日、韓、港、新與台灣等亞洲主要股市報酬變異分析－多重波動性狀態馬可夫轉換模型的應用

Exploring Return Variability for Major East Asian Market Indices via Multile-Volatility-State Markov-switching Models

黎明淵(Leon Ming-Yuan Li) ； 林修葳(William Hsiou-Wei Lin)

《Asia Pacific Management Review》 5卷2期 (2000/06) Pp. 183-198

https://doi.org/10.6126/APMR.2000.5.2.04

摘要

本研究以多重波動性狀態馬可夫轉換模型分析比較日、韓、港、新與台灣股價指數報酬變異性。實證結果發現，就統計與經濟門檻而言，馬可夫轉換模型的優勢固然明顯，然而這五個亞洲主要股市中，日、韓與台灣指數報酬變異性應配適以三重波動性狀態，港、新指數報酬變異性別以雙重波動性狀態劃分即可，不同國家所合用模型設定互異，此外，不同股市波動性狀態轉換過程亦不相同，模型設定須作適當微調。我們亦藉由多重波動狀態馬可夫轉換模型特性對各股市狀態期間作客觀劃分，分別以相對與絕對波動性大小，討論金融風暴對各股市造成衝擊。研究結果顯示，在指數報酬絕對波動性上，日本股市所受影響程度較低，台股報酬率雖然其絕對波動高於日本，但相對於自身報酬率數列前後各時點，當時其相對波動程度並不算高。這是由於台灣股市在風暴前夕的1996年4月至1997年7月間處於低波動性狀態，而台灣股市有不會逕由低波動轉換至高波動狀態的特性，所以該風暴未對台股造成直接高波動性狀態的衝擊。

關鍵字

馬可夫轉換模型 ； ARCH/GARCH模型 ； 股價指數報酬率

並列摘要

This study adopts multiple-volatility-state Markov-switching models to examine the return variability for Taiwan Stock Exchange (hereafter TSE) weighted index, Nikkei (price-weighted) index, Seoul Composite index, Hong Kong Hang Seng index and Singapore Straitrs index. The SWARCH forecasting models appear to outperform the competing constant variance, ARCH and GARCH models. Moreover, our findings are consistent with the notion that the three-volatility-regime setting is descriptive for TSE and Nikkei, and Seoul Composite indices. In contrast, the contemporaneous Hang Seng and Straitrs indices have only two regimes. Furthermore, Japanese market return is significantly less volatile than those of the other markets, including TSE, during the East Asian financial crisis. The relative volatility of the concurrent TSE returns, nevertheless, does not appear to be significant as compared with that of the past TSE return series. Our empirical results also lend an explanation to such phenomenon: the probability that TSE directly move from a low (high) volatility regime to the high (low) volatility regime is trivial, whereas TSE happened to be in a low volatility regime during the pre-financial-crisis period from April, 1996 to July, 1997.

並列關鍵字

Markov-switching model ； ARCH/GARCH model ； stock index returns

參考文獻

Baillie, R. T., DeGennaro, R. P.(1990).Stock Returns and Volatility.Journal of Financial and Quantitative Analysis.25

Bera, A. K., Bubnys, E., Park, H.(1988).Conditional heteroskedasticity in the market model and efficient estimates of betas.Financial Review.23

Bollerslev, T.(1986).Generalized Autoregressive Conditional Heteroskedasticity.Journal of Econometrics.31(3)

Bollerslev, T.(1987).A Conditionally Heteroskedastic Time Series Model for Speculative Prices and Rates of Return.Review of Economics and Statistics.69

Bollerslev, T., 周雨田 Chou, Ray Yeu-Tien, Kroner, K. F.(1992).ARCH Modeling in Finance: A Review of the Theory and Empirical Evidence.Journal of Econometrics.52(1/ 2)