ordcrm: Likelihood-Based Continual Reassessment Method (CRM) Dose Finding Designs

Provides the setup and calculations needed to run a likelihood-based continual reassessment method (CRM) dose finding trial and performs simulations to assess design performance under various scenarios. 3 dose finding designs are included in this package: ordinal proportional odds model (POM) CRM, ordinal continuation ratio (CR) model CRM, and the binary 2-parameter logistic model CRM. These functions allow customization of design characteristics to vary sample size, cohort sizes, target dose-limiting toxicity (DLT) rates, discrete or continuous dose levels, combining ordinal grades 0 and 1 into one category, and incorporate safety and/or stopping rules. For POM and CR model designs, ordinal toxicity grades are specified by common terminology criteria for adverse events (CTCAE) version 4.0. Function 'pseudodata' creates the necessary starting models for these 3 designs, and function 'nextdose' estimates the next dose to test in a cohort of patients for a target DLT rate. We also provide the function 'crmsimulations' to assess the performance of these 3 dose finding designs under various scenarios.

AuthorEmily V. Dressler, PhD Zhengyan Huang
Date of publication2016-11-04 23:54:11
MaintainerEmily V. Dressler <EmilyVDressler@gmail.com>
LicenseGPL (>= 2)
Version1.0.0

View on CRAN

Questions? Problems? Suggestions? or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.