Abstract

Green and Hollifield (1992) argue that the presence of a dominant factor would result in extreme negative weights in mean-variance efficient portfolios even in the absence of estimation errors. In that case, imposing no-short-sale constraints should hurt, whereas empirical evidence is often to the contrary. We reconcile this apparent contradiction. We explain why constraining portfolio weights to be nonnegative can reduce the risk in estimated optimal portfolios even when the constraints are wrong. Surprisingly, with no-short-sale constraints in place, the sample covariance matrix performs as well as covariance matrix estimates based on factor models, shrinkage estimators, and daily data.

Scientific Portfolio AI- Generated Summary

In their paper “Risk Reduction in Large Portfolios: Why Imposing the Wrong Constraints Helps,” Ravi Jagannathan and Tongshu Ma explore the benefits of imposing the wrong constraints when managing large portfolios. They argue that traditional portfolio optimization techniques, such as mean-variance optimization, can be improved by imposing additional constraints that are not necessarily optimal.

The authors begin by discussing the limitations of traditional portfolio optimization techniques, which often fail to account for the complexity of real-world investment scenarios. They argue that imposing additional constraints, such as upper bounds on portfolio weights or restrictions on short sales, can help to reduce risk and improve returns.

To support their argument, the authors provide a theoretical analysis of the shrinkage-like effect of imposing the no-short sales restriction and upper bounds on portfolio weights when constructing global minimum risk portfolios. They also use simulation to evaluate the tradeoff between specification error and sampling error, which depends on the true covariance structure of the assets.

The authors suggest that imposing the wrong constraints can help to reduce risk in large portfolios by limiting exposure to extreme events and reducing the impact of estimation error. They also argue that these constraints can help to improve diversification and reduce the impact of model misspecification.

Overall, Jagannathan and Ma provide valuable insights and suggestions for reducing risk in investment strategies. They suggest that investors should consider imposing additional constraints when managing large portfolios, even if these constraints are not necessarily optimal. By doing so, investors can improve their risk-return tradeoff and achieve better long-term performance.