Example $16\mathrm{.}12$ Constructing a Risk Profile

In the drug$-$development example, consider the strategy

of pursuing development. The possible outcomes that

can occur and their probabilities are:

Terminal Outcome Net Revenue Probability

Market large $$3,9250\mathrm{.}108$

Market medium $$1,6250\mathrm{.}054$

Market small $$9250\mathrm{.}018$

FDA not approved $($$$575)0\mathrm{.}120$

Clinical trials not

successful

$($$$550)0\mathrm{.}700$

The probabilities are computed by multiplying the

probabilities on the event branches along the path to the

terminal outcome. For example, the probability of getting

to $$Market large$$ is $0\mathrm{.}30\mathrm{.}60\mathrm{.}60\mathrm{.}108.$ Thus,

we see that the probability that the drug will not reach

the market is $110\mathrm{.}1080\mathrm{.}0540\mathrm{.}01820\mathrm{.}82,$ and

the company will incur a loss of more than $$500$ million.

On the other hand, if they decide not to pursue clinical

trials, the loss would be only $$300$ million, the cost of

research

to date. If this were a one$-$time decision, what

decision would you make if you were a top executive of

this company?

Sensitivity Analysis in Decision Trees

We may use Excel data tables to investigate the sensitivity of the optimal decision to changes

in probabilities or payoff values. We illustrate this using the airline revenue management

scenario we discussed in Example $5\mathrm{.}22$ in Chapter $5.$