Szabolcs Blazsek
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Szabolcs Blazsek has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
Adrian Licht
School of Business , Universidad Francisco Marroquín , Guatemala City , 01010 , Guatemala
14 shared publicationsAstrid Ayala
School of Business , Universidad Francisco Marroquín , Guatemala City , Guatemala
9 shared publications- Alvaro Escribano
Department of Economics , Universidad Carlos III de Madrid , Getafe 28903 , Spain
4 shared publications Astrid Loretta Ayala
Mercer University
4 shared publicationsSamantha R. Shadoff
3 shared publicationsAlvaro Escribano
Department of Economics , Universidad Carlos III de Madrid , Getafe , 28903 , Spain
2 shared publications
Latest Publications
- Open Access
- 10 June 2026
- Published by Springer Nature in Environmental Modeling & Assessment
- Vol. 31 (6) , 1791-1814
Persistence in Sustainable Development in OECD Countries: An International Assessment for the Load Capacity Factor
This paper aims to investigate the persistence of the load capacity factor (LCF), a comprehensive indicator of sustainable development, defined as biocapacity (BC) divided by ecological footprint (EF). Our contribution is methodological. We use long-memory processes for LCF as an alternative to combining short-memory or unit root processes with structural breaks, as in the literature. We use data for 31 OECD (Organization for Economic Cooperation and Development) countries from 1961 to 2024. We investigate the nature of sustainable development shocks associated with the LCF. A persistent LCF suggests that shocks may have long-run effects, potentially influencing the time horizon considered in environmental and sustainable development policy decisions. We empirically motivate long memory in LCF time series by testing against a short-memory process with structural breaks. We use several semiparametric estimators of the degree of fractional integration parameter from the literature. These involve alternative specifications of the (i) local Whittle estimator, (ii) exact local Whittle estimator, and (iii) two-step exact local Whittle estimator. Our results suggest predominant evidence of long memory in load capacity time series for most OECD countries. We discuss these results in terms of country-specific characteristics and environmental policies. One implication is that long-term initiatives concerning BC and EF are needed to pursue sustainable development in OECD countries.
- 10 June 2026
- Published by Springer Nature in Environmental Modeling & Assessment
- Vol. 31 (6) , 1791-1814
Open AccessPersistence in Sustainable Development in OECD Countries: An International Assessment for the Load Capacity Factor
This paper aims to investigate the persistence of the load capacity factor (LCF), a comprehensive indicator of sustainable development, defined as biocapacity (BC) divided by ecological footprint (EF). Our contribution is methodological. We use long-memory processes for LCF as an alternative to combining short-memory or unit root processes with structural breaks, as in the literature. We use data for 31 OECD (Organization for Economic Cooperation and Development) countries from 1961 to 2024. We investigate the nature of sustainable development shocks associated with the LCF. A persistent LCF suggests that shocks may have long-run effects, potentially influencing the time horizon considered in environmental and sustainable development policy decisions. We empirically motivate long memory in LCF time series by testing against a short-memory process with structural breaks. We use several semiparametric estimators of the degree of fractional integration parameter from the literature. These involve alternative specifications of the (i) local Whittle estimator, (ii) exact local Whittle estimator, and (iii) two-step exact local Whittle estimator. Our results suggest predominant evidence of long memory in load capacity time series for most OECD countries. We discuss these results in terms of country-specific characteristics and environmental policies. One implication is that long-term initiatives concerning BC and EF are needed to pursue sustainable development in OECD countries.
