Hedge Fund Index Returns Research Articles

Hedge Funds vs. Alternative Risk Premia

Alternative risk premia (ARP) are designed to provide low-cost exposures to long–short risk premia often embedded in hedge fund returns. This article describes the performance of the ARP market in the form of bank-provided total return swaps, which are investable strategies that provide after-cost access to ARP. Over the 2010–20 period, many of these risk premia provided significantly positive returns. In addition, these ARP explain a high fraction of returns on hedge fund indexes, especially for quantitative strategies, along with traditional market factors. Finally, we find that ARP and market factors largely eat away hedge fund index returns.

Hedge Fund Returns Characterized by Correlation Regimes (Presentation Slides)

We compute monthly correlation matrices of 25 global futures markets in four asset classes: fixed income, commodities, equities, fx. Comparing and grouping those correlation matrices leads to distinct «regimes» in time. We can characterize these regimes by futures market returns, finding patterns between risk-on and risk-off assets. One of those regimes is especially «risk-off». We can also characterize these regimes by CS hedge fund index returns. In the «risk-off» regime, they also underperform. The Eurekahedge EHF funds show a similar performance behaviour according to strategies across regimes as the CS hedge fund indices. The dispersion across the Eurekahedge EHF funds for each month is largest in the «risk-off» regime.

Dynamic Hedge Fund Portfolio Construction: A Semi-Parametric Approach

In this paper, we evaluate alternative optimization frameworks for constructing portfolios of hedge funds. Using monthly hedge fund index returns for the period 1990 to 2011, we compare the standard mean-variance optimization model with models based on CVaR, CDaR and Omega, for both conservative and aggressive hedge fund investment strategies. In order to implement the CVaR, CDaR and Omega optimization models, we propose a semi-parametric methodology, in which we first model the marginal density of each hedge fund index using extreme value theory and construct the joint density of hedge fund index returns using a copula-based approach. We then simulate hedge fund returns from this joint density in order to compute CVaR, CDaR and Omega, which are used in the optimization process. We compare the semi-parametric approach with the standard, non-parametric approach, in which the quantiles of the marginal density of portfolio returns are estimated empirically and used to compute CVaR, CDaR and Omega. We report two main findings. The first is that the CVaR, CDaR and Omega models offer a significant improvement in terms of risk-adjusted portfolio performance over the mean-variance model. The second is that semi-parametric estimation of the CVaR, CDaR and Omega models offers a very substantial improvement over non-parametric estimation. Our results are robust to the choice of target return, risk limit and estimation sample size.

Non-Parametric Analysis of Hedge Fund Returns: New Insights from High Frequency Data

The history of financial research often reflects the history of the changing nature of financial data. Simply put, one has a difficult time analyzing questions requiring empirical data that does not exist. In the area of hedge funds, currently-available databases provide only monthly returns. Moreover, various providers of hedge fund index data follow very different methodologies in structuring hedge fund indices. This article examines four daily hedge fund return indices: MSCI, FTSE, Dow Jones, and HFRX, all based on investable hedge funds, and three monthly hedge fund return indices: CSFB Tremont, CISDM, and HFR, which comprise both investable and non-investable hedge funds. This study, based on standard statistical analysis, non-parametric analysis of the return distribution, and non-parametric regressions with respect to the S&amp;P500 index, shows that key biases like fund selection, asset liquidity,data frequency, sample period, and index construction methodologies are responsible for different statistical properties of hedge fund indices.One key variable that highly affects the statistical properties of hedge fund index returns is the “investability” of hedge fund indices. <b>TOPICS:</b>Real assets/alternative investments/private equity, big data/machine learning, mutual funds/passive investing/indexing, performance measurement

Non-Parametric Analysis of Hedge Fund Returns: New Insights from High Frequency Data

This paper examines four daily hedge fund return indices: MSCI, FTSE, Dow Jones, and HFRX, all based on investable hedge funds, and three monthly hedge fund return indices: CSFB Tremont, CISDM, and HFR, which comprise both investable and non-investable hedge funds. Our study, based on standard statistical analysis, non-parametric analysis of the return distribution, and non-parametric regressions with respect to the S&P 500 index shows that key biases like fund selection, asset liquidity, data frequency, sample period, and index construction methodologies are responsible for different statistical properties of hedge fund indices. One key variable that highly affects the statistical properties of hedge fund index returns is the “investability” of hedge fund indices.

