Working Paper: NBER ID: w10372
Authors: Michael W. Brandt; Pedro Santa-Clara
Abstract: We present a novel approach to dynamic portfolio selection that is no more difficult to implement than the static Markowitz model. The idea is to expand the asset space to include simple (mechanically) managed portfolios and compute the optimal static portfolio in this extended asset space. The intuition is that a static choice among managed portfolios is equivalent to a dynamic strategy. We consider managed portfolios of two types: "conditional" and "timing" portfolios. Conditional portfolios are constructed along the lines of Hansen and Richard (1987). For each variable that affects the distribution of returns and for each basis asset, we include a portfolio that invests in the basis asset an amount proportional to the level of the conditioning variable. Timing portfolios invest in each basis asset for a single period and therefore mimic strategies that buy and sell the asset through time. We apply our method to a problem of dynamic asset allocation across stocks, bonds, and cash using the predictive ability of four conditioning variables.
Keywords: No keywords provided
JEL Codes: G0; G1
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| expanding the asset space to include mechanically managed portfolios (G11) | optimization of the portfolio strategy over time (G11) |
| conditioning variables (C29) | portfolio weights (G11) |
| portfolio weights (G11) | expected returns and risk (G17) |
| state variables (C29) | portfolio weights (G11) |
| managed portfolios (G11) | expected returns (G17) |