Plots

This function displays plots related to predictive accuracy functions: epoce and Diffepoce.

Usage

# S3 method for Diffepoce
plot(x, ...)

# S3 method for epoce
plot(x, ...)

Arguments

x: an object inheriting from classes epoce or Diffepoce
...: other parameters to be passed through to plotting functions

Value

Returns plots related to epoce and Diffepoce

Details

These functions do not apply for the moment with multiple causes of event (competing risks).

For epoce objects, the function displays the EPOCE estimate (either MPOL or CVPOL) according to the time of prediction. For Diffepoce objects, plot displays the difference in EPOCE estimates (either MPOL or CVPOL) and its 95% tracking interval between two joint latent class models

Author

Cecile Proust-Lima and Viviane Philipps

Examples


# \dontrun{
# estimation of the joint latent class model
m3 <- Jointlcmm(fixed= Ydep1~Time*X1,mixture=~Time,random=~Time,
classmb=~X3,subject='ID',survival = Surv(Tevent,Event)~X1+mixture(X2),
hazard="3-quant-splines",hazardtype="PH",ng=3,data=data_lcmm,
B=c(0.7667, 0.4020, -0.8243, -0.2726, 0.0000, 0.0000, 0.0000, 0.3020,
-0.6212, 2.6247, 5.3139, -0.0255, 1.3595, 0.8172, -11.6867, 10.1668,
10.2355, 11.5137, -2.6209, -0.4328, -0.6062, 1.4718, -0.0378, 0.8505,
0.0366, 0.2634, 1.4981))
# predictive accuracy of the model evaluated with EPOCE
VecTime <- c(1,3,5,7,9,11,13,15)
cvpl <- epoce(m3,var.time="Time",pred.times=VecTime)
#> Be patient, epoce function is running ... 
#> The program took 0.93 seconds 
summary(cvpl)
#> Expected Prognostic Observed Cross-Entropy (EPOCE) of the joint latent class model: 
#>  
#> Jointlcmm(fixed = Ydep1 ~ Time * X1, mixture = ~Time, random = ~Time, 
#>     subject = "ID", classmb = ~X3, ng = 3, survival = Surv(Tevent, 
#>         Event) ~ X1 + mixture(X2), hazard = "3-quant-splines", 
#>     hazardtype = "PH", data = data_lcmm)
#>  
#> EPOCE estimators on data used for estimation: 
#>     Mean Prognostic Observed Log-likelihood (MPOL) 
#>     and Cross-validated Prognostic Observed Log-likelihood (CVPOL) 
#>     (CVPOL is the bias-corrected MPOL obtained by approximated cross-validation) 
#>  
#>   pred. times  N at risk  N events     MPOL    CVPOL
#>             1        300       150 1.783568 1.820909
#>             3        299       150 1.826218 1.863911
#>             5        291       149 2.017346 2.053467
#>             7        258       127 1.815015 1.834995
#>             9        205       107 1.883315 1.904648
#>            11        158        81 1.712072 1.736993
#>            13        129        68 1.779851 1.784635
#>            15         99        49 1.492382 1.499277
#>  
plot(cvpl,bty="l",ylim=c(0,2))

# }