- Open Access
- 17 March 2026
- Published by Elsevier in SSRN Electronic Journal
Score-driven Degrees of Fractional Integration of Mean Return and Volatility with an Application
We introduce an econometric model in which the conditional mean and variance have long memory with dynamic degrees of fractional integration. The model is named the `score-driven fractionally integrated quasi-autoregressive (QAR) and fractionally integrated Beta-t-EGARCH (exponential generalized autoregressive conditional heteroscedasticity) model with Student's t innovations’, FI(d_mu,t)-t-QAR-FI(d_lambda,t)-Beta-$-EGARCH. In this model, (i) the mean return (mu_t), (ii) the degree of fractional integration of mean return (d_mu,t), (iii) the log scale of return (lambda_t), and (iv) the degree of fractional integration of the log scale of return (d_lambda,t) are four score-driven filters. We compare the in-sample and out-of-sample performances of FI(d_mu,t)-t-QAR-FI(d_lambda,t)-Beta-t-EGARCH with several score-driven models (e.g. Beta-t-EGARCH), t-GARCH, and ARMA-t-GARCH (AR moving average, ARMA). We use daily data of the NIFTY-50 and SENSEX indices from the Indian stock market. The in-sample period is from July 3, 1990, to April 24, 2025. The out-of-sample volatility forecasting period is the COVID-19 (coronavirus disease of 2019) pandemic from March 2, 2020, to May 31, 2023. We find that FI(d_mu,t)-$t$-QAR-FI (d_lambda,t)-Beta-t-EGARCH improves in-sample and out-of-sample performance relative to other models, indicating for investors that it is an efficient alternative to benchmark classical and score-driven I(0) models of mean return and volatility.
- 17 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessScore-driven Degrees of Fractional Integration of Mean Return and Volatility with an Application
We introduce an econometric model in which the conditional mean and variance have long memory with dynamic degrees of fractional integration. The model is named the `score-driven fractionally integrated quasi-autoregressive (QAR) and fractionally integrated Beta-t-EGARCH (exponential generalized autoregressive conditional heteroscedasticity) model with Student's t innovations’, FI(d_mu,t)-t-QAR-FI(d_lambda,t)-Beta-$-EGARCH. In this model, (i) the mean return (mu_t), (ii) the degree of fractional integration of mean return (d_mu,t), (iii) the log scale of return (lambda_t), and (iv) the degree of fractional integration of the log scale of return (d_lambda,t) are four score-driven filters. We compare the in-sample and out-of-sample performances of FI(d_mu,t)-t-QAR-FI(d_lambda,t)-Beta-t-EGARCH with several score-driven models (e.g. Beta-t-EGARCH), t-GARCH, and ARMA-t-GARCH (AR moving average, ARMA). We use daily data of the NIFTY-50 and SENSEX indices from the Indian stock market. The in-sample period is from July 3, 1990, to April 24, 2025. The out-of-sample volatility forecasting period is the COVID-19 (coronavirus disease of 2019) pandemic from March 2, 2020, to May 31, 2023. We find that FI(d_mu,t)-$t$-QAR-FI (d_lambda,t)-Beta-t-EGARCH improves in-sample and out-of-sample performance relative to other models, indicating for investors that it is an efficient alternative to benchmark classical and score-driven I(0) models of mean return and volatility.
- Open Access
- 19 February 2026
- Published by Elsevier in Energy Economics
- Vol. 156
Score-driven global climate zones from 1940 to 2024: A new objective climate classification method
- 19 February 2026
- Published by Elsevier in Energy Economics
- Vol. 156
Open AccessScore-driven global climate zones from 1940 to 2024: A new objective climate classification method
- Open Access
- 6 February 2026
- Published by Elsevier in SSRN Electronic Journal
Score-Driven Long Memory Dynamics of Worldwide Regional Temperature Anomalies
We develop a score-driven fractionally integrated quasi-autoregressive model with Student's t innovations (t-FI-QAR), in which the degree of fractional integration d t , the conditional mean, and the conditional scale evolve via likelihood-based updates. Using monthly U.S. National Oceanic and Atmospheric Administration (NOAA) land-and-ocean temperature anomalies for six regions (Arctic, Antarctic, Atlantic Ocean, Northeast Pacific Ocean, Northern and Southern Hemispheres) from January 1850 to October 2025, we show that d t rises over time across all regions, implying increasingly persistent temperature dynamics. The increase is strongest in the Arctic and Northern Hemisphere, where we detect a structural shift over the past three decades consistent with a move toward non-stationary behavior. Significant but more moderate increases occur in the Atlantic, Northeast Pacific, and Southern Hemisphere, while the Antarctic exhibits a slight upward trend. Models that allow heavy tails and time-varying scale outperform homoscedastic specifications in likelihood-based criteria and diagnostics. The findings indicate that climate shocks now propagate more durably than in earlier periods, suggesting that stronger and more sustained mitigation and adaptation policies are needed to counter long-lived deviations in regional temperatures.
