0

I have created the following model:

data("nwtco")

subcoh <- nwtco$in.subcohort
selccoh <- with(nwtco, rel==1|subcoh==1)
ccoh.data <- nwtco[selccoh,]
ccoh.data$subcohort <- subcoh[selccoh]
ccoh.data$age <- ccoh.data$age/12 # Age in years

fit.ccSP <- cch(Surv(edrel, rel) ~ stage + histol + age, 
                data =ccoh.data,subcoh = ~subcohort, id=~seqno, cohort.size=4028, method="LinYing")

However, I simply can't figure out how to get information on how well the model fits the data.

Does anyone know how to do this?

labna3452388
  • 21
  • 1
  • This doesn't appear to be a specific programming question that's appropriate for Stack Overflow. If you have general questions about assessing the fit for a statistical model, then you should ask such questions over at [stats.se] instead. You are more likely to get better answers there. – MrFlick Mar 29 '21 at 17:21
  • Thanks for the input. The problem, however, is specifically how to get the information from R, i.e. which code to use, since the cch-function makes things more complicated. – labna3452388 Mar 29 '21 at 17:27
  • But what information are you trying to get? How do you want to test the goodness of fit? You should state what exact value you are trying to calculate in the question. – MrFlick Mar 29 '21 at 17:29
  • I see. Ideally, I would for instance like to be able to derive Cox-Snell or Martingale residuals. – labna3452388 Mar 29 '21 at 17:36
  • Maybe `riskRegression` package could help you, but I have a question. Are you triying Proportional hazard Cox Model? – Marcos Pérez Mar 29 '21 at 17:39
  • Thanks for the tip. I'll have a look at the package immediately - any specific functions you were thinking about? And yes, the cch-function fits the proportional hazards model to case-cohort data. – labna3452388 Mar 29 '21 at 17:46

0 Answers0