Skip to contents

Integration Point: Multiplicity Adjustment

Gabriel Potvin

May 27, 2026

IntegrationPointMultiplicityAdjustment.Rmd

←\leftarrow Go back to the Getting Started: Overview page

Description

The Multiplicity Adjustment integration point allows you to customize how multiple hypotheses are adjusted for Type I error control, instead of relying on East Horizon’s default Fixed Sequence or Fallback methods. For example, you could implement alternative strategies such as Bonferroni, Holm, Hochberg, or graphical approaches.

Availability

East Horizon Explore

This integration point is available in East Horizon Explore for the following study objectives and endpoint types:

Time to Event Time to Event with Stratification Binary Continuous Continuous with Repeated Measures Count Composite Categorical Dual TTE-TTE Dual TTE-Binary
Dose Escalation - - ❌ - - - - - - -
Dose Finding - - ❌ ❌ - - - - - -
Multiple Arm Confirmatory ❌ - ❌ ❌ - - - - - -
One Arm Exploratory / Confirmatory ❌ - ❌ ❌ - ❌ - ❌ - -
Two Arm Confirmatory ❌ ❌ ❌ ❌ ❌ ❌ - - ✅ ✅
Two Arm Confirmatory - Multiple Endpoints ❌* - ❌* ❌* - - - - - -

*For Multiple Endpoints, you can use the Integration Point: Design to implement your own multiplicity method.

East Horizon Design

This integration point is not available in East Horizon Design.

Instructions

In East Horizon Explore

You can set up a multiplicity adjustment function under Multiplicity Adjustment in a Design Card while creating or editing an Input Set.

Follow these steps (click to expand/collapse):
  1. Select User Specified-R from the dropdown in the Multiplicity Adjustment field in the Design Card.
  2. Browse and select the appropriate R file (filename.r) from your computer, or use the built-in R Code Assistant to create one. This file should contain function(s) written to perform various tasks to be used throughout your Project.
  3. Choose the appropriate function name. If the expected function is not displaying, then check your R code for errors.
  4. Set any required user parameters (variables) as needed for your function using + Add Variables.
  5. Continue creating your project by specifying scenarios for patient Response, Enrollments, etc.

For a visual guide of where to find the option, refer to the screenshot below:

Input Variables

When creating a custom R script, you can optionally use specific variables provided by East Horizon’s engine itself. These variables are automatically available and do not need to be set by the user, except for the UserParam variable. Refer to the table below for the variables that are available for this integration point, outcome, and study objective.

Variable Type Description
SimData Data Frame Subject data generated in current simulation, one row per subject. To access these variables in your R code, use the syntax: SimData$NameOfTheVariable, replacing NameOfTheVariable with the appropriate variable name. See below for more information.
DesignParam List Input parameters which may be needed to compute test statistics and perform tests. To access these variables in your R code, use the syntax: DesignParam$NameOfTheVariable, replacing NameOfTheVariable with the appropriate variable name. See below for more information.
LookInfo List Input parameters related to multiple looks. Empty when Statistical Design = Fixed Sample, but still mandatory in the functions CyneRgy::GetDecisionString and CyneRgy::GetDecision. See below for more information.
TestStat Named List of Numeric Named List of length equal to the number of endpoints, indicating the value of the test statistic on Wald ﴾Z﴿ scale for each endpoint. For example, TestStat[“Endpoint 1”] is the test statistic for Endpoint 1. This is returned by the Analysis part.
OutList List List of outputs that was returned in the previous look. Only relevant for Statistical Design = Group Sequential. Set to NULL for the first look. See below in the Output Variable.
UserParam List Contains all user-defined parameters specified in the East Horizon interface (refer to the Instructions section). To access these parameters in your R code, use the syntax: UserParam$NameOfTheVariable, replacing NameOfTheVariable with the appropriate parameter name.

Note: “Endpoint 1” is used as a sample endpoint name. It will be the actual endpoint name as specified by the user.

Variables of SimData

Click here to explore the variables of SimData.

Variables of DesignParam

Click here to explore the variables of DesignParam.

Variables of LookInfo

Click here to explore the variables of LookInfo.

Expected Output Variable

East Horizon expects an output of a specific type. Refer to the table below for the expected output for this integration point:

Output Type Description
Decision Vector of Integer Vector of length DesignParam$NumTreatments, containing the boundary crossing decision for each treatment arm:
– 0: No boundary crossed.
– 1: Lower efficacy boundary crossed.
– 2: Upper efficacy boundary crossed.
– 4: Futility boundary crossed (only applicable when Statistical Design = Group Sequential).
OutList List List of outputs to pass to the next look. Only relevant for Statistical Design = Group Sequential. Will be available as input to this function in the next look. See above in the Input Variables.
ErrorCode Integer Optional. Can be used to handle errors in your script:
– 0: No error.
– Positive Integer: Nonfatal error, the current simulation will be aborted, but the next simulation will proceed.
– Negative Integer: Fatal error, no further simulations will be attempted.

Minimal Template

Your R script could contain a function such as this one, with a name of your choice. All input variables must be declared, even if they are not used in the script. We recommend always declaring UserParam and OutList as a default NULL value in the function arguments, as this will ensure that the same function will work regardless of whether the user has specified any custom parameters in the interface and whether or not OutList is used.

A detailed template with step-by-step explanations is available here: Decision.DEP.R

For Statistical Design = Fixed Sample 

PerformMultAdj <- function( SimData, DesignParam, TestStat, OutList = NULL, UserParam = NULL )
{
    nError  = 0 # Error handling (no error)
    
    Decision = list()
    Decision[ EndpointName[[ 1 ]]] = 0 # Initialize decision for endpoint 1
    Decision[ EndpointName[[ 2 ]]] = 0 # Initialize decision for endpoint 2
    
    # Write the actual code here.
    
    return( list( Decision = as.list( Decision ), ErrorCode = as.integer( nError )))
}

For Statistical Design = Group Sequential 

PerformMultAdj <- function( SimData, DesignParam, LookInfo, TestStat, OutList = NULL, UserParam = NULL )
{
    nError  = 0 # Error handling (no error)
    
    Decision = list()
    Decision[ EndpointName[[ 1 ]]] = 0 # Initialize decision for endpoint 1
    Decision[ EndpointName[[ 2 ]]] = 0 # Initialize decision for endpoint 2
    
    OutList = list()
    OutList$OutVal = 0 # This value will be passed to the next look
    
    # Write the actual code here.
    
    return( list( Decision = as.list( Decision ), OutList = as.list( OutList ), ErrorCode = as.integer( nError )))
}

Examples

Explore the following examples for more context:

  1. Dual Endpoints - Multiplicity Adjustment