Jozef Barunik


About


Jozef Baruník is an Associate Professor at the Institute of Economic Studies, Charles University in Prague. He also serves as a head of the Econometrics department at the Czech Academy of Sciences. In his research, he develops mathematical models for understanding financial problems (such as measuring and managing financial risk), develops statistical methods and analyzes financial data. Especially, he is interested in asset pricing, high-frequency data, financial econometrics, machine learning, high-dimensional financial data sets (big data), and frequency domain econometrics (cyclical properties and behavior of economic variables).

Jozef’s work has appeared in the Review of Economics and Statistics, Econometrics Journal, Journal of Financial Econometrics, Journal of Financial Markets, Econometric Reviews, Journal of Economic Dynamics and Control, The Energy Journal, he is an Associate Editor of the Digital Finance, and Journal of Economic Interaction and Coordination and also referees frequently for several journals and grant agencies in the fields of econometrics, finance, and statistics.



Selected Publications


Asymmetric Network Connectedness of Fears (with M.Bevilacqua, and R.Tunaru)
The Review of Economics and Statistics (2020) forthcoming


Measurement of Common Risks in Tails: A Panel Quantile Regression Model for Financial Returns (with F.Cech)
Journal of Financial Markets (2020) forthcoming


Forecasting dynamic return distributions based on ordered binary choice (with S.Anatolyev)
International Journal of Forecasting (2019), 35(3), pp.823-835,
code and package


Quantile Coherency: A General Measure for Dependence between Cyclical Economic Variables (with T.Kley)
The Econometrics Journal (2019), 22(2), pp. 131-152,
code and package
Supplementary material available


Total, asymmetric and frequency connectedness between oil and forex markets (with E. Kocenda)
The Energy Journal (2019),forthcoming
codes for introduced measures
Note the package frequencyConnectedness available here can be used to replicate the paper
Supplementary material available


Measuring the Frequency Dynamics of Financial Connectedness and Systemic Risk (with T.Krehlik)
Journal of Financial Econometrics (2018), 16 (2), pp. 271–296,
code and package
Supplementary material available


Do co-jumps impact correlations in currency markets? (with L.Vacha)
Journal of Financial Markets (2018), 37, pp.97-119,
codes for introduced measures


Modeling and Forecasting Persistent Financial Durations (with F.Zikes and N.Shenai)
Econometric Reviews (2017), 36:10, 1081-1110,
Supplementary material available


Estimation of financial agent-based models with simulated maximum likelihood (with J.Kukacka)
Journal of Economic Dynamics and Control (2017), 85, pp. 21-45,


Asymmetric volatility connectedness on forex markets (with E. Kocenda and L.Vacha)
Journal of International Money and Finance (2017), 77C, pp. 39-56,
code for replication


Cyclical properties of supply-side and demand-side shocks in oil-based commodity markets (with T.Krehlik)
Energy Economics (2017), 65, pp.208-218,
code and package codes for bootstrap


Good volatility, bad volatility: Which drives the asymmetric connectedness of Australian electricity markets? (with N. Apergis and M.Lau)
Energy Economics (2017), 66, pp.108- 115,
codes for introduced measures
Note the package frequencyConnectedness available here can be used to replicate the paper


Asymmetric connectedness on the U.S. stock market: Bad and good volatility spillovers (with E. Kocenda and L.Vacha)
Journal of Financial Markets (2016), 27, 55–78,
codes for introduced measures
Note the package frequencyConnectedness available here can be used to replicate the paper


Semiparametric Conditional Quantile Models for Financial Returns and Realized Volatility (with F.Zikes)
Journal of Financial Econometrics (2016), 14 (1), 185–226,
Supplementary material available


Forecasting the term structure of crude oil futures prices with neural networks (with B.Malinska)
Applied Energy (2016), 164, pp.366–379,


Modeling and forecasting exchange rate volatility in time-frequency domain (with T.Krehlik and L.Vacha)
European Journal of Operational Research (2016), 251 (1), pp. 329–340,
codes to paper


Volatility spillovers across petroleum markets (with E. Kocenda and L.Vacha)
The Energy Journal (2015), 36(3), 309-329
codes for introduced measures
Note the package frequencyConnectedness available here can be used to replicate the paper


Are benefits from oil - stocks diversification gone? A new evidence from a dynamic copulas and high frequency data (with K.Avdulaj)
Energy Economics (2015), 51, pp. 31-44,


Realizing stock market crashes: stochastic cusp catastrophe model of returns under time-varying volatility (with J.Kukacka)
Quantitative Finance (2015), 15 (8), pp. 1347-1364,


Realized wavelet-based estimation of integrated variance and jumps in the presence of noise (with L.Vacha)
Quantitative Finance (2015), 15 (6), pp. 959-973,
codes for introduced measures


