Optimal Granularity for Portfolio Choice
25 Pages Posted: 25 Apr 2016 Last revised: 15 Jul 2016
Date Written: July 13, 2016
Many optimization-based portfolio rules fail to beat the simple 1/N rule out-of-sample because of parameter uncertainty. In this paper we suggest a grouping strategy in which we first form groups of equally weighted stocks and then optimize over the resulting groups only. In a simplified setting we show analytically how to optimize the trade-off between drawbacks from parameter uncertainty and drawbacks from deviating from the overall optimal asset allocation. We illustrate that the optimal group size depends on the volatility of the assets, on the number of observations and on how much the optimal asset allocation differs from 1/N. Out of sample back-tests confirm the validity of our grouping strategy empirically.
Keywords: mean-variance optimization, the 1/N rule, parameter uncertainty, optimal portfolio granularity
JEL Classification: G1, G11
Suggested Citation: Suggested Citation