The SEQDESIGN Procedure
-
Overview
- Getting Started
-
Syntax
-
DetailsFixed-Sample Clinical TrialsOne-Sided Fixed-Sample Tests in Clinical TrialsTwo-Sided Fixed-Sample Tests in Clinical TrialsGroup Sequential MethodsStatistical Assumptions for Group Sequential DesignsBoundary ScalesBoundary VariablesType I and Type II ErrorsUnified Family MethodsHaybittle-Peto MethodWhitehead MethodsError Spending MethodsAcceptance (beta) BoundaryBoundary Adjustments for Overlapping Lower and Upper beta BoundariesSpecified and Derived ParametersApplicable Boundary KeysSample Size ComputationApplicable One-Sample Tests and Sample Size ComputationApplicable Two-Sample Tests and Sample Size ComputationApplicable Regression Parameter Tests and Sample Size ComputationAspects of Group Sequential DesignsSummary of Methods in Group Sequential DesignsTable OutputODS Table NamesGraphics OutputODS Graphics
-
ExamplesCreating Fixed-Sample DesignsCreating a One-Sided O’Brien-Fleming DesignCreating Two-Sided Pocock and O’Brien-Fleming DesignsGenerating Graphics Display for Sequential DesignsCreating Designs Using Haybittle-Peto MethodsCreating Designs with Various Stopping CriteriaCreating Whitehead’s Triangular DesignsCreating a One-Sided Error Spending DesignCreating Designs with Various Number of StagesCreating Two-Sided Error Spending Designs with and without Overlapping Lower and Upper beta BoundariesCreating a Two-Sided Asymmetric Error Spending Design with Early Stopping to Reject H0Creating a Two-Sided Asymmetric Error Spending Design with Early Stopping to Reject or Accept H0Creating a Design with a Nonbinding Beta BoundaryComputing Sample Size for Survival Data That Have Uniform AccrualComputing Sample Size for Survival Data with Truncated Exponential Accrual
- References
The SEQDESIGN procedure assumes that the standardized Z test statistics for the null hypothesis 
at the stages have the joint canonical distribution with the information levels at the stages for the parameter 
. This implies that these test statistics are normally distributed. If the test statistic is not normally distributed, then
it is assumed that the test statistic is computed from a large sample such that the statistic has an approximately normal
distribution. See the section Statistical Assumptions for Group Sequential Designs for a detailed description of the joint canonical distribution.
You can use the SEQDESIGN procedure to compute required sample sizes for commonly used hypothesis tests. Note that for a fixed-sample design, you should use the POWER and GLMPOWER procedures to compute sample sizes.
The applicable tests include tests for binomial proportions and the log-rank test for two survival distributions. See the section Applicable One-Sample Tests and Sample Size Computation, the section Applicable Two-Sample Tests and Sample Size Computation, and the section Applicable Regression Parameter Tests and Sample Size Computation for examples of applicable tests in group sequential trials.
At each stage, the data are analyzed with a statistical procedure such as the REG procedure, and a test statistic and its associated information level are computed. The information level is the amount of information available about the unknown parameter. For a maximum likelihood statistic, the information level is the inverse of its variance.
At each stage, you use the SEQTEST procedure to derive the boundary values that correspond to the information level associated with the test statistic. You then use the SEQTEST procedure to compare the test statistic with these boundary values. When a trial is stopped at an interim stage or at the final stage, the SEQTEST procedure also derives parameter estimates, confidence limits for the parameter, and a p-value for hypothesis testing.