Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

36
Adapting de Finetti's Proper Scoring Rules for Measuring Bayesian Subjective Probabilities when Those Probabilities Are not Bayesian Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam Topic: How to measure your subjective probability p of event E ("rain tomorrow")? Such that also acceptable to frequentists?

description

Adapting de Finetti's Proper Scoring Rules for Measuring Bayesian Subjective Probabilities when Those Probabilities Are not Bayesian. Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam. - PowerPoint PPT Presentation

Transcript of Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Page 1: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Adapting de Finetti's Proper Scoring Rules for Measuring

Bayesian Subjective Probabilities when Those Probabilities Are not

BayesianPeter P. Wakker (& Gijs van de Kuilen,

Theo Offerman, Joep Sonnemans)April 6, 2006Rotterdam

Topic: How to measure your subjective probability p of event E ("rain tomorrow")?Such that also acceptable to frequentists?

Page 2: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Method 1. Ask directly (introspection).Problem. No clear empirical meaning; no incentive(-compatibility).

Economists don't like such things.

2

Page 3: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Method 2. Reveal (binary) preferences.€ 0.30 (€ 1 under E) € 0.20 0.30 > p > 0.20 (if EV = expected value)Problem. Much work. Get only inequalities. (And: EV may be violated.)

Method 3. Reveal indifferences.€ 0.25 ~ (€ 1 under E) p = 0.25 (if EV …)Problem. Indifferences are hard to observe (BDM …). (And: EV may be violated.)

3

Page 4: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Method 4. de Finetti's book making. Not explained here.Problem. Not implementable in practice. (And: EV may be violated.)

4

Page 5: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Method 5. Proper scoring rules.Choose 0 r 1 as you like (called reported probability).Next, you receive

E Ec

1 – (1– r)2 1 – r2

EV: Take probability p of E;subjective if must be. Then maximize EV.Optimization of r:

5

Page 6: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

EV = p(1 – (1– r)2) + (1 – p)(1 – r2)

1st order condition:2p(1– r) – (1 – p)2r = 02p(1– r) = (1 – p)2rr = p!Wow!

Avoids all problems mentioned above, except Problem. EV may be violated …Proper scoring rules tractable & widely used:

See Hanson (Nature, 2002), Prelec (Science 2005).

In accounting (Wright 1988), Bayesian statistics (Savage 1971), business (Stael von Holstein 1972), education (Echternacht 1972), medicine (Spiegelhalter 1986), psychology (Liberman & Tversky 1993; McClelland & Bolger 1994).

6

Page 7: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Before analyzing nonEV descriptively, a:

Theoretical Example [EV].Urn K ("known") with 100 balls:25 G(reen), 25 R(ed), 25 S(ilver), 25 Y(ellow). One ball is drawn randomly.E: ball is not red; E = {G,S,Y}. p = 0.75.Under expected value,optimal rE is 0.75.rG + rS + rY = 0.25 + 0.25 + 0.25 = 0.75 = rE:r satisfies additivity; as probabilities should!

7

Example reanalyzed later.

Page 8: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

0.25 0.50 0.75 10p

8Reported probability R(p) = rE as function of true probability p, under:

nonEU

0.69

R(p)

EU

0.61

rEV

EV

rnonEU

rnonEUA

rnonEUA refers to nonexpected utility for unknown probabilities ("Ambiguity").

(c) nonexpected utility for known probabilities, with U(x) = x0.5 and with w(p) as common;

(b) expected utility with U(x) = x0.5 (EU);

(a) expected value (EV);

reward: if E true if not E true EV rEV=0.75 0.94 0.44 0.8125 rEU=0.69 0.91 0.52 0.8094

rEU

rnonEU=0.61 0.85 0.63 0.7920 rnonEUA=0.52 0.77 0.73 0.7596

next p.

go to p. 11, Example EU

go to p. 15, Example nonEU

0

0.50

1

0.25

0.75

go to p. 20, Example nonEUA

Page 9: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Deviation 1 [Utility curvature].Bernoulli (1738): risk aversion! U concave (if EU …).Now optimizepU(1 – (1– r)2) + (1 – p)U(1 – r2)

9

Page 10: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

10

U´(1–r2)U´(1 – (1–r)2)

(1–p)p +

pr =

Explicit expression:

U´(1–r2)U´(1 – (1–r)2)

(1–r)r +

rp =

EV: r is additive.EU: r is nonadditive (U nonsymmetric about 0.5).

