sharedMostProbableClusters: Shared Most Probable Clusters

In cleanzr/dblinkR: R interface for dblink

Description

Computes a point estimate of the most likely clustering that obeys transitivity constraints based on posterior samples. The method was introduced by Steorts et al. (2016), where it is referred to as the method of shared most probable maximal matching sets.

Usage

sharedMostProbableClusters(x, ...)

## S4 method for signature 'linkagechain'
sharedMostProbableClusters(x, ...)

## S4 method for signature 'mostprobableclusters'
sharedMostProbableClusters(x, ...)

## S4 method for signature 'dblinkresult'
sharedMostProbableClusters(x, ...)

Arguments

x	A dblinkresult object as returned by runInference or a linkagechain object as returned by loadLinkageChain.
m_jobj	An optional mostprobableclusters object as returned by mostProbableClusters. If provided, the function can skip computing the most probable clusters.

Value

A clusters object.

References

Steorts, R. C., Hall, R. & Fienberg, S. E. A Bayesian Approach to Graphical Record Linkage and Deduplication. JASA 111, 1660–1672 (2016).

cleanzr/dblinkR documentation built on June 13, 2021, 4:17 a.m.