Arbitrage Capital and Currency Carry Trade Returns

In carry trades the purchase of riskier, higher-yielding currencies is funded by selling lower-yielding currencies. In our model, with partially segmented markets and limited arbitrage capital, the returns to carry trades are positive, but decrease in the amount of arbitrage capital. Empirically, we find: 1) carry trade returns explain hedge fund index returns, 2) due to an increase in arbitrage capital, the carry trade returns have been decreasing over time, 3) higher arbitrage capital decreases the cross country differences in real interest rates, 4) flow of new arbitrage capital leads to an appreciation (depreciation) of the carry long (short) currencies.

Hedge Fund Return Statistics 1994–2005

In this article we examine various statistical properties of several hedge fund style returns. We use hedge fund indices from CSBF/Tremont as well as global bonds and equity investment indices covering the period 1994–2005. We find that some of the hedge fund styles seem to have a higher mean return and a lower standard deviation than the equity market. We also find the index return distributions to be not normal and exhibit negative skewness and positive excess kurtosis for several styles. We also utilize stochastic dominance as a tool for ranking the best risk-adjusted investment style. Many hedge fund index returns have a high positive correlation with the stock market while most styles are nearly uncorrelated with the bond market. A high correlation with the equity market put the diversification effect of hedge funds into question <b>TOPICS:</b>Real assets/alternative investments/private equity, security analysis and valuation, risk management

Arbitrage Capital and Currency Carry Trade Returns

We develop a model based on risk averse investors and limited arbitrage capital to explain the rationale for the so called carry trades: that is, trades where “the purchase of riskier, higher-yielding assets is funded by selling lower-yielding currencies” (Financial Times, January 28, 2008). In our model, due to partially segmented markets and differences in inflation risk and money supply, the returns to carry trades are positive, but decrease in the amount of arbitrage capital. In the empirical part of the paper, using 32 years of exchange rate data, we document several new results related to carry trades and provide empirical support for the model’s predictions. We empirically document that 1) carry trade returns explain a significant part of hedge fund index returns, providing strong evidence that carry trades are indeed used by arbitrageurs, 2) the positive returns to carry trades have been decreasing over time in parallel with an increase in arbitrage capital, 3) the real interest rates are higher in countries with higher inflation risk and higher per capita money supply, but higher arbitrageurs’ equity capital and a better funding liquidity for them decrease the cross country differences in real interest rates, 4) flow of new arbitrage capital leads to an appreciation (depreciation) of the carry long (short) currencies.

Alternative Routes to Hedge Fund Return Replication

The author starts with the observation that although institutions are still pouring more and more money into hedge funds, hedge fund performance is clearly deteriorating. In part, this reflects lower interest rates and a global decline in risk premiums. Part of hedge funds9 disappointing performance, however, is also due to the huge inflow of institutional money itself. The author then notes that driven by a desire to reduce costs and improve investor returns, the market has recently seen several attempts to “replicate” hedge fund index returns. Stating that the driving force behind hedge fund replication is the realization that the majority of hedge fund managers do not have enough skill to make up for the fees they charge, the author argues that it may be worthwhile to replace the managers in question with a synthetic hedge fund. Synthetic hedge funds produce no pre-fee alpha, but they don9t cost a fortune to run and may therefore very well produce significant after-fee alpha. In addition, synthetic hedge funds come with great improvements in liquidity, transparency, capacity, etc. The article proceeds to discuss three different approaches to replications. <b>TOPICS:</b>Real assets/alternative investments/private equity, mutual funds/passive investing/indexing, portfolio construction, performance measurement

A Learning-Based Linear Replicator for Hedge Fund Indexes

There has been great interest in creating portfolios using common liquid instruments to replicate hedge fund returns. In a recent article, Hasanhodzic and Lo (2007) demonstrate that a factor-based approach based on a linear regression model with 5 tradable risk factors can adequately replicate monthly returns of 1,610 hedge funds in 1986 to 2005. We propose a learning-based linear replication algorithm to enhance the linear model. Results show that our approach can improve the replicating capability of linear replicator, especially for some nonlinear and dynamic strategies, e.g., Event-driven and Emerging Markets. The annualized root mean squared error is improved by 40% and 34%, respectively. The new method can automatically detect the market changes and separate return points into different polyhedral regions, even high dimensions (multiple risk factors). By using 12 major strategy indexes' monthly returns compiled by 7 data vendors from their inception date until December 2008, we examine our method with six common risk factors and find that our algorithm can improve explanatory of hedge fund index returns. The performance of our new replicator is also tested by cloning out-of-sample monthly returns through using five out of these six factors.