Gives critical test of EV versus EU

Page 11: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Theoretical Example continued [Expected Utility]. (urn K, 25 G, 25 R, 25 S, 25 Y).E: {G,S,Y}; p = 0.75.EV: rEV = 0.75.Expected utility, U(x) = x: rEU = 0.69.rG + rS + rY = 0.31 + 0.31 + 0.31 = 0.93 > 0.69 = rE:additivity violated!Such data prove that expected value cannot hold.

11

Example reanalyzed later.

go to p. 8, with figure of R(p)

Page 12: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Deviation 2 from EV: nonexpected utility (Allais 1953, Machina 1982, Kahneman & Tversky 1979, Quiggin 1982, Schmeidler 1989, Gilboa 1987, Gilboa & Schmeidler 1989, Gul 1991, Tversky & Kahneman 1992, etc.)

12

For two-gain prospects, all theories are as follows:

For r 0.5, nonEU(r) = w(p)U(1 – (1–r)2) + (1–w(p))U(1–r2).

r < 0.5, symmetry; soit!Different treatment of highest and lowest outcome: "Rank-dependence."

Page 13: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

p

w(p)

1

1

0 1/3

Figure. The common weighting fuction w.w(p) = exp(–(–ln(p))) for = 0.65.

w(1/3) 1/3;

13

1/3

w(2/3) .51

2/3

.51

Page 14: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Now

14

U´(1–r2)U´(1 – (1–r)2)

(1–w(p))w(p) +

w(p)r =

U´(1–r2)U´(1 – (1–r)2)

(1–r)r +

rp =

Explicit expression:

w –1(

)

Page 15: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Example continued [nonEU]. (urn K, 25 G, 25 R, 25 S, 25 Y).E: {G,S,Y}; p = 0.75.EV: rEV = 0.75.EU: rEU = 0.69.Nonexpected utility, U(x) = x, w(p) = exp(–(–ln(p))0.65).rnonEU = 0.61.rG + rS + rY = 0.39 + 0.39 + 0.39 = 1.17 > 0.61 = rE:additivity is strongly violated!

15

go to p. 8, with figure of R(p)

Deviations from EV and Bayesianism so far were at level of behavior; not of beliefs. Now for something different; more fundamental.

Page 16: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

3rd violation of EV: Ambiguity (unknown probabilities)

Preparation for theoretical example.Random draw from additional urn A.100 balls, ? Ga, ? Ra, ? Sa, ? Ya. Unknown composition ("Ambiguous").Ea: {Ga,Sa,Ya}; p = ?.How deal with unknown probabilities?

Have to give up Bayesian beliefs.

16

Page 17: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

1st Proposal (trying to maintain Bayesian beliefs) Assign "subjective" probabilities to events. Then behave as if known probs (may be nonEU)("probabilistic sophistication," Machina & Schmeidler 1992; they did it for normative, not as we do now descriptively).By symmetry then P(G) = P(R) = P(S) = P(Y) = ¼.Treated same as known urn K.Empirically violated (Ellsberg)!

17

>< Probabilistic soph. Bayesian beliefs!

Page 18: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

18

Instead of additive beliefs p = P(E), nonadditive beliefs B(E), with B(E) B(G) + B(S) + B(Y).(Dempster&Shafer, Tversky&Koehler, etc.)

All currently existing decision models:For r 0.5, nonEU(r) = w(B(E))U(1 – (1–r)2) + (1–w(B(E)))U(1–r2).(Commonly written with W(E) for w(B(E)), soB(E) = w–1(W(E)); matter of notation.)

Page 19: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

19

U´(1–r2)U´(1 – (1–r)2)

(1–w(B(E)))w(B(E)) +

w(B(E))rE =

U´(1–r2)U´(1 – (1–r)2)

(1–r)r +

rB(E) =

Explicit expression:

w –1(

)

Page 20: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Example continued [Ambiguity, nonEUA]. (urn A, 100 balls, ? G, ? R, ? S, ? Y).E: {G,S,Y}; p = ?rEV = 0.75.rEU = 0.69.rnonEU = 0.61 (under plausible assumptions).Typically, w(B(E)) << w(B(E)) (E from known urn). rnonEUA is, say, 0.52.rG + rS + rY = 0.48 + 0.48 + 0.48 = 1.44 > 0.52 = rE:additivity is very extremely violated!r's are close to always saying fifty-fifty.Belief component B(E) = 0.62.

