seqBound: Sequential bounds for cumulative Z-test in Group Sequential...

In sasLM: 'SAS' Linear Model

Sequential bounds for cumulative Z-test in Group Sequential Design

Description

Sequential upper bounds for cumulative Z-test on accumaltive data. Z values are correlated. This is usually used for group sequential design.

Usage

  seqBound(ti, alpha = 0.05, side = 2, t2 = NULL, asf = 1)

Arguments

ti	times for test. These should be [0, 1].
alpha	goal alpha value for the last test at time 0.
side	1=one-side test, 2=two-side test
t2	fractions of information amount. These should be [0, 1]. If not available, ti will be used instead.
asf	alpha spending function. 1=O'Brien-Flemming, 2=Pocock, 3=alpha*ti, 4=alpha*ti^1.5, 5=alpha*ti^2

Details

It calculates upper z-bounds and cumulative alpha-values for the repeated test in group sequential design. The correlation is assumed to be sqrt(t_i/t_j).

Value

The result is a matrix.

ti	time of test
bi	upper z-bound
cum.alpha	cumulative alpha-value

Author(s)

Kyun-Seop Bae [e-mail]

References

Reboussin DM, DeMets DL, Kim K, Lan KKG. Computations for group sequential boundaries using the Lan-DeMets function method. Controlled Clinical Trials. 2000;21:190-207.

Examples

  seqBound(ti=(1:5)/5)
  seqBound(ti=(1:5)/5, asf=2)

sasLM documentation built on Oct. 2, 2024, 9:06 a.m.