Markov Chain Monte Carlo (MCMC) to run Bayesian split population survival model with no frailties.
Returns a summary of a SPsurv object via summary.mcmc.
Print method for a pooledSPsurv x.
Returns a plot of a pooledSPsurv object via plot.mcmc.
pooledSPsurv( duration, immune, Y0, LY, data, N, burn, thin, w = c(1, 1, 1), m = 10, ini.beta = 0, ini.gamma = 0, form = c("Weibull", "exponential", "loglog") ) # S3 method for SPsurv summary(object, parameter = character(), ...) # S3 method for SPsurv print(x, ...) # S3 method for SPsurv plot(x, parameter = character(), ...)
| duration | survival stage equation written in a formula of the form Y ~ X1 + X2 + ... where Y is duration until failure or censoring. |
|---|---|
| immune | split stage equation written in a formula of the form C ~ Z1 + Z2 + ... where C is a binary indicator of immunity. |
| Y0 | the elapsed time since inception until the beginning of time period (t-1). |
| LY | last observation year (coded as 1; 0 otherwise) due to censoring or failure. |
| data | data.frame. |
| N | number of MCMC iterations. |
| burn | burn-in to be discarded. |
| thin | thinning to prevent from autocorrelation. |
| w | size of the slice in the slice sampling for (betas, gammas, rho). Write it as a vector. E.g. c(1,1,1). |
| m | limit on steps in the slice sampling. A vector of values for beta, gamma, rho. |
| ini.beta | initial value for the parameter vector beta. By default is 0. |
| ini.gamma | initial value for the parameter vector gamma. By default is 0. |
| form | type of parametric model (Weibull, Exponential, or Log-Logistic). |
| object | an object of class |
| parameter | one of Four parameters of the |
| ... | additional parameter. |
| x | an object of class |
pooledSPsurv returns an object of class "SPsurv".
A "pooledSPsurv" object has the following elements:
matrix, numeric values of the posterior for each variable in the duration equation .
matrix, numeric values of the posterior for each variable in the immune equation.
vector, numeric values of rho.
vector, numeric values of delta.
matrix of X's variables.
matrix of Z's variables.
vector of `Y'.
vector of `Y0'.
vector of `C'.
numeric initial value of beta.
numeric initial value of gamma.
character, type of distribution.
description for the model to be estimated.
# \donttest{ walter <- spduration::add_duration(Walter_2015_JCR,"renewed_war", unitID = "ccode", tID = "year", freq = "year", ongoing = FALSE)#> Warning: Converting to 'Date' class with yyyy-06-30set.seed(123456) model <- pooledSPsurv( duration = duration ~ fhcompor1 + lgdpl + comprehensive + victory + instabl + intensityln + ethfrac + unpko, immune = cured ~ fhcompor1 + lgdpl + victory, Y0 = 't.0', LY = 'lastyear', data = walter, N = 100, burn = 10, thin = 10, w = c(1,1,1), m = 10, form = "Weibull" ) print(model)#> Call: #> pooledSPsurv(duration = duration ~ fhcompor1 + lgdpl + comprehensive + #> victory + instabl + intensityln + ethfrac + unpko, immune = cured ~ #> fhcompor1 + lgdpl + victory, Y0 = "t.0", LY = "lastyear", #> data = walter, N = 100, burn = 10, thin = 10, w = c(1, 1, #> 1), m = 10, form = "Weibull") #> #> #> Iterations = 1:9 #> Thinning interval = 1 #> Number of chains = 1 #> Sample size per chain = 9 #> #> Empirical mean and standard deviation for each variable, #> plus standard error of the mean: #> #> #> Duration equation: #> Mean SD Naive SE Time-series SE #> (Intercept) 1.69150492 1.13842191 0.37947397 0.72836286 #> fhcompor1 -0.95879645 0.71976455 0.23992152 0.23992152 #> lgdpl -0.01711938 0.10324308 0.03441436 0.03308852 #> comprehensive -0.88064889 0.48338727 0.16112909 0.16112909 #> victory 0.36350782 0.58901831 0.19633944 0.19633944 #> instabl 0.68810472 0.60268434 0.20089478 0.20089478 #> intensityln 0.10202337 0.05913569 0.01971190 0.01202436 #> ethfrac -0.21938349 0.70877869 0.23625956 0.23625956 #> unpko 0.84936611 0.65902802 0.21967601 0.21967601 #> #> Immune equation: #> Mean SD Naive SE Time-series SE #> (Intercept) 0.7645582 1.878438 0.6261459 1.2225668 #> fhcompor1 3.4480967 4.610149 1.5367162 2.8349533 #> lgdpl -3.1381824 2.568191 0.8560636 0.8560636 #> victory -0.6346364 3.068650 1.0228834 1.0228834 #>#> #> Iterations = 1:9 #> Thinning interval = 1 #> Number of chains = 1 #> Sample size per chain = 9 #> #> 1. Empirical mean and standard deviation for each variable, #> plus standard error of the mean: #> #> Mean SD Naive SE Time-series SE #> (Intercept) 1.69150 1.13842 0.37947 0.72836 #> fhcompor1 -0.95880 0.71976 0.23992 0.23992 #> lgdpl -0.01712 0.10324 0.03441 0.03309 #> comprehensive -0.88065 0.48339 0.16113 0.16113 #> victory 0.36351 0.58902 0.19634 0.19634 #> instabl 0.68810 0.60268 0.20089 0.20089 #> intensityln 0.10202 0.05914 0.01971 0.01202 #> ethfrac -0.21938 0.70878 0.23626 0.23626 #> unpko 0.84937 0.65903 0.21968 0.21968 #> #> 2. Quantiles for each variable: #> #> 2.5% 25% 50% 75% 97.5% #> (Intercept) -0.13664 1.06496 1.84080 2.326544 3.27727 #> fhcompor1 -2.08731 -1.58665 -0.80098 -0.589260 -0.05586 #> lgdpl -0.14048 -0.07796 -0.02347 -0.003296 0.15663 #> comprehensive -1.69718 -1.12879 -0.88757 -0.601159 -0.27984 #> victory -0.44365 0.25385 0.28800 0.321501 1.45898 #> instabl -0.11008 0.28032 0.66443 1.119573 1.59026 #> intensityln 0.01332 0.06036 0.12142 0.140956 0.17080 #> ethfrac -1.13836 -0.55928 -0.44751 0.427076 0.84619 #> unpko -0.15069 0.51824 0.93883 1.298319 1.71663 #># plot(model) # }