856 research outputs found
Replication data for: Good Volatility, Bad Volatility: Signed Jumps and the Persistence of Volatility
No full textPatton, Andrew J., and Sheppard, Kevin, (2015) "Good Volatility, Bad Volatility: Signed Jumps and the Persistence of Volatility." Review of Economics and Statistics 97:3, 683-697
Twitters for a Lark: Poetry of the European Union of Imaginary Authors
No full textAn anthology of fictional European poets, written collaboratively by a team of real writers for a project created, curated and edited by Robert Sheppard, Emeritus Professor at Edge Hill University.
I have co-written (with Robert Sheppard) two poems by the imaginary author Hermes, along with his biographical note, for this anthology of imaginary authors
Realising the future: forecasting with high frequency based volatility (HEAVY) models
No full textThis paper studies in some detail a class of high frequency based volatility (HEAVY) models. These models are direct models of daily asset return volatility based on realized measures constructed from high frequency data. Our analysis identifies that the models have momentum and mean reversion effects, and that they adjust quickly to structural breaks in the level of the volatility process. We study how to estimate the models and how they perform through the credit crunch, comparing their fit to more traditional GARCH models. We analyse a model based bootstrap which allow us to estimate the entire predictive distribution of returns. We also provide an analysis of missing data in the context of these models.ARCH models; bootstrap; missing data; multiplicative error model; multistep ahead prediction; non-nested likelihood ratio test; realised kernel; realised volatility.
A "work in progress"? Public engagement is now part of the UK research landscape but challenges remain
No full textFunders of UK research have sought to foster a research culture in which public engagement is embedded at all levels. Kevin Burchell, Chloe Sheppard and Jenni Chambers report on research examining the extent of participation in public engagement by UK researchers, how it varies, and why. Large majorities of researchers have participated in public engagement and are broadly positive about it, while institutions are also shown to be supportive. However, a lack of time, opportunities, funding, and reward are cited as constraints. Meanwhile, public engagement appears more firmly embedded in the arts, humanities and social sciences than it is among STEM researchers. The provision of effective, accessible training is found to be an important precursor to participation in public engagement
54/11/04 Sheppard Drama Set To Unfold
No full textJurors solemnly take a tour of the Sheppard home in Bay Village, Ohio. Author describes the rooms they visited.https://engagedscholarship.csuohio.edu/newspaper_coverage/1360/thumbnail.jp
Do We Really Need Both BEKK and DCC? A Tale of Two Covariance Models
No full textLarge and very large portfolios of financial assets are routine for many individuals and organizations. The two most widely used models of conditional covariances and correlations are BEKK and DCC. BEKK suffers from the archetypal "curse of dimensionality" whereas DCC does not. This is a misleading interpretation of the suitability of the two models to be used in practice. The primary purposes of the paper are to define targeting as an aid in estimating matrices associated with large numbers of financial assets, analyze the similarities and dissimilarities between BEKK and DCC, both with and without targeting, on the basis of structural derivation, the analytical forms of the sufficient conditions for the existence of moments, and the sufficient conditions for consistency and asymptotic normality, and computational tractability for very large (that is, ultra high) numbers of financial assets, to present a consistent two step estimation method for the DCC model, and to determine whether BEKK or DCC should be preferred in practical applications.Conditional correlations, Conditional covariances, Diagonal models, Forecasting, Generalized models, Hadamard models, Scalar models, Targeting.
Do We Really Need Both BEKK and DCC? A Tale of Two Covariance Models
No full textLarge and very large portfolios of financial assets are routine for many individuals and organizations. The two most widely used models of conditional covariances and correlations are BEKK and DCC. BEKK suffers from the archetypal "curse of dimensionality" whereas DCC does not. This is a misleading interpretation of the suitability of the two models to be used in practice. The primary purposes of the paper are to define targeting as an aid in estimating matrices associated with large numbers of financial assets, analyze the similarities and dissimilarities between BEKK and DCC, both with and without targeting, on the basis of structural derivation, the analytical forms of the sufficient conditions for the existence of moments, and the sufficient conditions for consistency and asymptotic normality, and computational tractability for very large (that is, ultra high) numbers of financial assets, to present a consistent two step estimation method for the DCC model, and to determine whether BEKK or DCC should be preferred in practical applications.
