LoginSign Up
← Back to all sparks
P

PowerTOST

INFRA · APIS
Velocity0.0

Power and Sample Size for (Bio)Equivalence Studies

github.com/detlew/powertost ↗

A bioequivalence sample-size workhorse whose news is which regulator it now covers

bioequivalencesample-sizeregulatorypharmacometricsmaintenance
◆Current state
PowerTOST computes power and sample size for bioequivalence and its changelog reads as a record of regulatory divergence more than statistical development. Version 1.5-3 added the Gulf Co-operation Council as a regulator setting; 1.5-4 and 1.5-6 stripped 'FDA' out of the narrow-therapeutic-index function names once China's CDE began requiring the same evaluation. The most recent release, 1.5-7, is a single fix to how nvec() splits a total sample size across sequences.
◆Where it's heading
The package is in long maintenance with a widening regulatory surface: the statistical methods are settled, and releases arrive when an agency publishes a framework that can be expressed as a settings variant of an existing method. Function naming has been deliberately decoupled from any single agency, with the deprecated FDA-suffixed aliases carried for years before removal. Cadence has slowed to roughly one release every eighteen months.
◆Prediction
The next release is most likely another regulator setting or a small fix; on the deprecation notice already given, the power.NTIDFDA()-style aliases are the obvious removal candidate.

◆Recent moves

  1. 10mo ago

    Fix for splitting total sample size across sequences

    A single bug fix in nvec() covering how a total sample size is divided into subjects per sequence. The only release in eighteen months, and it leaves the methods untouched.

    View source ↗
  2. 2y ago

    NTID functions renamed off the FDA acronym; GCC guidance in vignettes

    Completes the de-acronyming of the narrow-therapeutic-index functions now that China's CDE requires the same evaluation, recodes shadowtext() locally after TeachingDemos was orphaned, and makes the group-by-treatment interaction significance level a parameter instead of a hard-coded 0.1. Consistent with the package treating regulators as interchangeable settings.

    View source ↗
  3. 4y ago

    power.NTID() aliases added; FDA-suffixed names deprecated

    Introduces the agency-neutral NTID aliases and marks the FDA-named originals for removal, the naming half of the move 1.5-6 finished. Also fixes vectorization of CV and theta0 in power.TOST().

    View source ↗
  4. 5y ago

    Gulf Co-operation Council added as a regulator setting

    Adds GCC as a regulator, handled as a special case of average bioequivalence with expanding limits rather than as new machinery, and adapts scABEL.ad() and its sample-size counterpart accordingly. Another jurisdiction mapped onto an existing framework, which is the pattern this package has followed for years.

    View source ↗
  5. 5y ago

    Maintenance release with vignette and documentation clarifications

    Bug fixes and clarifications, the most useful being an explicit statement that every sampleN function returns a total sample size rather than subjects per sequence or group. Note the feed's ordering lies here: this version reached CRAN in August 2020, before both 1.5-1 and 1.5-2, despite carrying a later timestamp.

    View source ↗
  6. 5y ago

    stringsAsFactors fix for older R in a vignette example

    A vignette-only fix for a data.frame default that errored on an outdated macOS R build. No functional change to the package.

    View source ↗