Research and publications

Portfolio Choice with Model Misspecification: A Foundation for Alpha and Beta Portfolios

In this paper, our objective is to provide a rigorous foundation for alpha and beta portfolio strategies. In particular, we characterize the properties of these strategies when there is model misspecification in either the alpha component or the beta component of returns and show how to mitigate the effect of model misspecification for portfolio choice. The APT is ideal for this analysis because it allows for alphas, while still imposing no arbitrage. Our first contribution is to extend the interpretation of the APT to show that it can capture not just small pricing errors that are independent of factors but also large pricing errors arising from mismeasured or missing factors. Our second contribution is to show that under the APT, the optimal mean-variance portfolio in the presence of a risk-free asset can be decomposed into two components: an 'alpha' portfolio that depends only on pricing errors and a 'beta' portfolio that depends only on factor risk premia and their loadings.

Author(s) :

Raman Uppal, Paolo Zaffaroni

Summary :

In this paper, our objective is to provide a rigorous foundation for alpha and beta portfolio strategies. In particular, we characterize the properties of these strategies when there is model misspecification in either the alpha component or the beta component of returns and show how to mitigate the effect of model misspecification for portfolio choice. The APT is ideal for this analysis because it allows for alphas, while still imposing no arbitrage. Our first contribution is to extend the interpretation of the APT to show that it can capture not just small pricing errors that are independent of factors but also large pricing errors arising from mismeasured or missing factors. Our second contribution is to show that under the APT, the optimal mean-variance portfolio in the presence of a risk-free asset can be decomposed into two components: an 'alpha' portfolio that depends only on pricing errors and a 'beta' portfolio that depends only on factor risk premia and their loadings.

Type : Working paper
Date : 07/05/2016
Keywords :

Portfolio Management