Epsilon).

Usage

CuPlotDiag(M, variable = "Lambda", pos = 1)

Arguments

M

List. Contains the output by CuMRes.

variable

Either "Lambda", "U", "C", "Mu", "Pi", "Z" or "Epsilon". Variable for which diagnostic plot will be shown.

pos

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

Details

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

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

See Also

Examples

## Simulations may be time intensive. Be patient.

## Example 1
# data(crm3)
# times<-crm3$times
# delta<-crm3$delta
# res <- CuMRes(times, delta, type.t = 2, 
#                   K = 100, length = .1, alpha = rep(1, 100  ), 
#                   beta = rep(1, 100),c.r = rep(50, 99), 
#                   iterations = 100, burn.in = 10, thinning = 1, type.c = 2)
# CuPlotDiag(M = res, variable = "Mu")
# CuPlotDiag(M = res, variable = "Z")
# CuPlotDiag(M = res, variable = "Pi")
# CuPlotDiag(M = res, variable = "Lambda", pos = 2)
# CuPlotDiag(M = res, variable = "U", pos = 4)
# CuPlotDiag(M = res, variable = "C", pos = 3)

BGPhazard

Markov Beta and Gamma Processes for Modeling Hazard Rates

v2.1.0
GPL (>= 2)
Authors
L. E. Nieto-Barajas, J. A. Garcia Bueno, E.A. Morones Ishikawa and J. Pliego
Initial release

We don't support your browser anymore

Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.