Spillovers in the environmental, social and governance (ESG) markets are crucial for evaluating contagion risks and sustainable investments. This study aims to examine risk spillovers in China’s ESG stock market and explores their impact mechanisms.
Previous research mainly employed the Diebold and Yilmaz (DY) (2012) connectedness model to construct connectedness networks and measure spillovers. However, this approach only captures linear relationships and faces the “curse of dimensionality”. To overcome these limitations, we propose a hybrid framework that integrates the random forest with DY. Additionally, the time-varying parameter vector autoregressive model with stochastic volatility model is applied to investigate the underlying impact mechanisms.
First, China's ESG stock market shows notable risk spillovers across firms, industries and regions. Second, systemically important entities include financial institutions, large-scale infrastructure, and leading liquor firms; the industrial, finance, information technology and optional consumption industries and the Eastern and Southern coastal regions. They play a key role in the network and are primary spillover sources. Third, macroeconomic information, geopolitical risks and climate policy uncertainty significantly influence spillovers, with stronger short-term effects.
First, we propose a hybrid framework that excels at measuring high-dimensional and nonlinear spillovers. Second, we expand the body of ESG research in emerging markets. Third, we explore spillover mechanisms, unveiling how key factors affect risk spillovers in the ESG stock market.
