Asset Allocation under Parameter Uncertainty
organized by
Alex Weissensteiner, Free University of Bozen-Bolzano, Italy
In many decision problems relevant input parameters are unknown. Errors in the estimates of these values will lead to a sub-optimal decision. Cynics claim that optimizers maximize input errors. Indeed, over the last years a lot of effort has been devoted to mitigate this problem: Jorion (1986, 1991) proposed the Bayes-Stein approach, Michaud (1998) resampling, Black-Litterman combining views with equilibrium expected returns, DeMiguel et al. (2009) constraints on the norm of the portfolio weights. The academic discussion on asset allocation under parameter uncertainty is still ongoing. The workshop aims at addressing this issue in a very broad sense.
venue: Free University of Bolzano - Room E-422
date: May 29, 2015
map: see below
Invited speakers
Martin Bohl - University of Muenster
Nicole Branger - University of Muenster
Thomas Dangl - TU Wien
Massimo Guidolin - Bocconi University
Katarina Lucivjanska-Kvasnakova - VU Amsterdam
Michael Hanke - University of Liechtenstein
Rolf Poulsen - University of Copenhagen
Christian Wagner - Copenhagen Business School
Thursday, May 28 come together
18:15 meeting in the lobby of the Mondschein Hotel
19:00 visit of the MUSEION (museum of modern art)
20:00 dinner at Torgglhaus
Friday, May 29 scientific program
09:00 - 09:15 greetings from the dean Lucie Courteau
09:15 - 10:00 Risk Control in Asset Management: Motives and Concepts (T. Dangl)
10:00 - 10:45 On the Riskiness of Stocks for the Long Run: Asset Pricing Perspectives (K. Lucivjanska-Kvasnakova)
10:45 - 11:15 coffee break
11:15 - 12:00 The Fundamental Theorem of Derivative Trading (R. Poulsen)
12:00 - 12:45 Robustness of Stable Volatility Strategies (N. Branger)
12:45 - 14:15 lunch break
14:15 - 15:00 Strategic Asset Allocation under Structurally Unstable Predictability (M. Guidolin)
15:00 - 15:45 Low Risk Anomalies? (C. Wagner)
15:45 - 16:15 coffee break
16:15 - 17:00 A Premium for Parameter Uncertainty in Equities (M. Hanke)
17:00 - 17:45 Price Discovery in Thinly Traded Futures Markets: How Thin Is too Thin? (M. Bohl)
17:45 - 18:00 discussion
19:30 dinner at Voegele
Abstract of invited talks:
Risk Control in Asset Management: Motives and Concepts (SSRN)
Thomas Dangl (Vienna University of Technology), Otto Randl (Vienna University of Economics and Business), Josef Zechner (Vienna University of Economics and Business)
Abstract:
In traditional portfolio theory, risk management is limited to the choice of the relative weights of the riskless asset and a diversifed basket of risky securities, respectively. Yet in industry, risk management represents a central aspect of asset management, with distinct responsibilities and organizational structures. We identify frictions that lead to increased importance of risk management and describe three major challenges to be met by the risk manager. First, we derive a framework to determine a portfolio position's marginal risk contribution and to decide on optimal portfolio weights of active managers. Second, we survey methods to control downside risk and unwanted risks since investors frequently have non-standard preferences which make them seek protection against excessive losses. Third, we point out that quantitative portfolio management usually requires the selection and parametrization of stylized models of financial markets. We therefore discuss risk management approaches to deal with parameter uncertainty, such as shrinkage procedures or resampling procedures, and techniques of dealing with model uncertainty via methods of Bayesian model averaging.
On the Riskiness of Stocks for the Long Run: Asset Pricing Perspectives
Doron Avramov (The Hebrew University of Jerusalem, Israel), Scott Cederburg (University of Arizona), Katarina Lucivjanska-Kvasnakova (VU Amsterdam)
Abstract:
This paper studies the long run riskiness of equities when the traditional predictive regression model follows the guidance implied by asset pricing theories. In particular, the dynamics of the equity premium and state variables conform to the behavioral prospect theory and the traditional long run risk theory. Risk for the long run is also examined when the equity premium is constrained to be nonnegative. In the presence of structure implied by economic theory, the investor's perception of stock volatility in the long run is considerably different. While the prospect theory magnifies mean reversion effects and ultimately suggests that stocks are less risky in longer horizon, the long run risk model and the non-negativity constraint both soften mean reversion, and future uncertainty prevails. Then investors essentially perceive stocks to be more risky in the long horizons.
The Fundamental Theorem of Derivative Trading - Exposition, Extensions, and Experiments (SSRN)
Simon Ellersgaard (University of Copenhagen), Martin Jönsson (University of Copenhagen), and Rolf Poulsen (University of Copenhagen)
Abstract:
When estimated volatilities are not in perfect agreement with reality, delta hedged option portfolios will incur a non-zero profit-and-loss over time. There is, however, a surprisingly simple formula for the resulting hedge error, which has been known since the late 90s. We call this The Fundamental Theorem of Derivative Trading. This paper is a survey with twists of that result. We prove a more general version of it and discuss various extensions (including jumps) and applications (including deriving the Dupire-Gyöngy-Derman formula). We also consider its practical consequences both in simulation experiments and on empirical data thus demonstrating the benefits of hedging with implied volatility.
