conditional.power: Conditional power for sequential tests.

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

Conditional power for sequential tests.

Description

Compute conditional power for Sequential tests in clinical trials.

Usage

  conditional.power(tk=0, theta=0.5, sig.level=0.025, power = 0.8, tm = 0.5)

# Conditional power for survival analysis
#
  cpower.surv(hrk = 1.0, HR = 0.7, sig.level = 0.025, power = 0.8, tm = 0.5) 
#
#
# Conditional power for t-test
#
  cpower.tt(muk = 0.0, mu = 0.7, sig.level = 0.025, power = 0.8, 
      tm = 0.5, sigma = 1.0, cc.ratio = 1) 
#
#

Arguments

cc.ratio	Control / case ratio, default is 1
sig.level	Significance level (Type I error probability)
power	Power of test (1 minus Type II error probability)
HR	Target hazards ratio for survival outcome
mu	Target difference for continuous outcome
sigma	Standard error for continuous outcome
theta	Difference under althernative hypothesis
muk	Difference in mean for the k^th interim analysis
tk	Test statistics Tk for the k^th interim analysis
hrk	Observed harzards ratio for the k^th interim analysis
tm	Time of the k^th test (percentage of information)

Details

Calculate conditional power for sequential tests in clinical trials to provide information on whether or not to futile a study. The algorithm is based on methods by Jennison and Turnbull (2000) Chapter 10, page 207-220.

Value

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

case.control	A vector for number of cases and controls
n.total	Total number of sample size for the study
cpower.low	Lower conditional power for one-sided futility analysis
cpower.up	Upper conditional power for one-sided futility analysis
cpower	Conditional power for two-sided test
Power	Power of the test
I.max	Maximum information at the final analysis
zk	Standardized test statistics Zk at the k^th interim analysis
time	Time of the k^th interim analysis

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

Jennison C. and Turnbull B. W. (2000). Group Sequential methods applications to clinical trials.

See Also

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

Examples

# Example
conditional.power(tk=0, theta=0.5, sig.level=0.05, power = 0.8, tm = 0.5)

statapps/power.ctepd documentation built on April 26, 2024, 3:22 a.m.