### Refine

#### Document Type

- Conference Proceeding (1)
- Working Paper (1)

#### Keywords

- Bayesian inference (2) (remove)

- How much foreign stocks? : Bayesian approaches to asset allocation can explain the home bias of US investors (2003)
- US investors hold much less foreign stocks than mean/variance analysis applied to historical data predicts. In this article, we investigate whether this home bias can be explained by Bayesian approaches to international asset allocation. In contrast to mean/variance analysis, Bayesian approaches employ different techniques for obtaining the set of expected returns. They shrink sample means towards a reference point that is inferred from economic theory. We also show that one of the Bayesian approaches leads to the same implications for asset allocation as mean-variance/tracking error criterion. In both cases, the optimal portfolio is a combination the market portfolio and the mean/variance efficient portfolio with the highest Sharpe ratio. Applying the Bayesian approaches to the subject of international diversification, we find that substantial home bias can be explained when a US investor has a strong belief in the global mean/variance efficiency of the US market portfolio and when he has a high regret aversion falling behind the US market portfolio. We also find that the current level of home bias can justified whenever regret aversion is significantly higher than risk aversion. Finally, we compare the Bayesian approaches to mean/variance analysis in an empirical out-ofsample study. The Bayesian approaches prove to be superior to mean/variance optimized portfolios in terms of higher risk-adjusted performance and lower turnover. However, they not systematically outperform the US market portfolio or the minimum-variance portfolio.

- How much foreign stocks? : classical versus Bayesian approaches to asset allocation (2003)
- The classical approaches to asset allocation give very different conclusions about how much foreign stocks a US investor should hold. US investors should either allocate a large portion of about 40% to foreign stocks (which is the result of mean/variance optimization and the international CAPM) or they should hold no foreign stocks at all (which is the conclusion of the domestic CAPM and mean/variance spanning tests). There is no way in between. The idea of the Bayesian approach discussed in this article is to shrink the mean/variance efficient portfolio towards the market portfolio. The shrinkage effect is determined by the investor's prior belief in the efficiency of the market portfolio and by the degree of violation of the CAPM in the sample. Interestingly, this Bayesian approach leads to the same implications for asset allocation as the mean-variance/tracking error criterion. In both cases, the optimal portfolio is a combination of the market portfolio and the mean/variance efficient portfolio with the highest Sharpe ratio. Applying both approaches to the subject of international diversification, we find that a substantial home bias is only justified when a US investor has a strong belief in the global mean/variance efficiency of the US market portfolio and when he has a high regret aversion of falling behind the US market portfolio. We also find that the current level of home bias can be justified whenever-regret aversion is significantly higher than risk aversion. Finally, we compare the Bayesian approach of shrinking the mean/variance efficient portfolio towards the market portfolio to another Bayesian approach which shrinks the mean/variance efficient portfolio towards the minimum-variance portfolio. An empirical out-of-sample study shows that both Bayesian approaches lead to a clearly superior performance compared to the classical mean/variance efficient portfolio.