Abstract
This paper uses simulation (written in R) to compare six methods of decision making under uncertainty: the agent must choose one of eight lotteries where the six possible (randomly chosen) outcomes and their probabilities are known for each lottery. Will risk-averse or risk-preferring or other methods result in the highest mean payoff after the uncertainty is resolved and the outcomes known? Methods include max-max, max-min, Laplace, Expected Value, CARA, CRRA, and modified Kahneman-Tversky. The benchmark is Clairvoyance, where the lotteries’ outcomes are known in advance; this is possible with simulation. The findings indicate that the highest mean payoff occurs with risk neutrality, contrary to common opinion.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
The lottery outcomes fall randomly in the range ±$10; see Sect. 4.
- 2.
With 48 outcomes, the expected maximum outcome across the eight lotteries is $9.59; the expected maximum of the eight simulated realised outcomes is 81.2% of this maximum.
- 3.
This does not require that we include wealth w in the ranking of the lotteries, as in CRRA case; instead we choose a reference point at the current level of wealth, and consider the prospective gains and losses of the eight lotteries.
- 4.
See the R [4] code at http://www.agsm.edu.au/bobm/papers/riskmethods.r.
References
Howard, R.A.: The foundations of decision analysis. IEEE Trans. Syst. Sci. Cybern. ssc–4, 211–219 (1968)
Kahneman, D., Tversky, A.: Prospect theory: an analysis of decision under risk. Econometrica 47, 263–291 (1979)
Marks, R.E.: Searching for agents’ best risk profiles. In: Handa, H., Ishibuchi, M., Ong, Y.-S., Tan, K.-C. (eds.) Proceedings of the 18th Asia Pacific Symposium on Intelligent and Evolutionary Systems (IES 2014), Chapter 24. Proceedings in Adaptation, Learning and Optimization, vol. 1, pp. 297-309. Springer (2015). http://www.agsm.edu.au/bobm/papers/marksIES2014.pdf
R Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria (2013). http://www.R-project.org/
Arthur, W.B.: Designing economic agents that act like human agents: a behavioral approach to bounded rationality. Am. Econ. Rev. Papers Proc. 81, 353–360 (1991)
Rabin, M.: Risk aversion and expected-utility theory: a calibration theorem. Econometrica 68, 1281–1292 (2000)
DellaVigna, S., LiCalzi, M.: Learning to make risk neutral choices in a symmetric world. Math. Soc. Sci. 41, 19–37 (2001)
Chen, S.-H., Huang, Y.-C.: Risk preference, forecasting accuracy and survival dynamics: simulation based on a multi-asset agent-based artificial stock market. J. Econ. Behav. Organ. 67(3–4), 702–717 (2008)
Marks, R.E.: Learning to be risk averse? In: Serguieva, A., Maringer, D., Palade, V., Almeida, R.J. (eds.) Proceedings of the 2014 IEEE Computational Intelligence for Finance Engineering and Economics (CIFEr), London, 28–29 March, pp. 1075-1079. IEEE Computational Intelligence Society (2015)
Szpiro, G.G.: The emergence of risk aversion. Complexity 2, 31–39 (1997)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Marks, R.E. (2020). Calibrating Methods for Decision Making Under Uncertainty. In: Bucciarelli, E., Chen, SH., Corchado, J. (eds) Decision Economics: Complexity of Decisions and Decisions for Complexity. DECON 2019. Advances in Intelligent Systems and Computing, vol 1009. Springer, Cham. https://doi.org/10.1007/978-3-030-38227-8_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-38227-8_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-38226-1
Online ISBN: 978-3-030-38227-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)