gRain (version 1.2-5)

querygrain: Set evidence and query a network

Description

Query an independence network, i.e. obtain the conditional distribution of a set of variables given finding (evidence) on other variables.

Usage

setEvidence(object, nodes=NULL, states=NULL, evidence=NULL, nslist=NULL, propagate=TRUE, details=0)
getEvidence(object)
pEvidence(object)
retractEvidence(object, nodes=NULL, propagate=TRUE)
querygrain(object, nodes = nodeNames(object), type = "marginal", evidence = NULL, exclude = TRUE, normalize = TRUE, result="array", details = 0)

Arguments

object

A "grain" object

nodes

A vector of nodes; those nodes for which the (conditional) distribution is requested.

states

A vector of states (of the nodes given by 'nodes')

evidence

An alternative way of specifying findings (evidence), see examples below.

nslist

deprecated

exclude

If TRUE then nodes on which evidence is given will be excluded from nodes (see above).

propagate

Should the network be propagated?

normalize

Should the results be normalized to sum to one.

type

Valid choices are "marginal" which gives the marginal distribution for each node in nodes; "joint" which gives the joint distribution for nodes and "conditional" which gives the conditional distribution for the first variable in nodes given the other variables in nodes.

result

If "data.frame" the result is returned as a data frame (or possibly as a list of dataframes).

details

Debugging information

Value

A list of tables with potentials.

References

Sren Hjsgaard (2012). Graphical Independence Networks with the gRain Package for R. Journal of Statistical Software, 46(10), 1-26. http://www.jstatsoft.org/v46/i10/.

See Also

setFinding getFinding retractFinding pFinding

Examples

testfile <- system.file("huginex", "chest_clinic.net", package = "gRain")
chest <- loadHuginNet(testfile, details=0)
qb <- querygrain(chest)
qb

lapply(qb, as.numeric) 
sapply(qb, as.numeric) 

## setFinding / setEvidence

yn <- c("yes","no")
a    <- cptable(~asia, values=c(1,99),levels=yn)
t.a  <- cptable(~tub+asia, values=c(5,95,1,99),levels=yn)
s    <- cptable(~smoke, values=c(5,5), levels=yn)
l.s  <- cptable(~lung+smoke, values=c(1,9,1,99), levels=yn)
b.s  <- cptable(~bronc+smoke, values=c(6,4,3,7), levels=yn)
e.lt <- cptable(~either+lung+tub,values=c(1,0,1,0,1,0,0,1),levels=yn)
x.e  <- cptable(~xray+either, values=c(98,2,5,95), levels=yn)
d.be <- cptable(~dysp+bronc+either, values=c(9,1,7,3,8,2,1,9), levels=yn)
plist <- compileCPT(list(a, t.a, s, l.s, b.s, e.lt, x.e, d.be))
chest <- grain(plist)


## 1) These two forms are identical
setEvidence(chest, c("asia","xray"), c("yes", "yes"))
setFinding(chest, c("asia","xray"), c("yes", "yes"))

## 2) Suppose we do not know with certainty whether a patient has
## recently been to Asia. We can then introduce a new variable
## "guess.asia" with "asia" as its only parent. Suppose
## p(guess.asia=yes|asia=yes)=.8 and p(guess.asia=yes|asia=no)=.1
## If the patient is e.g. unusually tanned we may set
## guess.asia=yes and propagate. This corresponds to modifying the
## model by the likelihood (0.8, 0.1) as
setEvidence(chest, c("asia","xray"), list(c(0.8,0.1), "yes"))

## 3) Hence, the same result as in 1) can be obtained with
setEvidence(chest, c("asia","xray"), list(c(1, 0), "yes"))

## 4) An alternative specification using evidence is
setEvidence(chest, evidence=list("asia"=c(1, 0), "xray"="yes"))