ryusuke
2011-Jul-10 09:37 UTC
[R] Package "survival" --- Difference of coxph strata with subset?
[code]>require("survival")> coxph(Surv(futime,fustat)~age + strata(rx),ovarian)
Call:
coxph(formula = Surv(futime, fustat) ~ age + strata(rx), data = ovarian)
coef exp(coef) se(coef) z p
age 0.137 1.15 0.0474 2.9 0.0038
Likelihood ratio test=12.7 on 1 df, p=0.000368 n= 26, number of events= 12
> coxph(Surv(futime,fustat)~age, ovarian, subset=rx==1)
Call:
coxph(formula = Surv(futime, fustat) ~ age, data = ovarian, subset = rx =1)
coef exp(coef) se(coef) z p
age 0.115 1.12 0.0456 2.52 0.012
Likelihood ratio test=8.68 on 1 df, p=0.00321 n= 13, number of events= 7
> coxph(Surv(futime,fustat)~age, ovarian, subset=rx==2)
Call:
coxph(formula = Surv(futime, fustat) ~ age, data = ovarian, subset = rx =2)
coef exp(coef) se(coef) z p
age 0.351 1.42 0.183 1.92 0.055
Likelihood ratio test=6 on 1 df, p=0.0143 n= 13, number of events= 5
[/code]
May I know why I cant separate
coxph(Surv(futime,fustat)~age + strata(rx),ovarian)
To be
coxph(formula = Surv(futime, fustat) ~ age, data = ovarian, subset = rx
== 1)
coxph(formula = Surv(futime, fustat) ~ age, data = ovarian, subset = rx
== 2)
May I know the difference of these issue? Many thanks...
--
View this message in context:
http://r.789695.n4.nabble.com/Package-survival-Difference-of-coxph-strata-with-subset-tp3657397p3657397.html
Sent from the R help mailing list archive at Nabble.com.
ryusuke
2011-Jul-11 06:32 UTC
[R] Package "survival" --- Difference of coxph strata with subset?
Finally, I found the answer from here... http://www.childrensmercy.org/stats/weblog2005/StratifiedCoxRegression.asp http://www.childrensmercy.org/stats/weblog2005/StratifiedCoxRegression.asp Thernau and Grambsch describe it well in their book on survival analysis. /Analysis of multicenter clinical trials frequently uses stratification. Because of varying patient populations and referral patterns, the different clinical centers in the trial are likely to have difference baseline survival curves, ones that do not have simple parallel relationships. Strata play a role similar to blocks in randomized block designs analyzed by two-factor analysis of variance. (page 44)./ -- View this message in context: http://r.789695.n4.nabble.com/Package-survival-Difference-of-coxph-strata-with-subset-tp3657397p3658798.html Sent from the R help mailing list archive at Nabble.com.