and it is equal to:
μ
δσ2
The economic agents use the personal model gr|s as if it represented the actual model. The problem
is that assuming gr|s to be the density function of a Normal random variable, is likely that the model is
misspecified.
What is described next is a characterization of expected utility maximization under ‘risk’ very similar
to Gilboa-Schmilder(2001), that is the decision process is one in which the “decision maker first forms
probabilistic beliefs and then uses them to reduce a decision problem under uncertainty to a decision problem
under risk”. In other words, the use of models selection and combination described in previous sections
helps reducing the degree of model ambiguity, because it shrinks the set of candidate models into a unique
distribution that characterizes the risk of the decision problem.
Example 2: CARA investors with probabilistic belief M (θMj ). In the context of example 1, lets suppose
that the investor instead of assuming that the returns are Normally distributed, builds his probabilistic belief
gr/s as described in section II and III. Moreover, lets assume that the current regime is known. Therefore,
his model for the asset return is equal to M(θMj ).
Egr|s[U(W(ret,a))] =
KEM(bθMj)[exp(-δaret)]
EM(bMj)[exP(-δar)] = -ʃeχp(-δar) ∙ (XPj(KCI)fj(r,b)))dr
= - Xpj(KcI) exp(-δar)fj (r, bθ))dr = X pj (KcI)(-Efj (exp(-δar).
jj
If we define t = δa we can rewrite the expected utility function as -E[exp(-tr)], which is the Moment
Generating Function20 (MGF) after we account for the change in signs. This implies that the expected
utility function, when the expectation is taken under the model M (θMj ) is equal to
- pj(KCI)MGFfj(-t),
j
which is nothing more than the weighted average of the Moment Generating Function of each model included
in M(bθMj ).
It is important to notice that the existence of a closed form solution for the optimal share a is still
guaranteed. However, in this framework the optimal choice not only depends on the risk aversion and on
the moments of the probability law of stock returns, but it also depends on the weights contained in the
model combination. As such, it is affected by the measure of uncertainty about the true structure. Explicit
formulas for each MGF and for the expected utility are provided in the Appendix.
20The Moment Generating Function MGFr(t) = Er(exptr).
19