ModelLogNormal-class

.ModelLogNormal

ModelLogNormal

.DefaultModelLogNormal

<a href="https://lifecycle.r-lib.org/articles/stages.html#stable"><img src="figures/lifecycle-stable.svg?package=crmPack&version=2.0.0" alt="[Stable]"></a>
<code>ModelLogNormal</code> is the class for a model with a reference dose and bivariate
normal prior on the model parameters <code>alpha0</code> and natural logarithm of <code>alpha1</code>,
i.e.: $$(alpha0, log(alpha1)) ~ Normal(mean, cov),$$. Transformations other
than <code>log</code>, e.g. identity, can be specified too in <code>priormodel</code> slot.
The parameter <code>alpha1</code> has a log-normal distribution by default to ensure
positivity of <code>alpha1</code> which further guarantees <code>exp(alpha1) &gt; 1</code>.
The slots of this class contain the mean vector, the covariance and
precision matrices of the bivariate normal distribution, as well as the
reference dose. Note that the precision matrix is an inverse of the
covariance matrix in the <code>JAGS</code>.
All ("normal") model specific classes inherit from this class.

Implements a wide range of dose escalation
designs. The focus is on model-based designs, ranging from classical and
modern continual reassessment methods (CRMs) based on dose-limiting toxicity
endpoints to dual-endpoint designs taking into account a biomarker/efficacy
outcome. Bayesian inference is performed via MCMC sampling in JAGS, and it is easy
to setup a new design with custom JAGS code. However, it is also possible to
implement 3+3 designs for comparison or models with non-Bayesian estimation.
The whole package is written in a modular form in the S4 class system, making it
very flexible for adaptation to new models, escalation or stopping rules.
Further details are presented in
Sabanes Bove et al. (2019) <doi:10.18637/jss.v089.i10>.

Daniel Sabanes Bove

crmPack

Object-Oriented Implementation of Dose Escalation Designs

Wai Yin Yeung

Burak Kuersad Guenhan

Giuseppe Palermo

Thomas Jaki

Jiawen Zhu

Ziwei Liao

Dimitris Kontos

Marlene Schulte-Goebel

Doug Kelkhoff

Oliver Boix

Robert Adams

Clara Beck

John Kirkpatrick

Wojciech Wójciak

Guanya Peng

Prerana Chandratre

F. Hoffmann-La Roche AG 

Merck Healthcare KGaA 

Bayer AG 

RPACT GmbH 

ModelLogNormal-class function

<dl><dt>mean</dt>
<dd>(<code>numeric</code>) the prior mean vector.</dd>
<dt>cov</dt>
<dd>(<code>matrix</code>) the prior covariance matrix. The precision matrix
<code>prec</code> is internally calculated as an inverse of <code>cov</code>.</dd>
<dt>ref_dose</dt>
<dd>(<code>number</code>) the reference dose $x*$ (strictly positive
number).</dd></dl>

Arguments

<dl>
<dt><code>params</code></dt>
<dd>(<code>ModelParamsNormal</code>) bivariate normal prior parameters.</dd></dl>
<dt><code>ref_dose</code></dt>
<dd>(<code>positive_number</code>) the reference dose.</dd>

Slots

<a href='https://lifecycle.r-lib.org/articles/stages.html#stable'><img src='figures/lifecycle-stable.svg' alt='[Stable]' /></a>
<code>ModelLogNormal</code> is the class for a model with a reference dose and bivariate
normal prior on the model parameters <code>alpha0</code> and natural logarithm of <code>alpha1</code>,
i.e.: $$(alpha0, log(alpha1)) ~ Normal(mean, cov),$$. Transformations other
than <code>log</code>, e.g. identity, can be specified too in <code>priormodel</code> slot.
The parameter <code>alpha1</code> has a log-normal distribution by default to ensure
positivity of <code>alpha1</code> which further guarantees <code>exp(alpha1) &gt; 1</code>.
The slots of this class contain the mean vector, the covariance and
precision matrices of the bivariate normal distribution, as well as the
reference dose. Note that the precision matrix is an inverse of the
covariance matrix in the <code>JAGS</code>.
All ("normal") model specific classes inherit from this class.

ModelLogNormal — ModelLogNormal-class

<dl>

<dt>mean</dt>
<dd>(<code>numeric</code>) the prior mean vector.</dd>


<dt>cov</dt>
<dd>(<code>matrix</code>) the prior covariance matrix. The precision matrix
<code>prec</code> is internally calculated as an inverse of <code>cov</code>.</dd>


<dt>ref_dose</dt>
<dd>(<code>number</code>) the reference dose $x*$ (strictly positive
number).</dd>

</dl>

<dl>
<dt><code>params</code></dt>
<dd>(<code>ModelParamsNormal</code>) bivariate normal prior parameters.</dd>


<dt><code>ref_dose</code></dt>
<dd>(<code>positive_number</code>) the reference dose.</dd>


</dl>

<code>ModelLogNormal</code>

ModelLogNormal-class: `ModelLogNormal`

Description

Usage

Arguments

Slots

See Also