Robustness of Stable Volatility Strategies (SSRN)
Nicole Branger (University of Muenster), Antje Mahayni (University of Duisburg-Essen), Daniel Zieling (University of Duisburg-Essen)
Abstract:
The paper analyzes the robustness of stable volatility strategies, i.e. strategies in which the portfolio weight of the stock is inversely proportional to its local volatility. These strategies are optimal for a CRRA investor if the stock follows a diffusion process, the expected excess return is proportional to its volatility, and the hedging demand is zero. We assess the performance of stable volatility strategies when these restrictive assumptions do not hold, in particular, when the risk premium is not proportional to volatility and when the stock price is subject to jumps. We find that stable volatility strategies are indeed robust or close to robust under a maxmin decision rule. In addition to our theoretical results, we perform a simulation analysis to evaluate strategies that scale the portfolio weight by the volatility, variance or a constant portfolio weight, and also analyze the strategies using empirical excess returns. Both analyses confirm the robustness of stable volatility strategies.
Strategic Asset Allocation under Structurally Unstable Predictability
Massimo Guidolin (Bocconi University), Francesco Ravazzolo (Norges Bank), Zhiping Zhou (Bocconi University)
Abstract:
This paper contributes to the long-standing debate on the economic value of the predictability of stock and bond returns by specifying, estimating using MCMC, and forecasting the joint density of asset returns from a flexible econometric model that captures all possible sources of uncertainty plaguing standard portfolio exercises, i.e., parameter uncertainty, model uncertainty, and structural instability. An application to two canonical portfolio problems (i.e., switching strategies a' la Pesaran and Timmermann, 1995, and buy-and-hold expected utility maximization a' la Barberis, 2000) shows that the relative value to be attached to parameter and model uncertainty vs. structural instability differ according to the investment horizon and
the type of preferences. Parameter and model uncertainty lead to higher performance improvements for very short-term, risk-averse investors; to longer horizon investors, structural instability becomes more relevant but because the overall amount of return predictability weakens, it is often the case that simple benchmark strategies end up outperforming our rich model.
Low Risk Anomalies? (SSRN)
Paul Schneider (Univerity Lugano) / Christian Wagner (Copenhagen Business School) / Josef Zechner (Vienna University of Economics and Business)
Abstract:
This paper shows theoretically and empirically that beta- and volatility-based low risk anomalies are driven by return skewness. The empirical patterns concisely match the predictions of our model that endogenizes the role of skewness for stock returns through default risk. With increasing downside risk, the standard capital asset pricing model (CAPM) increasingly overestimates expected equity returns relative to firms' true (skew-adjusted) market risk. Empirically, the profitability of betting against beta/volatility increases with firms' downside risk, and the risk-adjusted return differential of betting against beta/volatility among low skew firms compared to high skew firms is economically large. Our results suggest that the returns to betting against beta or volatility do not necessarily pose asset pricing puzzles but rather that such strategies collect premia that compensate for skew risk. Since skewness is directly connected to default risk, our results also provide insights for the distress puzzle.
A Premium for Parameter Uncertainty in Equities
Michael Hanke (Universität Liechtenstein), Sebastian Stöckl (Universität Liechtenstein), Alex Weissensteiner (Free University of Bolzano/Bozen)
Abstract:
The literature on the effects of parameter uncertainty on optimal portfolio choice suggests the existence of a premium for parameter uncertainty in asset returns. We use a simple extension to classical mean-variance portfolio optimization and devise a robust strategy to benefit from such a premium. Using well-known, long time series of equity returns, we show that this strategy indeed outperforms competitor strategies and yields positive and significant alphas relative to the most prominent factor models. We interpret these results to provide empirical support for the existence of a parameter uncertainty premium in equity returns.
Price Discovery in Thinly Traded Futures Markets: How Thin Is too Thin?
Philipp Adämmer (University of Münster) , Martin T. Bohl (University of Münster) and Christian Gross (University of Münster)
Abstract:
It is still an unanswered question how much trading activity is needed for efficient price discovery in commodity futures markets. For this purpose, we investigate the price discovery dynamics of two thinly traded agricultural futures contracts traded at the European Exchange in Frankfurt. Our empirical results show that the trading volume threshold which is necessary to facilitate efficient price discovery is very low. As our findings are based on constant and time-varying vector error correction models, we also show that neglecting time-variation in the parameters can lead to misleading results, especially for thinly traded markets.
Participation is free of charge - but please register by sending an email to: alex.weissensteiner@unibz.it
Arrival via train: both the university and the hotel are within walking distance