On the Relation between Robust and Bayesian Decision Making



Example 2 Let the optimal robust decision be given by x,r' = [x,rl0,xtrl1,... )
and the state S{ (i = 1, 2) that maximizes the loss for this and any neighboring
decisions is given by
si. Next consider the decision

x' = x* + (d', O, O, O ... )

which is equal to xtr, except for the first period. Suppose that altering the decision
from x
tr to x causes the loss in period zero to increase by γ1 > O units in state
sɪ. This causes x to be suboptimal for the robust decision maker.

Next, consider a Bayesian decision maker with objective (8) who considers
a deviation from x
tr to x. The changein the first period loss is given by

k = (ek(z0r*.o,sB+7j


- efez(^,O>sl))p1 + I efc(z(r,0.s2)+72)


- efeZ(^r,0.S2)


(9)


where γ2 = l(x*r0 + d,sfi) - l(xtr0,s2).  Suppose γ2 < O and l(x*r0,s2) >

l(xtr0,sι) + Y1 > O, which cannot be excluded, then

Iim k = -∞
k→∞

which indicates that a Bayesian with objective function (8) will prefer x to xr
for all sufficiently large k.

To obtain a convergence result similar to the one in section 3 one has to
de
fine the transformed loss function as

Tk(T(x, s)) = ek(ez(^t,sf))                          (10)

and let the Bayesian minimize

I

min V ek(∑ ∑o        .

(11)


{ttΩt} 2-'

i=1

where pi are prior probabilities.

Proposition 3 below shows that, as k increases without bound, the Bayesian
solution to problem (11) converges to the robust solution in terms of the follow-
ing vector norm:

llxlβ = V βtx'txt

(12)


¢=0

10



More intriguing information

1. The name is absent
2. BODY LANGUAGE IS OF PARTICULAR IMPORTANCE IN LARGE GROUPS
3. Correlation Analysis of Financial Contagion: What One Should Know Before Running a Test
4. The Values and Character Dispositions of 14-16 Year Olds in the Hodge Hill Constituency
5. The magnitude and Cyclical Behavior of Financial Market Frictions
6. Neighborhood Effects, Public Housing and Unemployment in France
7. Text of a letter
8. Towards a framework for critical citizenship education
9. The name is absent
10. The name is absent