# Portfolio Risk Analysis

Gregory Connor
Lisa R. Goldberg
Robert A. Korajczyk
Pages: 400
https://www.jstor.org/stable/j.ctt7sm49

1. Front Matter
(pp. i-vi)
(pp. vii-x)
3. Acknowledgments
(pp. xi-xii)
4. Introduction
(pp. xiii-xviii)

This book provides a quantitative, technical treatment of portfolio risk analysis with a focus on real-world applications. It is intended for both academic and practitioner audiences, and it draws its inspiration and ideas from both the academic and practitioner research literature. Quantitative modeling for portfolio risk management is an active research field. Virtually all institutional investment management firms use quantitative models as an integral part of their portfolio riskmanagement procedures. Research and development on these models takes place at investment management firms, brokerage houses, investment consultants, and risk-management software providers. Academic researchers have explored the econometric foundations of portfolio risk...

5. Key Notation
(pp. xix-xxiv)
6. 1 Measures of Risk and Return
(pp. 1-35)

Section 1.1 gives definitions of portfolio return. Section 1.2 introduces some key portfolio risk measures used throughout the book. Section 1.3 discusses risk–return preferences and portfolio optimization. Section 1.4 discusses the capital asset pricing model (CAPM). In that section we relate the CAPM to the more general state-space pricing model, and critically assess its applications to portfolio risk management. Section 1.5 takes a broader perspective, discussing the institutional environment and overall objectives of portfolio risk management, and its fundamental limitations.

Except where noted, throughout the book we work in terms of a unit investment, that is, an investment with...

7. 2 Unstructured Covariance Matrices
(pp. 36-60)

This chapter considers the estimation and use of return covariance matrices without any factor structure imposed upon them. Following this, in chapters 3–6, we consider structured covariance matrices.

Section 2.1 discusses the estimation of return covariance matrices using classical statistical methods. Section 2.2 describes the errormaximization problem in portfolio management and its implications for risk modeling. Section 2.3 treats portfolio risk management as a problem in decision making under uncertainty, and considers the Bayesian approach to covariance matrix estimation.

This chapter is concerned with the estimation of the$n\; \times \;n$covariance matrix of returns or excess returns. Since, by definition,...

8. 3 Industry and Country Risk
(pp. 61-78)

Estimating country and industry risk factors is of paramount importance in the design and implementation of portfolio risk models. Country and industry allocations are a major determinant of the riskiness of a global equity portfolio, particularly when risk is measured relative to a standard benchmark portfolio. The expansion of the corporate bond market to a wider range of countries has led to an emergent interest in country–industry factors in corporate bond returns.

Country–industry models typically have a very simple structure, with each security having a unit exposure to exactly one industry and one country. Despite their simplicity, these...

9. 4 Statistical Factor Analysis
(pp. 79-100)

The three types of factor models are statistical, macroeconomic and characteristic based. This chapter considers statistical factor models, which are the most technically difficult of the three classic types but also the most fundamental.

Section 4.1 describes the basic types of statistical factor models. Section 4.2 looks at approximate factor models, which impose an approximate structure on the covariance matrix as the number of assets becomes large. Section 4.3 discusses the arbitrage pricing theory and its applications to portfolio risk management. Section 4.4 considers “smalln” factor model estimation techniques, in which the number of assets is small relative to the...

10. 5 The Macroeconomy and Portfolio Risk
(pp. 101-116)

Factor models of security returns divide returns into components that are specific to individual assets or small groups of assets and components that are common and pervasive across many assets. The pervasive components are caused by new information or events that affect most or all assets. In many cases these pervasive shocks can be traced to new realizations or changes in expectations about macroeconomic variables. Understanding the relationships between asset returns and the macroeconomy gives the analyst a deeper understanding of the pervasive risks in security markets.

Section 5.1 discusses the estimation of macroeconomic factor models. Section 5.2 analyzes the...

11. 6 Security Characteristics and Pervasive Risk Factors
(pp. 117-133)

Observable characteristics of equities such as market capitalization, book-to-price ratio and other accounting ratios, and return-based characteristics such as momentum and volatility have surprisingly strong power in explaining the comovements of individual equity returns. Similarly (but less surprisingly), cash flow and credit characteristics explain the comovements of individual bonds. This chapter explores the empirical link between security characteristics and return comovements and discusses how best to incorporate them into portfolio risk analysis models. Section 6.1 discusses some of the stock and bond market characteristics with empirical links to return comovements. Section 6.2 introduces Rosenberg’s approach to factor modeling of security...

12. 7 Measuring and Hedging Foreign Exchange Risk
(pp. 134-154)

Foreign exchange risk is an important component of international portfolio risk. In this chapter we study the empirical properties of currency risk and develop risk model architecture that includes it.

