We evaluate the out-of-sample performance of sample-based mean-variance model, and its extensions designed to reduce estimation error, relative naive 1/N portfolio. Of 14 models we across seven empirical datasets, none is consistently better than rule in terms Sharpe ratio, certainty-equivalent return, or turnover, which indicates that, out sample, gain from optimal diversification more offset by error. Based on parameters calibrated US equity market, our analytical results simulations show...

We provide a general framework for finding portfolios that perform well out-of-sample in the presence of estimation error. This relies on solving traditional minimum-variance problem but subject to additional constraint norm portfolio-weight vector be smaller than given threshold. show our nests as special cases shrinkage approaches Jagannathan and Ma (Jagannathan, R., T. Ma. 2003. Risk reduction large portfolios: Why imposing wrong constraints helps. J. Finance 58 1651–1684) Ledoit Wolf...

Journal Article Portfolio Selection with Parameter and Model Uncertainty: A Multi-Prior Approach Get access Lorenzo Garlappi, Garlappi University of Texas at Austin Address correspondence to McCombs School Business, Austin, TX 78712, or e-mail: lorenzo.garlappi@mccombs.utexas.edu. Search for other works by this author on: Oxford Academic Google Scholar Raman Uppal, Uppal London Business CEPR Tan Wang British Columbia CCFR The Review Financial Studies, Volume 20, Issue 1, January 2007, Pages...

Abstract In this paper, we study intertemporal portfolio choice when an investor accounts explicitly for model misspecification. We develop a framework that allows ambiguity about not just the joint distribution of returns all stocks in portfolio, but also different levels marginal any subset these stocks. find overall is high, then small differences return will result significantly underdiversified relative to standard mean‐variance portfolio.

ABSTRACT Our objective is to identify the trading strategy that would allow an investor take advantage of “excessive” stock price volatility and “sentiment” fluctuations. We construct a general equilibrium “difference‐of‐opinion” model sentiment in which there are two classes agents, one overconfident about public signal, while still optimizing intertemporally. Overconfident investors overreact signal introduce additional risk factor causing prices be excessively volatile. Consequently,...

ABSTRACT Returns on international equities are characterized by jumps; moreover, these jumps tend to occur at the same time across countries leading systemic risk . We capture stylized facts using a multivariate system of jump‐diffusion processes where arrival is simultaneous assets. then determine an investor's optimal portfolio for this model returns. Systemic has two effects: One, it reduces gains from diversification and two, penalizes investors holding levered positions. find that loss...

ABSTRACT With transaction costs for trading goods, the nominal exchange rate moves within a band around purchasing power parity (PPP) value. We model behavior of and band. The explains why there are below‐unity slope coefficients in regression tests PPP, these increase toward unity under hyperinflation or with low‐frequency data. Our results independent presence nontraded goods economy.

Abstract Our objective in this paper is to examine whether one can use option-implied information improve the selection of mean-variance portfolios with a large number stocks, and document which aspects are most useful their out-of-sample performance. Portfolio performance measured terms volatility, Sharpe ratio, turnover. empirical evidence shows that using volatility helps reduce portfolio volatility. Using correlation does not any metrics. risk premium, skewness adjust expected returns...

Journal Article Asset Prices with Heterogeneity in Preferences and Beliefs Get access Harjoat S. Bhamra, Bhamra University of British Columbia Imperial College Send correspondence to Business School, College, South Kensington Campus, London SW7 2AZ, UK; telephone: +44 20 7594 9077. E-mail: h.bhamra@imperial.ac.uk. Search for other works by this author on: Oxford Academic Google Scholar Raman Uppal Edhec School CEPR The Review Financial Studies, Volume 27, Issue 2, February 2014, Pages...

Abstract We investigate how transaction costs change the number of characteristics that are jointly significant for an investor’s optimal portfolio and, hence, they dimension cross-section stock returns. find increase from 6 to 15. The explanation is that, as we show theoretically and empirically, combining reduces because trades in underlying stocks required rebalance different often cancel out. Thus, provide economic rationale considering a larger than prominent asset-pricing models....