Portfolio Optimization and Hedge Fund Style Allocation Decisions

This article attempts to evaluate the out-of-sample performance of an improved estimator of the covariance structure of hedge fund index returns, focusing on its use for optimal portfolio selection. Using data from CSFB/Tremont hedge fund indices, we find that ex-post volatility of minimum variance portfolios generated using implicit factor-based estimation techniques is between 1.5 and 6 times lower than that of a value-weighted benchmark, such differences being both economically and statistically significant. This strongly indicates that optimal inclusion of hedge funds in an investor portfolio can potentially generate a dramatic decrease in the portfolio volatility on an out-of-sample basis. Differences in mean returns, on the other hand, are not statistically significant, suggesting that the improvement in terms of risk control does not necessarily come at the cost of lower expected returns.

The Statistical Properties of Hedge Fund Index Returns and Their Implications for Investors

The monthly return distributions of many hedge fund indices exhibit highly unusual skewness and kurtosis properties as well as first-order serial correlation. This has important consequences for investors. Although many hedge fund indices are highly attractive in mean-variance terms, this is much less the case when skewness, kurtosis and autocorrelation are taken into account. Sharpe ratios will substantially overestimate the true risk/return performance of (portfolios containing) hedge funds. Similarly, mean-variance portfolio analysis will overestimate the benefits of including hedge funds in an investment portfolio and therefore overallocate to hedge funds. We also find substantial differences between indices that aim to cover the same type of strategy. Investors9 perceptions of hedge fund performance and value added will therefore strongly depend on the indices used.

Evidence of Predictability in Hedge Fund Returns and Multi-Style Multi-Class Tactical Style Allocation Decisions

While there has been a significant amount of research on the predictability of traditional asset classes, very little is known about the predictability of returns emanating from alternative vehicles such as hedge funds. This is perhaps surprising, given that significant attempts at structuring the alternative investment markets have occurred over the last decade which now allow investors to implement dynamic trading strategies in hedge fund indexes. This paper attempts to fill this gap by documenting evidence of predictability in hedge fund index returns, focusing on their use for tactical style allocation decisions. Using data from nine CSFB-Tremont hedge fund indexes, we find that there is strong evidence of very significant predictability in hedge fund returns. We also find that the benefits in terms of tactical style allocation portfolios are potentially very large. Even more spectacular results are obtained both for an equity-oriented portfolio mixing traditional and alternative investment vehicles, and for a fixed-income oriented portfolio mixing traditional and alternative investment vehicles. These results do not seem to be significantly affected by the presence of reasonably high transaction costs.

Portfolio Optimization and Hedge Fund Style Allocation Decisions

This paper attempts to evaluate the out-of-sample performance of an improved estimator of the covariance structure of hedge fund index returns, focusing on its use for optimal portfolio selection. Using data from CSFB-Tremont hedge fund indices, we find that ex-post volatility of minimum variance portfolios generated using implicit factor based estimation techniques is between 1.5 and 6 times lower than that of a value-weighted benchmark, such differences being both economically and statistically significant. This strongly indicates that optimal inclusion of hedge funds in an investor portfolio can potentially generate a dramatic decrease in the portfolio volatility on an out-of-sample basis. Differences in mean returns, on the other hand, are not statistically significant, suggesting that the improvement in terms of risk control does not necessarily come at the cost of lower expected returns.

The Statistical Properties of Hedge Fund Index Returns and Their Implications for Investors

The monthly return distributions of many hedge fund indices exhibit highly unusual skewness and kurtosis properties as well as first-order serial correlation. This has important consequences for investors. We demonstrate that although hedge fund indices are highly attractive in mean-variance terms, this is much less the case when skewness, kurtosis and autocorrelation are taken into account. Sharpe Ratios will substantially overestimate the true risk-return performance of (portfolios containing) hedge funds. Similarly, mean-variance portfolio analysis will over-allocate to hedge funds and overestimate the attainable benefits from including hedge funds in an investment portfolio. We also find substantial differences between indices that aim to cover the same type of strategy. Investors' perceptions of hedge fund performance and value added will therefore strongly depend on the indices used.