sampleH

Implementation of the Stochastic Expectation Maximisation (StEM) approach to Record Linkage described in the paper by K. Robach, S. L. van der Pas, M. A. van de Wiel and M. H. Hof (2024, <doi:10.48550/arXiv.2407.06835>); see 'citation("FlexRL")' for details. This is a record linkage method, for finding the common set of records among 2 data sources based on Partially Identifying Variables (PIVs) available in both sources. It includes modelling of dynamic Partially Identifying Variables (e.g. postal code) that may evolve over time and registration errors (missing values and mistakes in the registration). Low memory footprint.

Kayané ROBACH

FlexRL

A Flexible Model for Record Linkage

sampleH function

<dl><dt>nA</dt>
<dd>IntegerVector of dimensions of registered values of the Partially Identifying Variables (PIVs) in A</dd>
<dt>nB</dt>
<dd>IntegerVector of dimensions of registered values of the PIVs in B</dd>
<dt>links</dt>
<dd>IntegerMatrix of 2 columns with the indices of the linked records</dd>
<dt>survivalpSameH</dt>
<dd>NumericMatrix with for each PIV the probability that true values coincide (if stable: filled with 1)</dd>
<dt>pivs_stable</dt>
<dd>LogicalVector indicating for each PIV whether it is stable of not (if not we expect survivalpSameH for that same element to not be filled with 1 but with lower values)</dd>
<dt>pivsA</dt>
<dd>List ith registered data from A</dd>
<dt>pivsB</dt>
<dd>List with registered data from B</dd>
<dt>nvalues</dt>
<dd>IntegerVector with number of unique values of each PIV</dd>
<dt>nonlinkedA</dt>
<dd>LogicalVector indicating for all records in A whether they are linked or not</dd>
<dt>nonlinkedB</dt>
<dd>LogicalVector indicating for all records in B whether they are linked or not</dd>
<dt>eta</dt>
<dd>List parameters of the PIVs distributions</dd>
<dt>phi</dt>
<dd>List parameters of the PIVs registration errors</dd></dl>

Arguments

sampleH — sampleH

<dl>

<dt>nA</dt>
<dd>IntegerVector of dimensions of registered values of the Partially Identifying Variables (PIVs) in A</dd>


<dt>nB</dt>
<dd>IntegerVector of dimensions of registered values of the PIVs in B</dd>


<dt>links</dt>
<dd>IntegerMatrix of 2 columns with the indices of the linked records</dd>


<dt>survivalpSameH</dt>
<dd>NumericMatrix with for each PIV the probability that true values coincide (if stable: filled with 1)</dd>


<dt>pivs_stable</dt>
<dd>LogicalVector indicating for each PIV whether it is stable of not (if not we expect survivalpSameH for that same element to not be filled with 1 but with lower values)</dd>


<dt>pivsA</dt>
<dd>List ith registered data from A</dd>


<dt>pivsB</dt>
<dd>List with registered data from B</dd>


<dt>nvalues</dt>
<dd>IntegerVector with number of unique values of each PIV</dd>


<dt>nonlinkedA</dt>
<dd>LogicalVector indicating for all records in A whether they are linked or not</dd>


<dt>nonlinkedB</dt>
<dd>LogicalVector indicating for all records in B whether they are linked or not</dd>


<dt>eta</dt>
<dd>List parameters of the PIVs distributions</dd>


<dt>phi</dt>
<dd>List parameters of the PIVs registration errors</dd>

</dl>

sampleH: sampleH

Description

Usage

Value

Arguments