A utility-based comparison of some models of exchange rate volatility

doi:10.1016/0022-1996(93)90003-G

Journal of International Economics

Volume 35, Issues 1–2, August 1993, Pages 23-45

https://doi.org/10.1016/0022-1996(93)90003-G Get rights and content

Abstract

When estimates of variances are used to make asset allocation decisions, underestimates of population variances lead to lower expected utility than equivalent overestimates: a utility-based criterion is asymmetric, unlike standard criteria such as mean squared error. To illustrate how to estimate a utility-based criterion, we use five bilateral weekly dollar exchange rates, 1973–1989, and the corresponding pair of Eurodeposit rates. Of homoskedastic, GARCH, autoregressive and non-parametric models for the conditional variance of each exchange rate, GARCH models tend to produce the highest utility, on average. A mean squared error criterion also favors GARCH, but not as sharply.

References (26)

Tim Bollerslev
Generalized autoregressive conditional heteroskedasticity
Journal of Econometrics
(1986)
Francis X. Diebold et al.
Nonparametric exchange rate prediction?
Journal of International Economics
(1990)
Robert McCulloch et al.
Posterior, predictive and utility-based approaches to testing the arbitrage pricing theory
Journal of Financial Economics
(1990)
Richard A. Meese et al.
Empirical exchange rate models of the seventies: Do they fit out of sample?
Journal of International Economics
(1983)
Adrian R. Pagan et al.
Alternative models for conditional stock volatility
Journal of Econometrics
(1990)
Vedat Akgiray
Conditional heteroskedasticity in time series of stock returns: Evidence and forecasts
Journal of Business
(1989)
Tim Bollerslev et al.
ARCH modelling in finance: A selective review of the theory and empirical evidence, with suggestions for future research
(1990)
William Breen et al.
Economic significance of predictable variations in stock index returns
Journal of Finance
(1989)
Francis X. Diebold
Empirical modelling of exchange rate dynamics
(1988)
Hali J. Edison et al.
Target zones, intervention and exchange rate volatility
(1991)

Robert F. Engle

Autoregressive conditional heteroskedasticity, with estimates of the variance of United Kingdom inflation

Econometrica

(1982)

Robert F. Engle et al.

Modelling the persistence of conditional variances

Econometric Reviews

(1986)

Robert F. Engle et al.

Valuation of variance forecasts with simulated options markets

(1990)

Cited by (208)

