entEst

Entropy estimator based on k-nearest neighbors.

Empirical likelihood-based approximate Bayesian Computation. Approximates the required posterior using empirical likelihood and estimated differential entropy. This is achieved without requiring any specification of the likelihood or estimating equations that connects the observations with the underlying parameters. The procedure is known to be posterior consistent. More details can be found in Chaudhuri, Ghosh, and Kim (2024) <doi:10.1002/SAM.11711>.

Sanjay Chaudhuri

abcel

Empirical Likelihood-Based Approximate Bayesian Computation

Nicholas Chua

Riddhimoy Ghosh

entEst function

<dl><dt>summaries</dt>
<dd>data matrix with summary statistics as rows and samples as columns (d x m)</dd>
<dt>k</dt>
<dd>user-chosen k, or NULL</dd>
<dt>terms</dt>
<dd>user-supplied terms, or NULL</dd>
<dt>wts</dt>
<dd>user-supplied weights, or NULL</dd></dl>

Arguments

New Entropy Estimator — entEst

<dl>

<dt>summaries</dt>
<dd>data matrix with summary statistics as rows and samples as columns (d x m)</dd>


<dt>k</dt>
<dd>user-chosen k, or NULL</dd>


<dt>terms</dt>
<dd>user-supplied terms, or NULL</dd>


<dt>wts</dt>
<dd>user-supplied weights, or NULL</dd>

</dl>

entEst: New Entropy Estimator

Description

Usage

Value

Arguments

Examples