log_prior_pdf

Compute the natural log of the PDF for the parameters in an E-family design

internal

Optimal experimental designs for both population and individual
studies based on nonlinear mixed-effect models. Often this is based on a
computation of the Fisher Information Matrix. This package was developed
for pharmacometric problems, and examples and predefined models are available
for these types of systems. The methods are described in Nyberg et al.
(2012) <doi:10.1016/j.cmpb.2012.05.005>, and Foracchia et al. (2004)
<doi:10.1016/S0169-2607(03)00073-7>.

Andrew C. Hooker

PopED

Population (and Individual) Optimal Experimental Design

Marco Foracchia

Eric Stroemberg

Martin Fink

Giulia Lestini

Sebastian Ueckert

Joakim Nyberg

log_prior_pdf function

<dl><dt>alpha</dt>
<dd>A parameter vector.</dd>
<dt>bpopdescr</dt>
<dd>Matrix defining the fixed effects, per row (row number =
parameter_number) we should have:<ul>
<li>column 1 the type of the
distribution for E-family designs (0 = Fixed, 1 = Normal, 2 = Uniform, 3 =
User Defined Distribution, 4 = lognormal and 5 = truncated normal)</li>
<li>column 2 defines the mean.</li>
<li>column 3 defines the variance of the
distribution (or length of uniform distribution).</li>
</ul></dd>
<dt>ddescr</dt>
<dd>Matrix defining the diagonals of the IIV (same logic as for
the <code>bpopdescr</code>).</dd>
<dt>return_gradient</dt>
<dd>Should the gradient be returned.</dd>
<dt>return_hessian</dt>
<dd>Should the hessian be returned?</dd></dl>

Arguments

Compute the natural log of the PDF for the parameters in an E-family design — log_prior_pdf

<dl>

<dt>alpha</dt>
<dd>A parameter vector.</dd>


<dt>bpopdescr</dt>
<dd>Matrix defining the fixed effects, per row (row number =
parameter_number) we should have:<ul>
<li>column 1 the type of the
distribution for E-family designs (0 = Fixed, 1 = Normal, 2 = Uniform, 3 =
User Defined Distribution, 4 = lognormal and 5 = truncated normal)</li>
<li>column 2 defines the mean.</li>
<li>column 3 defines the variance of the
distribution (or length of uniform distribution).</li>
</ul></dd>


<dt>ddescr</dt>
<dd>Matrix defining the diagonals of the IIV (same logic as for
the <code>bpopdescr</code>).</dd>


<dt>return_gradient</dt>
<dd>Should the gradient be returned.</dd>


<dt>return_hessian</dt>
<dd>Should the hessian be returned?</dd>

</dl>

log_prior_pdf: Compute the natural log of the PDF for the parameters in an E-family design

Description

Usage

Arguments