- 6 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessScore-Driven Long Memory Dynamics of Worldwide Regional Temperature Anomalies
We develop a score-driven fractionally integrated quasi-autoregressive model with Student's t innovations (t-FI-QAR), in which the degree of fractional integration d t , the conditional mean, and the conditional scale evolve via likelihood-based updates. Using monthly U.S. National Oceanic and Atmospheric Administration (NOAA) land-and-ocean temperature anomalies for six regions (Arctic, Antarctic, Atlantic Ocean, Northeast Pacific Ocean, Northern and Southern Hemispheres) from January 1850 to October 2025, we show that d t rises over time across all regions, implying increasingly persistent temperature dynamics. The increase is strongest in the Arctic and Northern Hemisphere, where we detect a structural shift over the past three decades consistent with a move toward non-stationary behavior. Significant but more moderate increases occur in the Atlantic, Northeast Pacific, and Southern Hemisphere, while the Antarctic exhibits a slight upward trend. Models that allow heavy tails and time-varying scale outperform homoscedastic specifications in likelihood-based criteria and diagnostics. The findings indicate that climate shocks now propagate more durably than in earlier periods, suggesting that stronger and more sustained mitigation and adaptation policies are needed to counter long-lived deviations in regional temperatures.
- Open Access
- 2 December 2025
- Published by Walter de Gruyter GmbH in Studies in Nonlinear Dynamics & Econometrics
- Vol. 30 (4) , 561-593
Fractionally Integrated Multivariate Score-Driven Location Models with an Application to Climate Data
We introduce the quasi-vector autoregressive fractionally integrated (QVAR-FI) model to the literature on score-driven models. We apply QVAR-FI to climate data on global sea ice volume, carbon dioxide (CO 2 ) concentration in Earth’s atmosphere, and land surface temperature in Antarctica for the period of 798,000 to 1,000 years ago. In the QVAR-FI model, known as the fractionally integrated score-driven ice-age model, we control for the Milankovitch cycles (i.e. eccentricity and obliquity of Earth’s orbit and precession of the equinoxes) as exogenous explanatory variables. We consider alternative VAR, QVAR, and QVAR-FI models, using different specifications of the exogenous orbital explanatory variables and deterministic and stochastic seasonality components. We estimate the QVAR-FI model and its alternatives using the maximum likelihood (ML) method. Model diagnostics support the QVAR-FI specifications. We estimate the impulse response functions (IRFs) for QVAR-FI and compare them with those of the VAR and QVAR filters for the conditional mean. The in-sample statistical and out-of-sample multi-step-ahead forecasting performances of QVAR-FI improve those of the VAR and QVAR models.
- 2 December 2025
- Published by Walter de Gruyter GmbH in Studies in Nonlinear Dynamics & Econometrics
- Vol. 30 (4) , 561-593
Open AccessFractionally Integrated Multivariate Score-Driven Location Models with an Application to Climate Data
We introduce the quasi-vector autoregressive fractionally integrated (QVAR-FI) model to the literature on score-driven models. We apply QVAR-FI to climate data on global sea ice volume, carbon dioxide (CO 2 ) concentration in Earth’s atmosphere, and land surface temperature in Antarctica for the period of 798,000 to 1,000 years ago. In the QVAR-FI model, known as the fractionally integrated score-driven ice-age model, we control for the Milankovitch cycles (i.e. eccentricity and obliquity of Earth’s orbit and precession of the equinoxes) as exogenous explanatory variables. We consider alternative VAR, QVAR, and QVAR-FI models, using different specifications of the exogenous orbital explanatory variables and deterministic and stochastic seasonality components. We estimate the QVAR-FI model and its alternatives using the maximum likelihood (ML) method. Model diagnostics support the QVAR-FI specifications. We estimate the impulse response functions (IRFs) for QVAR-FI and compare them with those of the VAR and QVAR filters for the conditional mean. The in-sample statistical and out-of-sample multi-step-ahead forecasting performances of QVAR-FI improve those of the VAR and QVAR models.