20

go to p. 8, with figure of R(p)

Page 21: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

B(E): ambiguity attitude /=/ beliefs??Before entering that debate, first:How measure B(E)?Our contribution: through proper scoring rules with "risk correction."

Earlier proposals for measuring B:

21

Page 22: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Proposal 1 (common in decision theory).Measure U,W, and w from behavior.Derive B(E) = w–1(W(E)) from it.Problem: Much and difficult work!!!

22

Page 23: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Proposal 2 (common in decision analysis of the 1960s, and in modern experimental economics). Measure "canonical probabilities": For ambiguous event Ea, find objective prob. p such that (€100 if Ea) ~ (€100 with prob. p). Then (algebra …) B(E) = p.Problem: measuring indifferences is difficult.

23

Page 24: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Proposal 3 (common in proper scoring rules): Calibration …Problem: Need many repeated observations.

24

Page 25: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

25

Our proposal: Take the best of all worlds!

Get B(E) = w–1(W(E)) without measuring U,W, and w from decision making.

Get canonical probability without measuring indifferences, or BDM.

Calibrate without needing long repeated observations.

Do all that with no more than simple proper-scoring-rule questions.

Page 26: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

26

We reconsider explicit expressions:

U´(1–r2)U´(1 – (1–r)2)

(1–r)r +

rp = w

–1(

)

U´(1–r2)U´(1 – (1–r)2)

(1–r)r +

rB(E) = w

–1(

)

Corollary. p = B(E) if related to the same r!!

Page 27: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

27

Because p = B(E) if related to same: We simply measure the R(p) curves, and use their inverses:B(E) = R–1(rE).

Appling R–1 is called risk correction.

Directly implementable empirically.

We did so in an experiment, and found plausible results.

Page 28: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Experimental Test of Our Correction Method

28

Page 29: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Method

Participants. N = 93 students. Procedure. Computarized in lab. Groups of 15/16 each. 4 practice questions.

29

Page 30: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

30Stimuli 1. First we did proper scoring rule for unknown probabilities. 72 in total.

For each stock two small intervals, and, third, their union. Thus, we test for additivity.

Page 31: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

31Stimuli 2. Known probabilities: Two 10-sided dies thrown. Yield random nr. between 01 and 100.Event E: nr. 75 (etc.).Done for all probabilities j/20.

Motivating subjects. Real incentives. Two treatments. 1. All-pay. Points paid for all questions.6 points = €1. Average earning €15.05.2. One-pay (random-lottery system).One question, randomly selected afterwards, played for real. 1 point = €20. Average earning: €15.30.

Page 32: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

32

Results

Page 33: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

33

0

0.1

0.2

0.3

0.4

0.5

0.6

0.7

0.8

0.9

1

0.000 0.100 0.200 0.300 0.400 0.500 0.600 0.700 0.800 0.900 1.000

Reported probability

Cor

rect

ed p

roba

bilit

y

ONE (rho = 0.70) ALL (rho = 1.14) 45°

Average correction curves.

Page 34: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

34

0

0.1

0.2

0.3

0.4

0.5

0.6

0.7

0.8

0.9

1

-2.0 -1.5 -1.0 -0.5 0.0 0.5 1.0 1.5

ρ

F(ρ )

treatmentone

treatmentall

Individual corrections.

Page 35: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

35

Figure 9.1. Empirical density of additivity bias for the two treatments

Fig. b. Treatment t=ALL

0.60

20

40

60

80

100

120

140

160

0.4 0.2 0 0.2 0.4 0.6

Fig. a. Treatment t=ONE

0

20

40

60

80

100

120

140

160

0.6 0.4 0.2 0 0.2 0.4 0.6

For each interval [, ] of length 0.05 around , we counted the number of additivity biases in the interval, aggregated over 32 stocks and 89 individuals, for both treatments. With risk-correction, there were @ > 60 additivity biases between 0.375 and 0.425 in the treatment t=ONE, and without risk-correction there were @<100 such; etc.

corrected

corrected

uncorrected

uncorrected

Page 36: Peter P. Wakker (& Gijs van de Kuilen, Theo Offerman, Joep Sonnemans) April 6, 2006 Rotterdam

Summary and ConclusionModern decision theories show that proper scoring rules are heavily biased.We present ways to correct for these biases (get right beliefs even if EV violated).Experiment shows that correction improves quality and reduces deviations from ("rational"?) Bayesian beliefs.Correction does not remove all deviations from Bayesian beliefs. Beliefs seem to be genuinely nonadditive/nonBayesian/sensitive-to-ambiguity.

36