Introduction
In many statistical studies we have prior knowledge about a
temporal or causal ordering of the variables. In this chapter we will use directed
graphs to incorporate such knowledge into a graphical model for the variables.
Let
X
V
= (
X
v
)
v
∈
V
be a vector of real-valued random variables with probability
distribution
P
and density
p
. Then the density
p
can always be decomposed into a
product of conditional densities,