Are Bayesian Fan Charts Useful? The Effect of Zero Lower Bound and Evaluation of Financial Stability Stress Tests (with M.Franta, R.Horvath,K.Smidkova)
International Journal of Central Banking (2014), 10(1), 159-187


Comovement of energy commodities revisited: Evidence from wavelet coherence analysis (with L.Vacha)
Energy Economics (2012), 34(1), pp. 241–247,


Can a stochastic cusp catastrophe model explain stock market crashes? (with M.Vosvrda)
Journal of Economic Dynamics and Control (2012), 33(10), 1824-1836


Full list of publications available here


Working Papers


Deep Learning, Predictability, and Optimal Portfolio Returns (with M.Babiak)
preprint draft (Sept 2020) available

Abstract: We study optimal dynamic portfolio choice of a long-horizon investor who uses deep learning methods to predict equity returns when forming optimal portfolios. The results show statistically and economically significant out-of-sample portfolio benefits of deep learning as measured by high certainty equivalent returns and Sharpe ratios. Return predictability via deep learning generates substantially improved portfolio performance across different subsamples, particularly the recession periods. These gains are robust to including transaction costs, short-selling and borrowing constraints.


Dynamic Networks in Large Financial and Economic Systems (with M.Ellington)
submitted (2020)

Abstract: We propose new measures to characterize dynamic network connections in large financial and economic systems. In doing so, our measures allow one to describe and understand causal network structures that evolve throughout time and over horizons using variance decomposition matrices from time-varying parameter VAR (TVP VAR) models. These methods allow researchers and practitioners to examine network connections over any horizon of interest whilst also being applicable to a wide range of economic and financial data. Our empirical application redefines the meaning of big in big data, in the context of TVP VAR models, and track dynamic connections among illiquidity ratios of all S\&P500 constituents. We then study the information content of these measures for the market return and real economy.
code and package in Julia and Matlab


Dynamic Network Risk (with M.Ellington)
submitted (2020)

Abstract: This paper examines the pricing of short-term and long-term dynamic network risk in the cross-section of stock returns. Stocks with high sensitivities to dynamic network risk earn lower returns. We rationalize our finding with economic theory that allows the stochastic discount factor to load on network risk through the precautionary savings channel. A one-standard deviation increase in long-term (short-term) network risk loadings associate with a 7.66% (6.71%) drop in annualized expected returns.
code and package in Julia and Matlab


Sentiment-Driven Stochastic Volatility Model: A High-Frequency Textual Tool for Economists (with Cathy Yi-Hsuan Chen, and J.Vecer)
Submitted (2019)

Abstract: We propose how to quantify high-frequency market sentiment using high-frequency news from NASDAQ news platform and support vector machine classifiers. News arrive at markets randomly and the resulting news sentiment behaves like a stochastic process. To characterize the joint evolution of sentiment, price, and volatility, we introduce a unified continuous-time sentiment-driven stochastic volatility model. We provide closed-form formulas for moments of the volatility and news sentiment processes and study the news impact. Further, we implement a simulation-based method to calibrate the parameters. Empirically, we document that news sentiment raises the threshold of volatility reversion, sustaining high market volatility.


codes to paper


Quantile Spectral Beta: A Tale of Tail Risks, Investment Horizons, and Asset Prices (with M.Nevrla)
Submitted (2020)

Abstract: We examine how extreme market risks are priced in the cross-section of asset returns at various horizons. Based on the decomposition of covariance between indicator functions capturing fluctuations of different parts of return distributions over various frequencies, we define a quantile spectral beta representation that characterizes asset’s risk generally. Nesting the traditional frameworks, the new representation explains tail-specific as well as horizon-, or frequency-specific spectral risks. Further, we work with two notions of frequency-specific extreme market risks. First, we define tail market risk that captures dependence between extremely low market and asset returns. Second, extreme market volatility risk is characterized by dependence between extremely high increments of market volatility and extremely low asset return. Empirical findings based on the datasets with long enough history, 30 Fama-French Industry portfolios, and 25 Fama-French portfolios sorted on size and book-to-market support our intuition. We reach the same conclusion using stock-level data as well as daily data. These results suggest that both frequency-specific tail market risk and extreme volatility risk are priced and our final model provides significant improvement over specifications considered by previous literature.


Co-jumping of Treasury Yield Curve Rates (with P.Fiser)
Submitted (2019)

Abstract: We study the role of co-jumps in the interest rate futures markets. To disentangle continuous part of quadratic covariation from co-jumps, we localize the co-jumps precisely through wavelet coefficients and identify statistically significant ones. Using high frequency data about U.S. and European yield curves we quantify the effect of co-jumps on their correlation structure. Empirical findings reveal much stronger co-jumping behavior of the U.S. yield curves in comparison to the European one. Further, we connect co-jumping behavior to the monetary policy announcements, and study effect of 103 FOMC and 119 ECB announcements on the identified co-jumps during the period from January 2007 to December 2017.


