Formula parsing and updating

Hi all,
I can't come over a problem with formula. Suppose I have a coxmod model
with the following formula:

somemod$formula

Surv(lebzeit, tot == 1) ~ sex + (alter >= 65) + diff3k + zelltyp_k_c +
   q_nuc_3k + kar_k80_g80 + stadium

example(coxph)
test1$quant <- rnorm(length(test1$sex))
fit <- coxph( Surv(time, status) ~ x + (quant>0) + strata(sex), test1)

fit <- coxph( Surv(time, status) ~ x + I(quant>0) + strata(sex), test1)
update(fit,".~.-x")

and I want to drop the stadium explanatory variable from the model with

update(somemod, ". ~ . - stadium")

I get the following messages:

Fehler in coxph(formula = Surv(lebzeit, tot == 1) ~ sex + alter >= 65 +  :
 No (non-missing) observations
Zus?tzlich: Warning messages:
1: In Ops.factor(sex, alter) : + not meaningful for factors
2: In Ops.factor(65, diff3k) : + not meaningful for factors
3: In Ops.factor(65 + diff3k, zelltyp_k_c) : + not meaningful for factors
4: In Ops.factor(65 + diff3k + zelltyp_k_c, q_nuc_3k) :
 + not meaningful for factors
5: In Ops.factor(65 + diff3k + zelltyp_k_c + q_nuc_3k, kar_k80_g80) :
 + not meaningful for factors

What seems to happen is that "alter >= 65" is not parsed as an entity.

It does not look as a problem with the environment to me, as is outlined
in http://developer.r-project.org/nonstandard-eval.pdf, rather a parsing
problem.

By contrast, the following works like a charm:

x <- runif(50)
y <- rnorm(50)+x
regmod <- lm(y ~ x)
update(regmod, " . ~ . + (ifelse(x>.5, 0, x))")

Could anybody give me a hint on my wrongdoings?

-- 
Johannes H?sing               There is something fascinating about science.
                             One gets such wholesale returns of conjecture
mailto:johannes at huesing.name  from such a trifling investment of fact.
http://derwisch.wikidot.com         (Mark Twain, "Life on the Mississippi")

On Thu, 4 Dec 2008, Johannes Huesing wrote:

somemod$formula

Surv(lebzeit, tot == 1) ~ sex + (alter >= 65) + diff3k + zelltyp_k_c +
   q_nuc_3k + kar_k80_g80 + stadium

You need to give us something to reproduce. I get an error when I try

example(coxph)
test1$quant <- rnorm(length(test1$sex))
fit <- coxph( Surv(time, status) ~ x + (quant>0) + strata(sex), test1)

Error in model.matrix.default(newTerms, m) :
  model frame and formula mismatch in model.matrix()

When I protect with I(quant>0), I have no problems obtaining 'fit' nor  
update()ing it: