问R中具有时变协变量的全参数比例风险模型的拟合

EN

> # Input parameters
> n <- 100         # Number of individuals
> t_max <- 5       # max number of period per individual
> beta <- c(-1, 1) # true coefficient
> 
> # Simulate data
> set.seed(47261114)
> sim_dat <- replicate(
+   n, 
+   {
+     out <- data.frame(
+       tstart = rep(NA_integer_, t_max), 
+       tstop  = rep(NA_integer_, t_max),
+       event  = rep(NA, t_max),
+       x      = rnorm(t_max))
+     
+     for(i in 1:t_max){
+       rate     <- exp(beta %*% c(1, out$x[i]))
+       tstop <- min(rexp(1, rate), 1)
+       out[i, ] <- list(i - 1, i - (1 - tstop),  tstop < 1, out$x[i])
+       if(out$event[i])
+         break
+     }
+     out[!is.na(out$tstart), ]
+   }, simplify = FALSE)
> 
> sim_dat <- do.call(rbind, sim_dat)
> head(sim_dat) # show final data
  tstart     tstop event          x
1      0 0.3018182  TRUE  0.7095841
2      0 0.6724803  TRUE  1.5152877
3      0 1.0000000 FALSE  0.1036868
4      1 2.0000000 FALSE -0.5214508
5      2 2.4831577  TRUE  1.0101403
6      0 1.0000000 FALSE  0.1437594
> 
> # Fit with glm
> glm(event ~ x + offset(log(tstop - tstart)), sim_dat, family = poisson())

Call:  glm(formula = event ~ x + offset(log(tstop - tstart)), family = poisson(), 
    data = sim_dat)

Coefficients:
(Intercept)            x  
    -0.9053       0.9714  

Degrees of Freedom: 248 Total (i.e. Null);  247 Residual
Null Deviance:      382.5 
Residual Deviance: 306.4    AIC: 498.4