Codes for introduced measures


Investment Disputes and Abnormal Volatility of Stocks (with Z.Drabek and M.Nevrla)
Submitted (2020)

Abstract: Dramatic growth of investment disputes between foreign investors and host states rises serious questions about the impact of those disputes on investors. This paper is the first to explain increased uncertainty of investors about the outcome of arbitration, which may or may not lead to compensation for damages claimed by the investor. We find robust evidence that investment disputes lead to abnormal share fluctuations of companies involved in disputes with host countries. Importantly, while a positive outcome for an investor decreases uncertainty back to original levels, we document strong increase in the volatility of companies with negative outcome for the investor. We find that several variables including size of the award, political instability, location of arbitration, country of origin of investor or public policy considerations in host country explain large portion of the investor’s uncertainty.


Work in Progress


Deep Reinforcement Learning for Dynamic Decision Making with Quantile Preferences (with L.Vacha)


Asset Pricing with Quantile Machine Learning (with A.Galvao and M.Hronec)


Dynamic density forecasting using machine learning (with L.Hanus)


Tales of sentiment driven tails (with W.Hardle and C.Chen) slides available


Horizon-specific risks, higher moments, and asset prices (with J.Kurka)


Students


Current (Full-Time) Doctoral Students

Josef Kurka: Horizon-specific risks, higher moments, and asset prices

Martin Hronec: Asset Pricing with Quantile Machine Learning

Matej Nevrla: Tail risks, asset prices, and investment horizons

Lubos Hanus (joint supervision with L.Vacha) Dynamic density forecasting using machine learning


Past Doctoral Students

Krenar Avdulaj: Essays in Financial Econometrics

Frantisek Cech: Three Essays on Risk Modelling and Empirical Asset Pricing

Tomas Krehlik: Applications of Modern Spectral Tools in Financial Econometrics

Jiri Kukacka: Estimation of Financial Agent-Based Models


Teaching

JEM005 - Advanced Econometrics (Masters)

The objective of the course is to help students understand several important modern techniques in econometrics and apply them in empirical research and practical applications. Emphasis of the course will be placed on understanding the essentials underlying the core techniques, and developing the ability to relate the methods to important issues faced by a practicioner.

By completing this course, students will be able to use a computer based statistical software to analyze the data, choose appropriate models and estimators for given economic application, understand and interpret the results in detail (diagnose problems, understand proper inference) and will be confident to carry out the analysis and conclusions with respect to appropriatness and limitation of the methodology used. Finally, students will have sufficient grounding in econometric theory to begin advanced work in the field.

web page of the course

JEM059 - Quantitative Finance I (Masters)

The objective of the course is to introduce advanced time series methods. Students will be able to use the modern financial econometric tools after passing this course and will be prepared to continue in the Quantitative Finance II course. Part of the course is also focused on the high frequency data econometrics.

web page of the course

JEM116 - Applied Econometrics (Masters)

The course concentrates on the practical use of econometric methods, reviewing the relevant methodology, its use, and the possible alternative modeling approaches. The lectures are supplemented by computer classes, where students can gain hands-on experience in applied econometric analysis. During the course we will especially focus on time series techniques applied to forecasting asset volatility, modeling inflation, exchange rate volatility and other topics that you may regularly encounter in economic and financial literature. The course focuses on following topics in econometrics: OLS, IV, ARIMA, GARCH, VAR, cointegration, non-linear model and limited dependent variable. The course is especially suited for students undertaking empirical exercise in writing their M.A. thesis.

web page of the course

JED412,413 - Nonlinear Dynamic Economic Systems: Theory and Applications (PhD seminar)

The aim of this seminar is an analysis of macroeconomic systems primarily by methods of nonlinear dynamics, stochastics dynamics, and nonlinear time series analysis. Special application will be focused on a behavior of the financial markets.

web page of the course


Contact


doc. PhDr. Jozef Baruník, Ph.D.

Associate Professor
Department of Macroeconomics and Econometrics
Institute of Economic Studies, Faculty of Social Sciences
Charles University
Opletalova 26
Prague 1, 110 00,Czech Republic

barunik [AT] fsv [DOT] cuni [DOT] cz
00 (420) 776 259273
http://ies.fsv.cuni.cz/en/staff/barunik


Head of the Department
Department of Econometrics
Institute of Information Theory and Automation
Academy of Sciences of the Czech Republic
Pod Vodarenskou Vezi 4
Prague 8, 182 08,Czech Republic

barunik [AT] utia [DOT] cas [DOT] cz
00 (420) 776 259273
https://www.utia.cas.cz/people/barunik