Section 7.1 describes an approximation method for decomposing the total return on a foreign investment into currency-unrelated return (called local return) and currency-only return. This decomposition can be employed in building a portfolio risk model with three components: a local risk component, a currency risk component, and a component measuring the covariances between local and currency returns. Section 7.2 discusses currency hedging models from both short-horizon and long-horizon investment perspectives....

13. 8 Intergrated Risk Models
(pp. 155-166)

Previous chapters have discussed risk models for individual asset classes such as stocks, bonds, and foreign exchange. This chapter discusses the integration of asset-class risk models into models of aggregate portfolio risk, reaching across asset types and across national borders. The choice of architecture for a multicountry and/or multitype risk model depends crucially on the empirical structure of returns. If the common factors across asset types and countries are nearly the same, then the best architecture is a fully integrated approach. If, on the other hand, the markets are subject to very different factor risks, then a more segmented approach...

14. 9 Dynamic Volatilities and Correlations
(pp. 167-190)

The evidence for dynamic patterns in portfolio risk is very strong, with a variety of dynamic patterns clearly documented across a range of asset classes. The influence of these dynamic features on accurate portfolio risk analysis can be substantial. This chapter reviews some of the empirical evidence and discusses analytical refinements to portfolio risk analysis models to account for these dynamic patterns. Section 9.1 deals with generalized autoregressive conditional heteroskedasticity (GARCH) models and section 9.2 with stochastic volatility (SV) models. Section 9.3 discusses time aggregation of risk forecasts in the presence of risk dynamics. Section 9.4 examines the issue of...

15. 10 Portfolio Return Distributions
(pp. 191-211)

In previous chapters we have usually taken a narrow view of risk as the variance of return. In this chapter we take a broader view and consider the full distribution of portfolio return. All familiar risk measures, including variance, value-at-risk (VaR), and expected shortfall, can be derived from the return distribution. Although the approach to analyzing risk taken in this chapter is much broader, we will see that there are considerable costs in terms of the statistical reliability of the derived risk measures.

In section 10.1 we describe the main measures of a return distribution, including the cumulative distribution, the...

16. 11 Credit Risk
(pp. 212-240)

Credit risk refers to the uncertainty about whether a counterparty will honor a financial obligation. It is present to some degree in every financial asset and is therefore a central component of portfolio risk. Credit exposure is actively traded, giving rise toindirect credit risk. For example, a commercial bank owning home mortgages can package and sell the cash flows of these mortgages to insurance companies and other financial institutions. A homeowner defaulting on his mortgage obligation to the bank generates indirect credit risk for the insurance company, since the defaulted cash flow is passed through. Similarly, an investment bank...

17. 12 Transaction Costs and Liquidity Risk
(pp. 241-270)

Understanding and managing transaction costs is a critical component of portfolio risk analysis. Optimal rebalancing and hedging policies are heavily affected by consideration of transaction costs. Also, liquidity risk, which is the uncertainty connected to the ability to liquidate or rebalance a portfolio at a “fair price,” is a very important component of portfolio risk, particularly during periods of market turmoil.

Section 12.1 provides some basic definitions. Section 12.2 discusses theoretical and econometric models of transaction costs. Section 12.3 looks at the time-series behavior of transaction costs and liquidity and their correlation with market movements. Section 12.4 considers optimal trading...

18. 13 Alternative Asset Classes
(pp. 271-298)

Investments outside of the traditional mix of publicly traded equities, bonds, and money market instruments are generally referred to as alternative assets. These alternative investments include hedge funds, private equity, real estate, timberland, commodities, and collectibles. They pose interesting problems for portfolio risk analysis. While this is a diverse set of assets, two common features are low and unreliable levels of liquidity for the assets and limited information on transaction prices.¹ Some issues that are of primary interest in risk analysis of these assets are stale or smoothed valuations due to lack of current market pricing; style drift caused by...

19. 14 Performance Measurement
(pp. 299-318)

The purpose of portfolio performance measurement is to monitor, motivate, and reward portfolio managers. Although not strictly part of portfolio risk analysis, performance measurement is closely linked to it, since one of its fundamental objectives is to assess the balance between portfolio risk and realized return. Also, performance measurement is intimately linked with manager compensation, and compensation has powerful effects on portfolio risk through its influence on manager behavior.

In this chapter we also consider the evaluation of portfolio riskforecasting accuracy. This is essentially performance evaluation applied to the risk-modeling system, and it is a topic that straddles traditional performance...

20. 15 Conclusion
(pp. 319-322)

This book provides an overview of quantitative portfolio risk analysis, concentrating mainly on primary asset classes such as stocks, bonds, real estate, and foreign exchange. Our approach relies on statistical modeling of asset returns, framed by economic theory and cognizant of the institutional settings of contemporary capital markets.

One key message that emerges from empirical research over the last forty years is that risk regimes change, often suddenly and in unexpected ways. This emphasizes the importance of a solid understanding of the statistical modeling used for risk analysis and risk management. To prepare adequately for sudden shifts, and to adjust...

21. References
(pp. 323-344)
22. Index
(pp. 345-354)