The R Package rpact – Functional Range
![]()
Trial Designs
- Fixed sample design
- Group sequential designs
- Adaptive designs using the inverse normal and Fisher’s combination test, and conditional error rate principle
Easy to understand R commands:
getDesignGroupSequential()
getDesignInverseNormal()
getDesignFisher()
getDesignConditionalDunnett()
Sample Size and Power Calculation
for
- testing means (continuous endpoint)
- testing rates (binary endpoint)
- survival trials with flexible recruitment and survival time options
- testing rates for count data
Easy to understand R commands:
getSampleSize[Means/Rates/Survival/Counts]()
getPower[Means/Rates/Survival/Counts]()
Example:
getSampleSizeMeans()
getPowerMeans()
Adaptive Analysis
for testing means, rates, and survival data
- Calculates adjusted point estimates and confidence intervals
- Some highlights:
- Automatic boundary recalculations during the trial for analysis with alpha spending approach, including under- and over-running
- Adaptive analysis tools for multi-arm trials
- Adaptive analysis tools for enrichment design
Easy to understand R commands:
getStageResults()
getRepeatedConfidenceIntervals()
getAnalysisResults()
…
User Concept – R generics
In general, everything runs with the R standard functions which are always present in R: so-called R generics.
- Visualize:
- Continue work:
as.data.frame()length()names()
User Concept – Most parameters have a default value
Example: getDesignInverseNormal() produces the output:
User Concept – Most parameters have a default value
Example: getDesignInverseNormal(kMax = 2) produces the output:
User Concept – Support of pipe operators
library(rpact)
getDesignGroupSequential() |>
getDataset(dataMeans) |>
getAnalysisResults()
Analysis results (means of one group, group sequential design)
Design parameters
- Information rates: 0.333, 0.667, 1.000
- Critical values: 3.471, 2.454, 2.004
- Futility bounds (non-binding): -Inf, -Inf
- Cumulative alpha spending: 0.0002592, 0.0071601, 0.0250000
- Local one-sided significance levels: 0.0002592, 0.0070554, 0.0225331
- Significance level: 0.0250
- Test: one-sided
Default parameters
- Normal approximation: FALSE
- Direction upper: TRUE
- Theta H0: 0
Stage results
- Cumulative effect sizes: 45.00, 48.60, 47.25
- Cumulative (pooled) standard deviations: 130.0, 134.8, 128.7
- Stage-wise test statistics: 1.548, 1.995, 2.054
- Stage-wise p-values: 0.06905, 0.02774, 0.02455
- Overall test statistics: 1.548, 2.550, 3.285
- Overall p-values: 0.0690533, 0.0069750, 0.0007617
Analysis results
- Assumed standard deviation: 128.7
- Actions: continue, reject and stop, reject
- Conditional rejection probability: 0.08839, 0.50232, NA
- Conditional power: NA, NA, NA
- Repeated confidence intervals (lower): -76.25044, 0.08653, 17.95726
- Repeated confidence intervals (upper): 166.25, 97.11, 76.54
- Repeated p-values: 0.2531791, 0.0247936, 0.0007821
- Final stage: 2
- Final p-value: NA, 0.00708, NA
- Final CIs (lower): NA, 9.421, NA
- Final CIs (upper): NA, 84.18, NA
- Median unbiased estimate: NA, 46.82, NA
