We utilize a Generalized Autoregressive Conditional Heteroskedasticity-Mixed Data Sampling (GARCH-MIDAS) framework to show that monthly indicators of global and United States supply concerns, along with their regional- and product-specific components, constructed from 200 million shipment-level transactions, increase daily West Texas Intermediate (WTI) oil returns volatility over the period from January 2013 through August 2024. Furthermore, the in-sample predictability of oil returns volatility translates into statistically significant and robust short-, medium-, and long-term forecasting gains derived from the information content of the various supply disruption indexes, relative to a benchmark model of GARCH-MIDAS-realized volatility (RV), over the out-of-sample period of January 2020 and beyond. The comprehensive supply disruption indexes are also shown to outperform other widely used monthly measures of global supply constraints and economic conditions when incorporated into the GARCH-MIDAS framework. Our results carry important implications for investors and policymakers.
This study examines how recent market returns are followed by subsequent trading activity in the Mongolian stock market and which dimensions of trading account for the aggregate response. Using daily TOP-20 data from 26 January 2016 to 31 December 2025, we construct regular-market trading measures with block trades excluded, including traded value, transaction frequency, trading breadth, trading intensity, and concentration. Local projections provide the primary dynamic evidence under a conservative specification that conditions on the contemporaneous outcome. Vector autoregression-based Granger tests provide complementary evidence on predictive direction, while feedforward-neural-network and state-dependent models are used as nonlinear and heterogeneity diagnostics. Robustness checks include alternative activity transformations, lag structures, volatility-standardized shocks, and lagged market-cap-weighted cross-sectional return dispersion. A one-percentage-point market-return increase is followed by approximately 3.6–4.0
We select a sample of non-financial listed Indian firms to analyse the effect of competition on innovation and on firms’ corporate finance decisions. Using firm-level data for 3,716 companies from 1998 to 2006 sourced from the CMIE Prowess database, we exploit the Competition Act (2002) in India as an exogenous policy shock and apply a difference-in-differences (DiD) framework to estimate its causal effects. The findings show that treated firms innovated between 0.19
This study examines the paradoxical role of financial technology (FinTech) in BRICS economies, where rapid digital financial innovation simultaneously supports economic and industrial growth while increasing pressure on natural resources. Using panel data from BRICS countries (Brazil, Russia, India, China and South Africa) for the period 2006–2020, the study investigates the long-run relationships among FinTech, green growth, natural resource rents, and industrial value-added. A FinTech index is constructed via principal component analysis using five indicators capturing the multidimensional nature of digital finance. The Panel Fourier Cointegration test, which accounts for smooth transition structural breaks and cross-sectional dependence, is employed to examine long-run relationships, while the Augmented Mean Group (AMG) estimator is used for coefficient estimation. To ensure robustness, findings are further validated using the one-step System GMM and the Common Correlated Effects Mean Group (CCEMG) estimators. The results consistently show that FinTech positively affects green growth and industrial value-added, while it also intensifies natural resource exploitation. Country-specific analyses uncover substantial heterogeneity across BRICS members, reflecting differences in institutional quality, energy dependence, and maturity digital finance. Causality tests further confirm that FinTech acts as a catalyst for green growth, natural resource rents, and industrial value-added. These findings suggest that while FinTech holds real potential as a driver of industrial efficiency and low-carbon transition, its environmental costs must be actively managed through green FinTech regulation, resource traceability policies, and coordinated governance frameworks across BRICS economies.
This paper considers a particular class of Markov models where we assume that the error term is dependent on the first lagged state variable. We show that the process is equivalent to a stochastic autoregressive coefficient model depending on the first lagged value of the process itself and we call such a model state-dependent first-order autoregressive process, (SDAR). We introduce some assumptions under which this class of models is strictly stationary and geometrically ergodic and we show that the quasi-maximum likelihood estimator of the parameters is consistent and asymptotically normal. Some particular specifications of the model are analyzed and applied to model nonlinear time series provided by the weekly realized volatility extracted from the returns of the FTSE100 index in two different periods containing a strong financial turbulence: the Great Recession of 2008 and the Covid-19 pandemic of 2020. The comparison of forecasting accuracy is made considering two alternative approaches widely used in literature: two-regime SETAR models and HAR models. Results show that SDAR models offer a predictive capability in line in line with competing models in both periods.
