Thomas Walther

Utrecht University | UU · School of Economics (USE)

We expand the literature of volatility and Value-at-Risk forecasting of oil price returns by comparing the recently proposed Mixture Memory GARCH (MMGARCH) model to other discrete volatility models (GARCH, RiskMetrics, EGARCH, APARCH, FIGARCH, HYGARCH, and FIAPARCH). We incorporate an Expectation-Maximization algorithm for parameter estimation of t...

We transfer the recently introduced fast fractional differencing that utilizes fast Fourier transforms (FFT) to long memory variance models and show that this approach offers immense computation speedups. We demonstrate how calculation times of parameter estimations benefit from this new approach without changing the estimation procedure. A more pr...

This paper contributes to the large debate regarding the impact of oil price changes on U.S. GDP growth. Firstly, we replicate empirical findings of prominent studies and find that the proposed measures have a dissipating effect with recent data up to 2016Q4. Secondly, we re-examine this relationship and put particular focus on nonlinearity and a p...

This paper investigates the time-varying volatility patterns of some major commodities as well as the potential factors that drive their long-term volatility component. For this purpose, we make use of a recently proposed GARCH-MIDAS approach which typically allows us to examine the role of economic and financial variables of different frequencies....

We conduct a systematic literature review on environmental and climate related risk management in the financial sector. The systematic literature review identified a total of 36 relevant articles. A formal coding leads to the aggregation and classification of papers to three main categories that consider the impact of environmental concerns on fina...

We study potential drivers of the cross-section of commodity futures returns based on mixed-frequency vector autoregression. We find that slowing real economic activity and growing macroeconomic uncertainty precede negative monthly returns. Stock markets predict commodity returns at a daily frequency but not at longer-term horizons. We show that us...

In statistics, samples are drawn from a population in a data‐generating process (DGP). Standard errors measure the uncertainty in estimates of population parameters. In science, evidence is generated to test hypotheses in an evidence‐generating process (EGP). We claim that EGP variation across researchers adds uncertainty—nonstandard errors (NSEs)....

Extending the popular HAR model with additional information channels to forecast realized volatility of WTI futures prices, we show that machine learning‐generated forecasts provide better forecasting quality and that portfolios that are constructed with these forecasts outperform their competing models resulting in economic gains. Analyzing the se...

We examine the impact of climate risks on the nexus of clean energy and technology stocks using a time-varying correlation model. We find that physical and transition climate risks are positively associated with the long-term correlation between clean energy and technology stock indices, whereas the effect of transition risk is more robust to diffe...

We examine the impact of climate risks on the nexus of clean energy and technology stocks using a time-varying correlation model. We find that physical and transition climate risks are positively associated with the long-term correlation between clean energy and technology stock indices, whereas the effect of transition risk is more robust to diffe...

We investigate the time-varying dynamics of the precious metal markets. We employ a mixed data sampling technique to identify the impact of macroeconomic and financial drivers from G7 and BRICS countries on the daily volatility and pairwise correlation of gold, silver, platinum, and palladium. We find that the U.S. and Chinese economies especially...

We assess the value of stranded coal-fired power plants in Germany in the light of the critical decision to phase them out by 2038. In a Monte Carlo simulation, the scenarios under consideration (slow decommissioning at the end of the technical lifetime in 2061, the highly probable phase-out by 2038, and an accelerated phase-out by 2030) are additi...

We re-examine the conditional volatility and dynamic correlation of precious metals and equity markets of developed countries by employing mixed data sampling. We find that Gold and Silver serve as short-term safe-haven with decreasing correlation towards zero during equity market recessions. A similar behaviour, albeit not as pronounced, is found...

This paper proposes a new metric to gauge investor sentiment using a relative valuation method. We combine investor behavioral finance traits and option-implied standard deviations under both the real-world probability (P) valued most in the view of uninformed investors and the risk-neutral space (Q) adopted when there exists no cognitive error. Gi...

Using a hand-collected dataset containing bullish, neutral, and bearish predictions for Bitcoin published by crypto experts, we show that neutral and bearish predictions are followed by negative abnormal returns whereas bullish predictions are not associated with nonzero abnormal returns. Based on all outstanding predictions, we compute prediction...

In statistics, samples are drawn from a population in a data-generating process (DGP). Standard errors measure the uncertainty in sample estimates of population parameters. In science, evidence is generated to test hypotheses in an evidence-generating process (EGP). We claim that EGP variation across researchers adds uncertainty: non-standard error...

In statistics, samples are drawn from a population in a data-generating process (DGP). Standard errors measure the uncertainty in sample estimates of population parameters. In science, evidence is generated to test hypotheses in an evidence-generating process (EGP). We claim that EGP variation across researchers adds uncertainty: non-standard error...