Proposing a strict epidemiological methodology for setting empirical critical loads for nitrogen deposition
No full textCurrently empirical critical loads are derived from manipulation experiments and field survey data and more recently these data have come under scrutiny as our understanding of how ecosystems respond to reactive nitrogen (Nr) deposition evolves. The importance of background nitrogen (N) deposition and the significance of the starting N capital, cumulative N, are now recognized. This has led to a credibility rating against which experimental data can be evaluated. However, there is still no robust and transparent system in place for setting empirical critical loads for nitrogen deposition. This chapter discusses some of the issues involved in the evaluation of the available data and proposes a testable approach to carry the system forward
To the author of Infant baptism dated 1773 [electronic resource].
No full textAnonymous. By Mary Gillam.'Infant baptism, defended from Scripture, antiquity, and reason' is attributed to Edward Sheppard and was first printed in Bath in 1773.O copy with MS. note after "To the author of Infant baptism": "Mr. Shepherd at Bath Chappel"Electronic reproduction.English Short Title Catalog,Reproduction of original from Bodleian Library (Oxford)
Essays in financial econometrics
No full textThis dissertation consists of three chapters discussing issues in the field of financial econometrics. All three chapters are largely empirical, with some theoretical developments in second moments modelling in the second chapter.
The first chapter of this thesis analyses the market neutrality of Pairs Trading, a statistical arbitrage trading technique, from a second moments perspective. In this study, I analyse how market and idiosyncratic news affect the profitability of this trading strategy. I propose a conditional covariance framework based on Kroner and Ng (1998) extension of the BEKK Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model to analyse the dependence of second moments between different portfolios of pairs and the returns of the market. In contradiction to what is generally assumed about the market neutrality of this strategy, the results indicate the existence of significant spillovers from market news to different portfolios of pairs. In a second step of the study, I analyse the contribution of both idiosyncratic and market components to pairs volatility over time in an asynchronous panel of pairs. This analysis shows that the volatility of the pairs strategy has become more dependent on idiosyncratic rather than market shocks. In this sense, although Pairs Trading cannot be said to be market neutral from a second moments perspective if we look at the full sample from 1962 to 2018, the strategy has certainly become more market neutral as markets have evolved over the last two decades.
In the second chapter of this thesis, Susana Campos-Martins (Oxford) and I propose an econometric framework that explains the Purchasing Power Parity (PPP) Puzzle as common volatility shocks. Most of the discussion about the PPP Puzzle of Rogoff (1996) has pertained to the reversion speed of deviations from PPP. Much less attention, however, has been given to the other component of the puzzle: the high volatilities of real exchange rates. In this paper, we provide a framework that is capable of explaining the econometric sources of these volatilities. First, we study the drivers of real exchange rate volatilities using a Cross-Sectionally Augmented Autoregressive Distributed Lag (CS-ARDL) panel framework and the conditional covariance matrices of the system with nominal exchange rates and price differentials. This analysis indicates that, for both emerging and developed markets, common factors are the main drivers of volatility. With this result in hand, we propose a novel econometric framework that explains the sources of these volatilities as common second moment shocks. This model allows us to gives structure to the origins of these high volatilities and propose an extension to study their macrofinancial drivers.
The third and final chapter of this thesis is an adapted version of a current IMF working paper which introduces the IMF Soft Power Index. In this chapter, Serhan Cevik (IMF) and I introduce a new composite Global Soft Power Index (GSPI) composed of six dimensions for a broad sample of 72 countries across the world over the period 2007-2019. The proposed framework allows for comparisons not only at the “headline” level of the GSPI, but also at the level of the sub-indices, which allows us to identify and study how countries differ at a granular level of soft power. In a final step of the analysis, we present a possible macro-financial application to analyse the relationship between soft power and the volatility of Real Effective Exchange Rates (REER) across countries and over time. The results indicate that some dimensions of the GSPI play an important role in explaining real exchange rate volatility at almost all significance levels. Overall, our framework presents a systematic approach to measure soft power and its dimensions. By capturing the matrix of soft power characteristics, the GSPI offers significant advantages in comparative analysis of soft power across countries and over time
- …