This paper analyzes the strategy that minimizes initial cost of replicating a contingent claim in market with transactions costs and trading constraints. The linear programming two-stage backward recursive models developed are applicable to replication convex as well nonconvex payoffs portfolio options different maturities. paper's formulation conveniently accounts for fixed variable costs, lot size constraints, position limits on trading. article shows presence frictions, it is no longer...

We develop a model of portfolio choice to nest the views Keynes, who advocates concentration in few familiar assets, and Markowitz, diversification. use concepts ambiguity aversion formalize idea an investor's “familiarity” toward assets. The shows that for any given level expected returns, optimal depends on two quantities: relative across assets standard deviation return estimate each asset. If both quantities are low, then consists mix unfamiliar assets; moreover, increase correlation...

ABSTRACT We investigate, in a two‐country general equilibrium model, whether bias consumption towards domestic goods will necessarily lead to preference for securities. develop model where investors are constrained consume only from their capital stock and it is costly transfer across countries. In this less risk averse than an investor with log utility portfolios assets. Investors more log, however, prefer foreign Thus, suggests that unlikely the observed empirically can be explained by...

Journal Article Stock Return Serial Dependence and Out-of-Sample Portfolio Performance Get access Victor DeMiguel, DeMiguel London Business School Search for other works by this author on: Oxford Academic Google Scholar Francisco J. Nogales, Nogales Universidad Carlos III de Madrid Raman Uppal Edhec CEPR The Review of Financial Studies, Volume 27, Issue 4, April 2014, Pages 1031–1073, https://doi.org/10.1093/rfs/hhu002 Published: 06 February 2014

In this paper, we extend the mean-variance portfolio model where expected returns are obtained using maximum likelihood estimation to explicitly account for uncertainty about estimated returns. contrast Bayesian approach error, there is only a single prior and investor neutral uncertainty, allow multiple priors aversion uncertainty. We characterize set of as confidence interval around value return via minimization over priors. The multi-prior has several attractive features: One, just like...

Journal Article The Effect of Introducing a Non-Redundant Derivative on the Volatility Stock-Market Returns When Agents Differ in Risk Aversion Get access Harjoat S. Bhamra, Bhamra Search for other works by this author on: Oxford Academic Google Scholar Raman Uppal Review Financial Studies, Volume 22, Issue 6, June 2009, Pages 2303–2330, https://doi.org/10.1093/rfs/hhm076 Published: 11 December 2007

ABSTRACT Moreira and Muir question the existence of a strong risk‐return trade‐off by showing that investors can improve performance reducing exposure to risk factors when their volatility is high. However, Cederburg et al. show these strategies fail out‐of‐sample, Barroso Detzel they do not survive transaction costs. We propose conditional multifactor portfolio outperforms its unconditional counterpart even out‐of‐sample net Moreover, we factor prices generally decrease with market...

With transaction costs for trading goods, the nominal exchange rate moves within a band around purchasing power parity (PPP) value. We model behavior of and band. The explains why there are below-unity slope coefficients in regression tests PPP, these increase toward unity under hyperinflation or with low-frequency data. Our results independent presence nontraded goods economy.

We compare the performance of equal-, value-, and price-weighted portfolios stocks in major U.S. equity indices over last four decades. find that equal-weighted portfolio with monthly rebalancing outperforms value- terms total mean return, factor alpha, Sharpe ratio, certainty-equivalent even though has greater risk. The return exceeds because both a higher for bearing systematic risk alpha measured using four-factor model. nonparametric monotonicity relation test indicates differences is...

Returns on international equities are characterized by jumps; moreover, these jumps tend to occur at the same time across countries leading systemic risk. In this paper, we evaluate whether risk reduces substantially gains from diversification. First, in order capture stylized facts, develop a model of equity returns using multivariate system jump-diffusion processes where arrival is simultaneous assets. Second, determine an investor's optimal portfolio for returns. Third, show how one can...

Presents a rigorous and balanced presentation of international financial markets corporate finance. Takes unified approach based on arbitrage-fee pricing. Includes an in-depth discussion the economic role forward rate value contract, comprehensive when why firm can increase its by hedging foreign exchange risk, analysis various payment credit insurance techniques used in trade, more. Over 400 end-of-chapter problems test studentsAE understanding concepts.