In this study, we analyze illiquidity premia and their effect on the expected returns of German real estate securities. To this end, we use a unique data set that includes real estate stocks, real estate investment trusts (REITs), and open- and closed-end real estate funds for 2003 to 2017. We follow Amihud‘s (2002) structural approach; specificall...

This study investigates the structural relationship between illiquidity and excess returns in the German stock market over time. The idea of illiquidity’s impact on asset prices has been challenged in more recent research and we provide further insight into the comprehensive picture of it. We show that illiquidity is still a significant factor when...

Die Volatilität ist als universelles Risikomaß von hoher Bedeutung für die Finanzmärkte. Sie spielt eine zentrale Rolle im Risiko- und Portfoliomanagement sowie bei der Bewertung von Finanzderivaten. Intratagesdaten ermöglichen eine genauere Schätzung der Volatilität. Dieser Artikel führt in das Konzept und die Modellierung Realisierter Volatilität...

We conduct a systematic literature review on environmental and climate-related risk management in the financial sector. We classify the current literature into three categories: (i) the impact of environmental concerns on financial risk; (ii) the current state of environmental risk practices in the financial sector; and (iii) measures to assess the...

We propose a stochastic spanning approach to assess whether a traditional portfolio of stocks and bonds spans augmented portfolios including commodities, foreign exchange, and real estate. We empirically show that in all seven portfolio combinations, the augmented portfolio is not spanned by the traditional one. Our results are further confirmed by...

Using a hand-collected dataset containing bullish, neutral, and bearish predictions for Bitcoin published by crypto experts, we show that neutral and bearish predictions are followed by negative abnormal returns whereas bullish predictions are not associated with nonzero abnormal returns. Based on all outstanding predictions, we compute prediction...

We analyse whether increased risk reporting by European energy utilities is positively or negatively related to firm value. Using an unsupervised machine learning topic model 'Latent Dirichlet Allocation', we classify the content of the risk reports presented in the notes to the financial statements in different risk topics over the period from 200...

We augment the HAR model with additional information channels to forecast realized volatility of WTI futures prices. These channels include stock markets, sentiment indices, commodity and FX markets, and text-based Google indices. We then apply four differing machine learning techniques to identify the most suitable endo-and exogenous factors which...

After the Paris Climate Conference (Conference of the Paris or COP: 21), the majority of countries and sovereigns agreed to tackle the global climate changes. From finance perspectives, green and sustainable finance play an essential role to reduce the carbon emission, which develops resilient climate infrastructure and environmental sustainability...

In this study, we analyze illiquidity premia and their effect on the expected returns of German real estate securities. To this end, we use a unique data set that includes real estate stocks, real estate investment trusts (REITs), and open- and closed-end real estate funds for 2003 to 2017. We follow Amihud‘s (2002) structural approach; specificall...

This paper presents a thorough replication of Hamilton (2003) which in turn replicates and extends the findings of four seminal papers regarding the oil price-GDP growth relationship. Firstly, we replicate the empirical results obtained with the oil price measures of by using an identical data set of real and nominal oil prices. Secondly, we extend...

We forecast the realized and median realized volatility of agricultural commodities using variants of the heterogeneous autoregressive (HAR) model. We obtain tick-by-tick data on five widely-traded agricultural commodities (corn, rough rice, soybeans, sugar, and wheat) from the CME/ICE. Real out-of-sample forecasts are produced for between 1 and 66...

This paper investigates the time-varying volatility patterns of some major commodities as well as the potential factors that drive their long-term volatility component. For this purpose, we make use of a recently proposed GARCH-MIDAS approach which typically allows us to examine the role of economic and financial variables of different frequencies....

We apply the GARCH-MIDAS framework to forecast the daily, weekly, and monthly volatility of five highly capitalized Cryptocurrencies (Bitcoin, Etherium, Litecoin, Ripple, and Stellar) as well as the Cryptocurrency index CRIX. Based on the prediction quality, we determine the most important exogenous drivers of volatility in Cryptocurrency markets....

We apply the GARCH-MIDAS framework to forecast the daily, weekly, and monthly volatility of five highly capitalized Cryptocurrencies (Bitcoin, Etherium, Litecoin, Ripple, and Stellar) as well as the Cryptocurrency index CRIX. Based on the prediction quality, we determine the most important exogenous drivers of volatility in Cryptocurrency markets....

