In addition to the planning and simulation features ADDPLAN allows for a convenient analysis of user supplied data within an adaptive design. ADDPLAN enables the user to utilize data from an interim analysis to recalculate the sample size of an ongoing trial. The recalculation will follow various methods. ADDPLAN will output relevant summary data in the form of spreadsheets and graphs. The user will have the choice between various forms of interim analysis including:

• hypothesis testing
• sample size recalculation based on various reassessment methods
• computation of overall conditional and predictive power
• computation of maximum likelihood estimates and confidence intervals, or RCIs, respectively
• computation of overall p-values and final analysis adjusted p-values
• recursive combination test designs.

The user may specify one of the following designs for data analysis and sample size recalculation or adaptive redesign, respectively:

• one-sided and two-sided testing of means (paired and unpaired samples)
• one-sided and two-sided testing of proportions (paired and unpaired samples).
• noninferiority and equivalence (TOST) testing of means (difference and ratio specified)
• noninferiority and equivalence (TOST) testing of proportions (difference or relative risk specified)
• survival analysis
• non-inferiority and equivalence (TOST) for survival analysis
• general design, where a p-value or z-value, respectively, must be entered for each stage.

ADDPLAN provides a worksheet that allows the user to choose for which interim analysis summary data will be entered, as well as whether the power is directed towards larger or smaller values of the test parameter.
Depending on the design that was chosen, the user can enter in the worksheet the summary data necessary for performing the interactive analysis. Different worksheets are available to perform the analysis of mean values and standard deviations, rates, hazard ratios, or p-values/ z-values by stage.
All analyses can be done based on the inverse normal method or the classical group sequential method.
ADDPLAN allows the user to choose between the on-hand computation options depending on the type of endpoint (variance equal/unequal variances in case of normal endpoints, Fisher's exact test/normal approximation in case of binary endpoints).
In ADDPLAN, the calculation of sample sizes of subsequent stages is based on two different principles:

• sample size recalculation based on conditional power arguments
• sample size recalculation based on the precision of the resulting RCI.

Sample size recalculation is included for both the observed treatment effect (according to the summary data entered in the worksheet), as well as the assumed treatment effect (any arbitrary effect entered by the user in a separate field on the worksheet).
Another type of adaptive redesign implemented in ADDPLAN is referred to as 'recursive analysis'. This method is based on the idea of computing the conditional type I error rate at a specific stage and using this value for redesigning the trial for later stages.
Two different types of overall p-values are available in ADDPLAN. First, the overall p-value, which is defined as the lowest significance level at a specific stage for which the summary data entered in the worksheet yield rejection of the corresponding null hypothesis within the specified group sequential test design. Second, the final analysis adjusted p-value based on the Tsiatis, Rosner, Mehta stagewise ordering principle. The final confidence interval based on this ordering, as well as the median unbiased estimate is provided. These are computable at the final analysis only.
Graphical output comprises plots of stopping boundaries along with test statistics, and plots of the conditional power vs effect.
Additional features:
ADDPLAN provides the cumulative distribution functions for a range of common distributions:
ADDPLAN also provides the critical values for test designs based on Fisher's combination test principle.
A Help menu is implemented that provides online help functionality, including parts of the user's manual.