A credit-based theory of the currency risk premium
2023, Journal of Financial Economics
This paper uncovers a novel component for exchange rate predictability based on the price difference between sovereign credit default swaps denominated in different currencies. This new forecasting variable – the credit-implied risk premium – captures the expected currency depreciation conditional on a severe but rare credit event. Using data for 16 Eurozone countries, we find that the credit-implied risk premium positively forecasts the dollar-euro exchange rate return at various horizons. Moreover, a currency strategy that exploits the informative content of our predictor generates substantial out-of-sample economic value against the naïve random walk benchmark.
Forecasting exchange rate: A bibliometric and content analysis
2023, International Review of Economics and Finance
Citation Excerpt :
In conclusion, the authors found positive evidence in favor of this model compared to the classic monetary and the random walk models. ARCH and GARCH volatility models are also present, according to studies by Diebold and Nerlove (1989), West, Edison, and Cho (1993), and Alexander and Lazar (2006). Two of the 69 studies adopt the Markov Switching model (Frömmel, MacDonald, & Menkhoff, 2005; Sarno & Valente, 2005).
The study aims to present a systematic overview of the research in the field of exchange rate projection models through bibliometric techniques and content analysis. First, 775 articles published in journals within the scope of the international Web of Science database from 1966 to May 2021 were analyzed through bibliometric techniques. Second, a selected sample of 69 articles was analyzed through a detail content analysis to identify hot topics and new avenues of interest in the field. The research findings suggest that the scientific production on the subject is in wide development. New approaches have been incorporated, such as neural networks, requiring a broad perspective by the researcher in the evaluation of the empirical results.
Realizing correlations across asset classes
2022, Journal of Financial Markets
We introduce a simple and intuitive composite model for forecasting correlations for use in portfolio optimization. Each element of the composite model is based on a realized volatility model. To test our model, we consider an investor seeking to diversify an equity portfolio by including commodities. In a high-frequency setting, we demonstrate that significant economic gains can be achieved by basing portfolio decisions on our modeling framework. The gains depend on the quality of the chosen volatility model, and for our preferred model, they are economically significant despite the realistic constraints on short selling and portfolio turnover.
Oil price volatility forecasts: What do investors need to know?
2022, Journal of International Money and Finance
Contrary to the current practice that mainly considers stand-alone statistical loss functions, the aim of the paper is to assess oil price volatility forecasts based on objective-based evaluation criteria, given that different forecasting models may exhibit superior performance at different applications. Thus, we forecast the implied and several intraday oil price volatilities and we evaluate them based on financial decisions for which these forecasts are used. Confining our interest on the use of such forecasts from financial investors, we consider four well-established volatility trading strategies. We evaluate the after-cost profitability of each forecasting model for 1-day up to 66-days ahead. Our results convincingly show that our forecasting framework is economically useful, since different models provide superior after-cost profits depending on the economic use of the volatility forecasts. Should investors evaluate the forecasting models based on statistical loss functions, then their financial decisions are sub-optimal. Several robustness tests confirm these findings.
Aggregation bias in tests of the commodity currency hypothesis
2022, Journal of Banking and Finance
According to the commodity currency hypothesis (CCH), a country’s commodity-export prices are predicted by its exchange rate. We investigate two types of aggregation biases that might affect CCH tests. First, monthly commodity prices are sometimes averaged across all days of the month, a practice that creates substantial spurious predictability in price changes. Second, in CCH tests commodity prices are often grouped into an index. If all commodity prices do not react equally fast to news, the active goods’ prices should lead those of the slower-acting ones and therefore predict the index. If so, the currency’s value changes can proxy for these active goods’ prices. We find a strong bias from price averaging in monthly returns, while the bias from ignoring predictability among commodities seems weak. When testing the CCH using end-of-period data the supporting evidence is weak at best.
A comparison of non-Gaussian VaR estimation and portfolio construction techniques
2020, Journal of Empirical Finance
We propose a multivariate model of returns that accounts for four of the stylised facts of financial data: heavy tails, skew, volatility clustering, and asymmetric dependence with the aim of improving the accuracy of risk estimates and increasing out-of-sample utility of investors’ portfolios. We accommodate volatility clustering, the generalised Pareto distribution to capture heavy tails and skew, and the skewed-t copula to provide for asymmetric dependence. The proposed approach produces more accurate VaR estimates than seven competing approaches across eight data sets encompassing five asset classes. We show that this produces portfolios with higher utility, and lower downside risk than alternative approaches including mean–variance. We confirm that investors can substantially increase utility by accounting for departures from normality.

View all citing articles on Scopus

^∗: We thank an anonymous referee, Buz Brock, Frank Diebold, Takatoshi Ito, Blake LeBaron, Robin Lumsdaine and participants in various seminars for helpful comments and discussions, Karen Lewis for providing data, and John Hulbert for research assistance. West thanks the National Science Foundation, the Sloan Foundation, and the University of Wisconsin Graduate School for financial support. This paper represents the views of the authors and not necessarily those of the Board of Governors of the Federal Reserve System or other members of its staff.

View full text

A utility-based comparison of some models of exchange rate volatility

Abstract

Journal of Econometrics

Journal of International Economics

Journal of Financial Economics

Journal of International Economics

Journal of Econometrics

Conditional heteroskedasticity in time series of stock returns: Evidence and forecasts

Journal of Business

ARCH modelling in finance: A selective review of the theory and empirical evidence, with suggestions for future research

Economic significance of predictable variations in stock index returns

Journal of Finance

Empirical modelling of exchange rate dynamics

Target zones, intervention and exchange rate volatility

Autoregressive conditional heteroskedasticity, with estimates of the variance of United Kingdom inflation

Econometrica

Modelling the persistence of conditional variances

Econometric Reviews

Valuation of variance forecasts with simulated options markets