power.2surv.test: Power and sample size for survival distribution (Two-sample)

In statapps/power.ctepd: Power and sample size for clinical trials and epidemiology

Description

Compute power and sample size of test or determine distribution of alternative hypothesis to obtain target power (same as power.surv.test).

Usage

power.2surv.test(n = NULL, sig.level = 0.05, hr = NULL, s0 = 0.7,
          year = 3, accrual = 3, followup = 3, power = NULL, ct.ratio = 1,
          ia.adj = 1.0, alternative = c("two.sided", "one.sided"),
          tol = .Machine$double.eps^0.25)

Arguments

n	Number of observations
year	Time point in which survival function is evaluated, default is 3
s0	Survival function at yaer = year under H0, default is 0.7
hr	Hazard ratio
accrual	Years of accrual, default is 3 years
followup	Years of followup, default is 3 years
sig.level	Significance level (Type I error probability)
power	Power of test (1 minus Type II error probability)
ct.ratio	Control / treatment ratio, default is 1
ia.adj	Ajdusted for interim analysis, default is 1 (no adjustment), ia.adj must > or = 1
alternative	Alternative, either two-sided or one-sided, default is two-sided
tol	tol for uniroot function

Details

These calculations use Poisson process and person-year under exponentioal distribution.

Exactly one of the parameters 'n','power' and 'hr' must be passed as NULL, and that parameter is determined from the others. Notice that the last one has non-NULL default so NULL must be explicitly passed if you want to compute it.

Value

Object of class 'power.htest', a list of the arguments (including the computed one) augmented with 'method' and 'note' elements.

n.trt	Sample size for the treatment arm
n.ctl	Sample size for control arm
s1	Survival rate for the treatment arm
s0	Survival rate for control arm
delta	Survival benefit at year = year
n.annual	Annual accrual rate
n.event	Total number of events required

Note

'uniroot' is used to solve power equation for unknowns, so you may see errors from it, notably about inability to bracket the root when invalid arguments are given.

Author(s)

Bingshu E. Chen ([e-mail])

References

1. Lawless, J. Statistical Models and Methods for Lifetime Data, John Wiley and Sons, 1982.

2. Chow, S. C., Shao, J. and Wang, H. S. Sample szie calculations in clinical research (second edition, 2008). page 177. equation 7.3.6

See Also

power.t.test, power.surv.test, pwr.2p.test

Examples

##
pw = power.2surv.test(power = 0.8, s0 = 0.83, hr = 0.75, year = 5)
print(pw, digits = 4)

statapps/power.ctepd documentation built on July 30, 2020, 6:05 p.m.