wlrt {nphRCT} | R Documentation |
Weighted log-rank test
Description
This function can perform two types of weighted log-rank test,
the modestly-weighted log-rank test and the Fleming-Harrington (\rho
,\gamma
) test, in addition to the standard log-rank test.
Usage
wlrt(
formula,
data,
method,
t_star = NULL,
s_star = NULL,
rho = NULL,
gamma = NULL,
timefix = TRUE
)
Arguments
formula |
Formula object. The response (on the left of the |
data |
Data frame containing time-to-event data. |
method |
Character string specifying type of weighted log-rank test.
Either |
t_star |
Parameter |
s_star |
Parameter |
rho |
Parameter |
gamma |
Parameter |
timefix |
Deal with floating point issues (as in the survival package). Default is TRUE. May need to set FALSE for simulated data. |
Details
Select which of the three tests to perform using argument method
.
The output is calculated as outlined in vignette("weighted_log_rank_tests", package="wlrt")
.
Value
List containing the outcome of the weighted log-rank test.
-
u
is the test statistic U for the weighted log-rank test -
v_u
is the variance of test statistic U -
z
is the Z-score -
trt_group
indicates which of the treatment arms the test statistic U corresponds to
In the presence of multiple strata, the results of the test on each individual strata is returned, in addition to the combined test that was proposed by
Magirr and Jiménez (2022), see vignette("weighted_log_rank_tests", package="wlrt")
.
References
Magirr, D. (2021). Non-proportional hazards in immuno-oncology: Is an old perspective needed?. Pharmaceutical Statistics, 20(3), 512-527. doi:10.1002/pst.2091
Magirr, D. and Burman, C.F., 2019. Modestly weighted logrank tests. Statistics in medicine, 38(20), 3782-3790.
Magirr, D. and Jiménez, J. (2022) Stratified modestly-weighted log-rank tests in settings with an anticipated delayed separation of survival curves PREPRINT at https://arxiv.org/abs/2201.10445
Examples
library(nphRCT)
set.seed(1)
sim_data <- sim_events_delay(
event_model=list(
duration_c = 36,
duration_e = c(6,30),
lambda_c = log(2)/9,
lambda_e = c(log(2)/9,log(2)/18)
),
recruitment_model=list(
rec_model="power",
rec_period = 12,
rec_power = 1
),
n_c=50,
n_e=50,
max_cal_t = 36
)
#example setting t_star
wlrt(formula=Surv(event_time,event_status)~group,
data=sim_data,
method="mw",
t_star = 4
)
#example setting s_star
wlrt(formula=Surv(event_time,event_status)~group,
data=sim_data,
method="mw",
s_star = 0.5
)
#example with 1 strata
sim_data_0 <- sim_data
sim_data_0$ecog=0
sim_data_1 <- sim_events_delay(
event_model=list(
duration_c = 36,
duration_e = c(6,30),
lambda_c = log(2)/6,
lambda_e = c(log(2)/6,log(2)/12)
),
recruitment_model=list(
rec_model="power",
rec_period = 12,
rec_power = 1
),
n_c=50,
n_e=50,
max_cal_t = 36
)
sim_data_1$ecog=1
sim_data_strata<-rbind(sim_data_0,sim_data_1)
wlrt(formula=Surv(event_time,event_status)~group+strata(ecog),
data=sim_data_strata,
method="mw",
t_star = 4
)
#example with 2 strata
sim_data_strata_2<-cbind(sim_data_strata,sex=rep(c("M","F"),times=100))
wlrt(formula=Surv(event_time,event_status)~group+strata(ecog)+strata(sex),
data=sim_data_strata_2,
method="mw",
t_star = 4
)