BOWL-class

Class <code>BOWL</code> contains results from a single step of BOWL algorithm.

internal

Methods to estimate dynamic treatment regimes using Interactive
Q-Learning, Q-Learning, weighted learning, and value-search methods based on
Augmented Inverse Probability Weighted Estimators and Inverse Probability
Weighted Estimators. Dynamic Treatment Regimes: Statistical Methods for
Precision Medicine, Tsiatis, A. A., Davidian, M. D., Holloway, S. T., and Laber, E. B.,
Chapman & Hall/CRC Press, 2020, ISBN:978-1-4987-6977-8.

Shannon Holloway

DynTxRegime

Methods for Estimating Optimal Dynamic Treatment Regimes

BOWL-class function

<dl>
<dt><code>step</code></dt>
<dd>Integer indicating step of the algorithm</dd></dl>
<dt><code>analysis</code></dt>
<dd>Contains a Learning or LearningMulti object.</dd>
<dt><code>analysis@txInfo</code></dt>
<dd>Feasible tx information.</dd>
<dt><code>analysis@propen</code></dt>
<dd>Propensity regression analysis.</dd>
<dt><code>analysis@outcome</code></dt>
<dd>Outcome regression analysis.</dd>
<dt><code>analysis@cvInfo</code></dt>
<dd>Cross-validation analysis if single regime.</dd>
<dt><code>analysis@optim</code></dt>
<dd>Optimization analysis if single regime.</dd>
<dt><code>analysis@optimResult</code></dt>
<dd>list of cross-validation and optimization results
if multiple regimes. optimResult[[i]]@cvInfo and optimResult[[i]]@optim.</dd>
<dt><code>analysis@optimal</code></dt>
<dd>Estimated optimal Tx and value.</dd>
<dt><code>analysis@call</code></dt>
<dd>Unevaluated call to statistical method.</dd>
<dt><code>prodPi</code></dt>
<dd>Vector of the products of the propensity for the tx received</dd>
<dt><code>sumR</code></dt>
<dd>Vector of the sum of the rewards</dd>
<dt><code>index</code></dt>
<dd>Vector indicating compliance with estimated optimal regime</dd>

Slots

Class BOWL — BOWL-class

<dl>
<dt><code>step</code></dt>
<dd>Integer indicating step of the algorithm</dd>


<dt><code>analysis</code></dt>
<dd>Contains a Learning or LearningMulti object.</dd>


<dt><code>analysis@txInfo</code></dt>
<dd>Feasible tx information.</dd>


<dt><code>analysis@propen</code></dt>
<dd>Propensity regression analysis.</dd>


<dt><code>analysis@outcome</code></dt>
<dd>Outcome regression analysis.</dd>


<dt><code>analysis@cvInfo</code></dt>
<dd>Cross-validation analysis if single regime.</dd>


<dt><code>analysis@optim</code></dt>
<dd>Optimization analysis if single regime.</dd>


<dt><code>analysis@optimResult</code></dt>
<dd>list of cross-validation and optimization results
if multiple regimes. optimResult[[i]]@cvInfo and optimResult[[i]]@optim.</dd>


<dt><code>analysis@optimal</code></dt>
<dd>Estimated optimal Tx and value.</dd>


<dt><code>analysis@call</code></dt>
<dd>Unevaluated call to statistical method.</dd>


<dt><code>prodPi</code></dt>
<dd>Vector of the products of the propensity for the tx received</dd>


<dt><code>sumR</code></dt>
<dd>Vector of the sum of the rewards</dd>


<dt><code>index</code></dt>
<dd>Vector indicating compliance with estimated optimal regime</dd>


</dl>

BOWL-class: Class `BOWL`

Description

Arguments

Slots