Bayesian networks with likelihood evidence in R

Research output: Contribution to conference without publisher/journalConference abstract for conferenceResearchpeer-review


The gRain package for R ( has been around for a decade and the package provides tools for building Bayesian networks as well as for probability propagation in such networks.
In gRain, attention is restricted to networks with discrete nodes.
A recent addition to the package is the ability to incorporate likelihood evidence (also called soft evidence or virtual evidence) in the network. This facility is useful in itself, and the facility also allows for handling networks where not all nodes are discrete.

[1] Højsgaard, S. (2012). Graphical Independence Networks with the gRain Package for R. Journal
of Statistical Software 46, 1–26.
Original languageEnglish
Publication date2018
Number of pages1
Publication statusPublished - 2018
Event27th Nordic Conference in Mathematical Statistics - Dorpat Convention Centre, Tartu, Estonia
Duration: 26 Jun 201829 Aug 2018
Conference number: 27


Conference27th Nordic Conference in Mathematical Statistics
LocationDorpat Convention Centre
Internet address


  • Message passing
  • Probability propagation


Dive into the research topics of 'Bayesian networks with likelihood evidence in R'. Together they form a unique fingerprint.

Cite this