AI 中文总结
研究台湾相关ETF在重尾与非对称波动下的投资组合优化，用尾部风险诊断等方法分析，发现半导体聚焦ETF风险值大，CVaR优化配置更集中，投资组合排名因绩效衡量标准而异，表明单方差框架难完整刻画风险。
AI 中文摘要
台湾在全球半导体制造中的核心地位，使台湾相关交易所交易基金（ETF）面临技术集中、地缘政治不确定性和供应链中断，导致回报分布具有重尾、波动聚集以及对负面冲击的非对称反应。本文从2015年2月至2025年2月，使用尾部风险诊断、非对称波动建模以及均值 - 方差和条件风险价值（CVaR）标准下的投资组合优化，分析了30只美国上市的台湾相关ETF。希尔尾部指数估计表明整个ETF领域存在重尾行为。半导体聚焦的ETF产生的风险价值（VaR）和条件风险价值（CVaR）估计值比多元化基准大得多。GJR - GARCH估计揭示了持续的非对称波动。CVaR优化产生的配置比重均值 - 方差优化更集中。投资组合排名取决于绩效衡量标准。结果表明，仅基于方差的框架对技术集中投资环境中的风险描述不完整，基于方差和尾部敏感的绩效衡量标准在同一时期可能青睐不同投资组合。
英文摘要
Taiwan's central role in global semiconductor manufacturing exposes Taiwan-related ETFs to technology concentration, geopolitical uncertainty, and supply-chain disruptions, resulting in return distributions characterized by heavy tails, volatility clustering, and asymmetric responses to negative shocks. This paper analyzes thirty U.S.-listed ETFs with Taiwan exposure from February 2015 to February 2025 using tail-risk diagnostics, asymmetric volatility modeling, and portfolio optimization under mean--variance and conditional value-at-risk (CVaR) criteria. Hill tail-index estimates document heavy-tailed behavior across the ETF universe. Although the ETFs exhibit broadly similar asymptotic tail-decay behavior, semiconductor-focused ETFs produce substantially larger VaR and CVaR estimates than diversified benchmarks, indicating that cross-sectional differences in extreme downside risk are driven primarily by differences in return scale rather than tail-index estimates. GJR-GARCH estimates reveal persistent, asymmetric volatility, and the apparent long memory in squared returns is largely attributable to conditional heteroskedasticity rather than genuine fractional integration. CVaR optimization produces substantially more concentrated allocations than mean--variance optimization, with the CVaR tangent portfolio allocating a large weight to SMH during the post-COVID AI-driven expansion. Portfolio rankings depend on the performance measure: the Sharpe ratio and STARR measure favor the equally weighted portfolio, whereas the Rachev ratio favors CVaR-based portfolios. Overall, the results suggest that variance-based frameworks alone provide an incomplete characterization of risk in technology-concentrated investment environments and that variance-based and tail-sensitive performance measures may favor different portfolios over the same sample period.
Comments46 pages, 19 figures, 4 tables. Submitted to Journal of Risk and Financial Management (JRFM)