- Open Access
- 26 September 2025
- Published by Walter de Gruyter GmbH in Studies in Nonlinear Dynamics & Econometrics
- Vol. 30 (4) , 699-722
Systematic Risk in Publicly Listed Private Equity: An Empirical Study Using Score-Driven Beta Models
We investigate systematic risk dynamics using the LPX Group’s 10 indices, which represent publicly listed private equity (PLPE) market indices as well as different PLPE investment styles and PLPE performance at alternative geographic regions. PLPE is a hybrid asset class that combines private capital exposure with public market liquidity. Using daily data from 2002 to 2025 and a recent score-driven modeling framework, i.e. the autoregressive conditional beta (ACB) model for the t -distribution ( t -ACB), we demonstrate that the betas and volatility are highly time-varying and LPX-specific, particularly during periods of macroeconomic or financial crisis. Contrary to classical theory, LPX betas do not converge in crises, revealing persistent heterogeneity across PLPE firms. These findings challenge the assumptions underlying static asset pricing models and conventional methods for estimating the cost of equity. By capturing how systematic risk evolves across indices and regimes, this paper extends the literature by offering a more accurate framework for valuing hybrid assets and managing risk in an increasingly institutionalized segment of the private equity market.
- 26 September 2025
- Published by Walter de Gruyter GmbH in Studies in Nonlinear Dynamics & Econometrics
- Vol. 30 (4) , 699-722
Open AccessSystematic Risk in Publicly Listed Private Equity: An Empirical Study Using Score-Driven Beta Models
We investigate systematic risk dynamics using the LPX Group’s 10 indices, which represent publicly listed private equity (PLPE) market indices as well as different PLPE investment styles and PLPE performance at alternative geographic regions. PLPE is a hybrid asset class that combines private capital exposure with public market liquidity. Using daily data from 2002 to 2025 and a recent score-driven modeling framework, i.e. the autoregressive conditional beta (ACB) model for the t -distribution ( t -ACB), we demonstrate that the betas and volatility are highly time-varying and LPX-specific, particularly during periods of macroeconomic or financial crisis. Contrary to classical theory, LPX betas do not converge in crises, revealing persistent heterogeneity across PLPE firms. These findings challenge the assumptions underlying static asset pricing models and conventional methods for estimating the cost of equity. By capturing how systematic risk evolves across indices and regimes, this paper extends the literature by offering a more accurate framework for valuing hybrid assets and managing risk in an increasingly institutionalized segment of the private equity market.
- 9 March 2025
- Published by Taylor & Francis in Applied Economics
- Vol. 58 (12) , 2364-2382
Score-driven expected return and volatility spillovers between the Indian and United States stock markets
- 9 March 2025
- Published by Taylor & Francis in Applied Economics
- Vol. 58 (12) , 2364-2382
Score-driven expected return and volatility spillovers between the Indian and United States stock markets
- 4 March 2025
- Published by Taylor & Francis in Applied Economics
- Vol. 58 (8) , 1449-1467
Score-driven credit risk clustering in Guatemala: an extension for unbalanced panels
- 4 March 2025
- Published by Taylor & Francis in Applied Economics
- Vol. 58 (8) , 1449-1467
Score-driven credit risk clustering in Guatemala: an extension for unbalanced panels
- 3 March 2025
- Published by Taylor & Francis in Applied Economics
- Vol. 58 (6) , 1194-1208
Exogenous, endogenous, and observable switching models of industrial production in the United Kingdom
- 3 March 2025
- Published by Taylor & Francis in Applied Economics
- Vol. 58 (6) , 1194-1208
Exogenous, endogenous, and observable switching models of industrial production in the United Kingdom
- 16 February 2025
- Published by Taylor & Francis in Applied Economics
- Vol. 58 (2) , 293-313
New score-driven scale and shape interactions: an application to international stock indices
- 16 February 2025
- Published by Taylor & Francis in Applied Economics
- Vol. 58 (2) , 293-313
New score-driven scale and shape interactions: an application to international stock indices