
90 Bayesian Methods in Health Economics
do not gather
additional data
keep
t
= 0
switch to
t
= 1
|
|
temporarily keep
t
= 0 & gather
additional data
E
}
}
switch to
t
= 1
keep
t
= 0
D
x( |)
x( |)
x( })
x( })
decisions
random events
sampling costs
FIGURE 3.3
A graphical representation of the sequential decision problem, in terms of a
decision tree.
(SA), in order to quantify and qualify the uncertainty underlying the deci-
sion process. Formally, SA is defined in risk assessment as the study of “how
uncertainty in some model output can be apportioned, qualitatively or quanti-
tatively, to different sources of uncertainty in the model input” ...