gamlss绘制平滑的基线危险

时间:2017-10-27 10:17:26

标签: r survival-analysis

如何在拟合

之后的离散生存函数后得到“平滑”基线危险的图表
burr<- function(xi) {
    linkfun <-function(mu) log(((1-mu)^(-xi)-1)/xi)
    linkinv <- function(eta) 1-(1+xi*exp(eta))^(-1/xi)
    mu.eta <- function(eta) exp(eta)*(1+xi*exp(eta))^(-1/xi-1) 
    valideta <- function(eta) TRUE
    link <- "burr"
    structure(list(linkfun = linkfun, linkinv = linkinv, mu.eta = mu.eta,
                   valideta = valideta, name = link), class = "link-gamlss") }

model00 <- gamlssNP(y ~ cs(FS$t,df=3)+v1+v2, 
             random=~1|id,family=BI(mu.link=burr(5)),  
             data=FS, K=1, mixture="gq", tol=0.5, 
             control = NP.control(EMcc=0.001, trace=FALSE), 
             g.control = gamlss.control(trace=FALSE))

0 个答案:

没有答案