R Survival Analysis: error in survreg using Weibull -
i'm trying replicate survival analysis using weibull distribution have produced in sas - i'm working unlicensed machine using r (both windows). (right censored) input data looks like:
> head(mydata) id key time score event censor 1 1231231 zxc 28 182.34 0 1 2 4564564 asd 28 320.04 0 1 3 7897897 qwe 28 306.32 0 1 4 9879879 qwe 28 211.92 0 1 5 6546546 asd 28 276.14 0 1 6 3213213 zxc 28 331.50 0 1
with event , censor being binaries, score varying between 150 , 450 , time between 1 , 28. there 30,000 rows in input dataset.
when try:
mydatasr <- survreg(surv(time, censor) ~ score, dist = "w")
i warning message:
in survreg.fit(x, y, weights, offset, init = init, controlvals = control, : ran out of iterations , did not converge,
and no output.
i've searched msg online (and through site) have not managed find indicates problem might be. had no convergence issues putting same data through (proc logistic and) lifereg in sas.
it's difficult know in absence of data. can double (or illustrated below, triple) number of iterations defaults 30:
(mydatasr <- survreg(surv(time, censor) ~ score , dist = "w", control = list(maxiter=90) )
see ?survreg.control further options. guessing may have missed surv-object has closing parenthesis before formula-~
Comments
Post a Comment