adoptr

adoptr-package

The adoptr package provides functionality to explore custom optimal
two-stage designs for one- or two-arm superiority tests.
Currently, only (asymptotically) normal test statistics are supported.
For more details on the theoretical background see
&lt;doi:10.1002/sim.8291&gt;.
adoptr makes heavy use of the S4 class system.
A good place to start learning about it can be found
<a href="http://adv-r.had.co.nz/OO-essentials.html">here</a>.

Optimize one or two-arm, two-stage designs for clinical trials with
respect to several pre-implemented objective criteria or implement custom
objectives.
Optimization under uncertainty and conditional (given stage-one outcome)
constraints are supported.
See Pilz M, Kunzmann K, Herrmann C, Rauch G, Kieser M. A variational
approach to optimal two-stage designs. Statistics in Medicine. 2019;1<e2><80><93>13.
<doi:10.1002/sim.8291> for details.

Kevin Kunzmann

Adaptive Optimal Two-Stage Designs in R

Maximilian Pilz

adoptr function

For a sample workflow and a quick demo of the capabilities, see
<a href="https://kkmann.github.io/adoptr/articles/adoptr.html">here</a>.
A variety of examples is presented in the validation report hosted
<a href="https://kkmann.github.io/adoptr-validation-report/">here</a>.

Quickstart

adoptr currently supports <code><a rd-options="" href="/link/TwoStageDesign?package=adoptr&version=0.2.2" data-mini-rdoc="adoptr::TwoStageDesign">TwoStageDesign</a></code>,
<code><a rd-options="" href="/link/GroupSequentialDesign?package=adoptr&version=0.2.2" data-mini-rdoc="adoptr::GroupSequentialDesign">GroupSequentialDesign</a></code>, and <code><a rd-options="" href="/link/OneStageDesign?package=adoptr&version=0.2.2" data-mini-rdoc="adoptr::OneStageDesign">OneStageDesign</a></code>.

Designs

Currently, the only implemented data distribution is <code><a rd-options="" href="/link/Normal?package=adoptr&version=0.2.2" data-mini-rdoc="adoptr::Normal">Normal</a></code>
(one or two arms).

Data distributions

Both <code><a rd-options="" href="/link/ContinuousPrior?package=adoptr&version=0.2.2" data-mini-rdoc="adoptr::ContinuousPrior">ContinuousPrior</a></code> and <code><a rd-options="" href="/link/PointMassPrior?package=adoptr&version=0.2.2" data-mini-rdoc="adoptr::PointMassPrior">PointMassPrior</a></code> are
supported for the single parameter of a <code><a rd-options="" href="/link/DataDistribution?package=adoptr&version=0.2.2" data-mini-rdoc="adoptr::DataDistribution">DataDistribution</a></code>.

Priors

See <code><a rd-options="" href="/link/Scores?package=adoptr&version=0.2.2" data-mini-rdoc="adoptr::Scores">Scores</a></code> for information on the basic system of representing
scores.
Available scores are <code><a rd-options="" href="/link/ConditionalPower?package=adoptr&version=0.2.2" data-mini-rdoc="adoptr::ConditionalPower">ConditionalPower</a></code>,
<code><a rd-options="" href="/link/ConditionalSampleSize?package=adoptr&version=0.2.2" data-mini-rdoc="adoptr::ConditionalSampleSize">ConditionalSampleSize</a></code>, <code><a rd-options="" href="/link/Power?package=adoptr&version=0.2.2" data-mini-rdoc="adoptr::Power">Power</a></code>, and
<code><a rd-options="" href="/link/ExpectedSampleSize?package=adoptr&version=0.2.2" data-mini-rdoc="adoptr::ExpectedSampleSize">ExpectedSampleSize</a></code>..

Scores

The adoptr package provides functionality to explore custom optimal
two-stage designs for one- or two-arm superiority tests.
Currently, only (asymptotically) normal test statistics are supported.
For more details on the theoretical background see
&lt;doi:10.1002/sim.8291&gt;.
adoptr makes heavy use of the S4 class system.
A good place to start learning about it can be found
<a href='http://adv-r.had.co.nz/OO-essentials.html'>here</a>.

adoptr: Adaptive Optimal Two-Stage Designs

Description

Arguments

Quickstart

Designs

Data distributions

Priors

Scores