In Folge der Finanzkrise von 2008 wurde die Copula für die “Zerstörung” der Wall Street verantwortlich gemacht. Die Copula erlaubt es auf einfache Weise die Abhängigkeitsstrukturen von Finanzinstrumenten zu beschreiben. Allerdings kann der unbedachte Gebrauch kostspielige Folgen bei Eintritt von Extremsituationen haben. Dieser Artikel führt in die...

Cryptocurrencies such as Bitcoin are establishing themselves as an investment asset and are often named the New Gold. This study, however, shows that the two assets could barely be more different. Firstly, we analyze and compare conditional variance properties of Bitcoin and Gold as well as other assets and find differences in their structure. Seco...

This presentation is for the paper titled:" Oil Price Changes and U.S. Real GDP Growth: Is this Time Different?".

This study compares the performance of several methods to calculate the Value-at-Risk of the six main ASEAN stock markets. We use filtered historical simulations, GARCH models, and stochastic volatility models. The out-of-sample performance is analyzed by various backtesting procedures. We find that simpler models fail to produce sufficient VaR for...

Cryptocurrencies such as Bitcoin are establishing themselves as an investment asset and are often named the New Gold. This study, however, shows that the two assets could barely be more different. Firstly, we analyze and compare conditional variance properties of Bitcoin and Gold as well as other assets and find differences in their structure. Seco...

This article analyses the profitability of a wind power plant in combination with a hydrogen storage. We distinguish between off- and on-shore locations with a 50 MW unit. The hydrogen of the storage unit can be used to either be re-electrified or directly marketed. The study analyses the profitability of a combination of lower-plant and hydrogen...

Purpose This study aims to analyse the conditional volatility of the Vietnam Index (Ho Chi Minh City) and the Hanoi Exchange Index (Hanoi) with a specific focus on their application to risk management tools such as Expected Shortfall (ES). Design/methodology/approach First, the author tests both indices for long memory in their returns and squared...

We examine the Croatian Kuna, the Czech Koruna, the Hungarian Forint, the Polish Zloty, the Romanian Leu, and the Swedish Krona whether their Euro exchange rates volatility exhibits true or spurious long memory. Recent research reveals long memory in foreign exchange rate volatility and we confirm this finding for these currency pairs by examining...

Bei der Parameterschätzung von empirischen Renditezeitreihen existiert oftmals das Problem, dass die Schätzung verzerrt ist. Grund dieser Verzerrung sind Strukturbrüche, welche dazu führen, dass die geschätzten Parameter für einige Zeitabschnitte zu hoch und für andere zu niedrig ausfallen. Die Markov-Regime- Switching-Modelle bieten die Möglichkei...

In econometrics, long memory models for variance modeling like FIGARCH or FIAPARCH are characterized by a Fractional Differencing term. In order to estimate and apply these models, the infinite MacLaurin expansion of the differencing term has to be truncated at a certain level. We transfer the recently introduced fast fractional differencing that u...

This paper investigates the performance of various conditional volatility models to forecast the second moment of tanker freight rates. Justified by existing theoretical and empirical evidence, we focus on asymmetric Markov regime-switching models to study the major global routes for long-haul trade of crude oil during the sample period from June 2...

This paper focuses on capturing the conditional volatility in the foreign exchange Value-at-Risk forecasts. By implementing a variety of GARCH models under different return distributions, we model the volatility of daily returns of EUR/PLN exchange rates. Statis-tically significant long memory and asymmetry effects in volatility are observed. These...

The EUR/PLN exchange rate is of great importance to Polish exporting industries as well as to investors in the Polish region. As a consequence, there is a particular interest in managing foreign exchange (FX) risks due to short and long FX exposures. By implementing a variety of GARCH models under different return distributions, we forecast the exc...

This paper discusses how contingent convertible bonds (CCB) influence the risk-taking behaviour of managers. A methodology to measure the impact is presented. The results show that the decision of issuing CCB to finance company assets sets incentives to managers to increase risk, if it is not adjusted to the compensation system. However, if the rem...

Die Schätzung von Risikomaßen von Finanzinvestitionen wie etwa des Value-at-Risk oder des Expected Shortfall erfordert Annahmen über die Volatilität der zugrunde liegenden Renditen. Die Annahmen konstanter Volatilität oder Normalverteilung der Renditen stehen oftmals in deutlichem Gegensatz zur Realität. Der vorliegende Artikel geht auf die Möglich...

Banken sind ein wichtiger Teil des Wirtschaftssystems. Ihre Funktion ist essentiell für die Wirtschaft eines Landes, da sie das nötige Kapital für die Unternehmen stellen und die Sparer bei ihnen ihr Geld verzinslich anlegen können, um für spätere Ausgaben zu sparen. Auch andere Unternehmen sind wichtig für das Wirtschaftssystem, so z. B. die Branc...