Partial-Kelly Strategies and Expected Utility: Small-Edge Asymptotics

Authors:
Joseph B. Kadane
Affiliations:
Department of Statistics, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213
Venue:
Decision Analysis
Year:
2011

Citing 3
Cited 5

Growth versus security in dynamic investment analysis

Management Science - Focused issue on financial modeling
Growth-security investment strategy for long and short runs

Management Science
Optimal Betting Strategies for Simultaneous Games

Decision Analysis

Investment and Defense Strategies, Heuristics, and Games: From the Editor...

Decision Analysis
From the Editors---Deterrence, Multiattribute Utility, and Probability and Bayes' Updating

Decision Analysis
From the Editors---Probability Scoring Rules, Ambiguity, Multiattribute Terrorist Utility, and Sensitivity Analysis

Decision Analysis
From the Editor---Optimal Betting, Reducing Unnecessary Mammography in Breast Cancer Diagnosis, Product Line Design, and Value of Information

Decision Analysis
Optimal Betting Under Parameter Uncertainty: Improving the Kelly Criterion

Decision Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

Partial-Kelly strategies, proposed because full-Kelly strategies that use log of fortune as utility were found to be too risky, are examined from the perspective of maximizing expected utility. The results are as follows: (1) there is no utility function that is independent of the risks it confronts and that exactly has partial-Kelly strategies as the optimal strategy; and (2) constant relative risk aversion utility, with the constant relative risk parameter equal to the reciprocal of the partial-Kelly parameter, is a good approximation to such a utility function, particularly when the investor's edge is small.