The SEQTEST Procedure
-
Overview
- Getting Started
-
Syntax
-
DetailsInput Data SetsBoundary VariablesInformation Level Adjustments at Future StagesBoundary Adjustments for Information LevelsBoundary Adjustments for Minimum Error SpendingBoundary Adjustments for Overlapping Lower and Upper beta BoundariesStochastic CurtailmentRepeated Confidence IntervalsAnalysis after a Sequential TestAvailable Sample Space Orderings in a Sequential TestApplicable Tests and Sample Size ComputationTable OutputODS Table NamesGraphics OutputODS Graphics
-
ExamplesTesting the Difference between Two ProportionsTesting an Effect in a Regression ModelTesting an Effect with Early Stopping to Accept H0Testing a Binomial ProportionComparing Two Proportions with a Log Odds Ratio TestComparing Two Survival Distributions with a Log-Rank TestTesting an Effect in a Proportional Hazards Regression ModelTesting an Effect in a Logistic Regression ModelConducting a Trial with a Nonbinding Acceptance Boundary
- References
In the SEQTEST procedure, the 
and 
spending values at the stages are used to derive the boundary values for the trial. For a two-sided design with early stopping
to accept 
, or to either reject or accept , a zero spending at an interim stage sets the boundary values to missing. A small spending at the current or subsequent interim stage might result in overlapping of the lower and upper boundaries for the two corresponding one-sided tests. Specifically, this form of overlapping occurs at an interim stage k if the upper boundary value that is derived from the one-sided test for the upper alternative is less than the lower boundary value that is derived from the one-sided test for the lower alternative (Kittelson and Emerson 1999, pp. 881–882; Rudser and Emerson 2007, p. 6). You can use the BETAOVERLAP= option to specify how this type of overlapping is to be handled.
If BETAOVERLAP=ADJUST (which is the default) is specified, the procedure derives the boundary values for the two-sided design
and then checks for overlapping of the two one-sided boundaries at the current and subsequent interim stages. If overlapping occurs at a particular stage, the boundary values for the two-sided design are set to missing (so the trial does not stop to accept the null hypothesis at
this stage), and the spending values at subsequent stages are adjusted proportionally as follows.
If the boundary values are set to missing at stage k in a K-stage trial, the adjusted spending value at stage k, 
, is updated for these missing boundary values, and then the spending values at subsequent stages are adjusted proportionally by
![\[ e’_{j} = e’_{k} + \frac{e_{j}-e_{k}}{e_{K}-e_{k}} \; (e_{K}-e’_{k}) \]](images/statug_seqtest0112.png){kind=small}
for 
, where 
and 
are cumulative spending values at stage j before and after the adjustment, respectively.
After all these adjusted spending values are computed, the boundary values are then further modified for these adjusted spending values.
If you specify BETAOVERLAP=NOADJUST, no adjustment is made when overlapping of one-sided boundaries occurs.