register_trend

Compiles and registers a user-provided C++ function that maps per-trial
kernel parameters and inputs to a numeric vector. The C++ function must have
signature:
NumericVector f(NumericMatrix trend_pars, NumericMatrix input)
and provide an exported pointer creator using EMC2_MAKE_PTR.

Fit Bayesian (hierarchical) cognitive models
using a linear modeling language interface using particle Metropolis Markov
chain Monte Carlo sampling with Gibbs steps. The diffusion decision model (DDM),
linear ballistic accumulator model (LBA), racing diffusion model (RDM), and the lognormal
race model (LNR) are supported. Additionally, users can specify their own likelihood
function and/or choose for non-hierarchical
estimation, as well as for a diagonal, blocked or full multivariate normal
group-level distribution to test individual differences. Prior specification
is facilitated through methods that visualize the (implied) prior.
A wide range of plotting functions assist in assessing model convergence and
posterior inference. Models can be easily evaluated using functions
that plot posterior predictions or using relative model comparison metrics
such as information criteria or Bayes factors.
References: Stevenson et al. (2024) <doi:10.31234/osf.io/2e4dq>.

Niek Stevenson

EMC2

Bayesian Hierarchical Analysis of Cognitive Models of Choice

Michelle Donzallaz

Andrew Heathcote

Steven Miletić

Raphael Hartmann

Karl C. Klauer

Steven G. Johnson

Jean M. Linhart

Brian Gough

Gerard Jungman

Rudolf Schuerer

Przemyslaw Sliwa

Jason H. Stover

register_trend function

<dl><dt>trend_parameters</dt>
<dd>Character vector of kernel parameter names (in order).</dd>
<dt>file</dt>
<dd>Path to the C++ file implementing the custom kernel. The file
should include EMC2/userfun.hpp and define a pointer creator (via
EMC2_MAKE_PTR) that is exported to R.</dd>
<dt>transforms</dt>
<dd>Optional named character vector or list mapping each custom
kernel parameter name to a transform name (e.g., "identity", "exp", "pnorm").
Length must match <code>trend_parameters</code>. If unnamed but the correct length,
the order is assumed to match <code>trend_parameters</code>.</dd>
<dt>base</dt>
<dd>Default base to use when creating trends with this custom kernel
if no <code>bases</code> argument is supplied to <code>make_trend</code>. One of
c("lin","exp_lin","centered","add","identity"). Default "add".</dd></dl>

Arguments

Register a custom C++ trend kernel — register_trend

<dl>

<dt>trend_parameters</dt>
<dd>Character vector of kernel parameter names (in order).</dd>


<dt>file</dt>
<dd>Path to the C++ file implementing the custom kernel. The file
should include EMC2/userfun.hpp and define a pointer creator (via
EMC2_MAKE_PTR) that is exported to R.</dd>


<dt>transforms</dt>
<dd>Optional named character vector or list mapping each custom
kernel parameter name to a transform name (e.g., "identity", "exp", "pnorm").
Length must match <code>trend_parameters</code>. If unnamed but the correct length,
the order is assumed to match <code>trend_parameters</code>.</dd>


<dt>base</dt>
<dd>Default base to use when creating trends with this custom kernel
if no <code>bases</code> argument is supplied to <code>make_trend</code>. One of
c("lin","exp_lin","centered","add","identity"). Default "add".</dd>

</dl>

Register a custom C++ trend kernel

register_trend: Register a custom C++ trend kernel

Description

Usage

Value

Arguments