Dear all
I am estimating a Cox model with frailty. I am running Splus 2000 under
Windows 98 in a Pentium III (128 MB RAM). When I run the model, the
program says that the "inner loop failed to converge". Can you help me
with this? Is that a problem?
Thanks
Jaime Gomez.
The results of running the model follow:
Call:
coxph(formula = Surv(ANOI, ANOF, CENSURA) ~ log(SIZE) + INTER + PROFI +
PROXIC + PROXIE + DENSI + MGROW + DEPHA + OBJEH + NUMSB + CMOBC +
NMARK + (NMARK^2) + frailty(NCAJA), data = AVER, na.action = na.omit,
eps = 0.0001, iter.max = 100, method = "efron")
coef se(coef) se2 Chisq DF p
log(SIZE) 1.337246 0.161832 0.146554 68.28 1.0 2.2e-016
INTER 2.224514 1.706520 1.585002 1.70 1.0 1.9e-001
PROFI 0.374407 0.212975 0.197735 3.09 1.0 7.9e-002
PROXIC 2.524886 0.201795 0.200045 156.55 1.0 0.0e+000
PROXIE 1.739035 0.233397 0.232317 55.52 1.0 9.3e-014
DENSI -0.000201 0.000607 0.000606 0.11 1.0 7.4e-001
MGROW 0.003407 0.025043 0.024962 0.02 1.0 8.9e-001
DEPHA 0.084440 0.495170 0.491879 0.03 1.0 8.6e-001
OBJEH -2.960687 1.825344 1.819987 2.63 1.0 1.0e-001
NUMSB -0.100384 0.026414 0.026341 14.44 1.0 1.4e-004
CMOBC -12.766192 3.991228 3.162052 10.23 1.0 1.4e-003
NMARK 0.014706 0.047282 0.043106 0.10 1.0 7.6e-001
I(NMARK^2) -0.000160 0.000830 0.000770 0.04 1.0 8.5e-001
frailty(NCAJA) 63.44 24.6 2.8e-005
Iterations: 6 outer, 411 Newton-Raphson
Variance of random effect= 0.571 EM likelihood = -1053.1
Degrees of freedom for terms= 0.8 0.9 0.9 1.0 1.0 1.0 1.0 1.0
1.0 1.0 0.6 0.8 0.9 24.6
Likelihood ratio test=952 on 36.36 df, p=0 n= 34529
Warning messages:
Inner loop failed to coverge for iterations 1 2 3 4 in:
coxpenal.fit(X, Y, strats, offset, init = init, iter.max = iter.max,
outer.max =
outer.max, eps = eps, toler.chol = toler.chol, weights = ...
|