پیش بینی نوسانات در بازار سهام چینی تحت مدل عدم اطمینان
|کد مقاله||سال انتشار||تعداد صفحات مقاله انگلیسی||ترجمه فارسی|
|17761||2013||4 صفحه PDF||سفارش دهید|
نسخه انگلیسی مقاله همین الان قابل دانلود است.
هزینه ترجمه مقاله بر اساس تعداد کلمات مقاله انگلیسی محاسبه می شود.
این مقاله تقریباً شامل 3190 کلمه می باشد.
هزینه ترجمه مقاله توسط مترجمان با تجربه، طبق جدول زیر محاسبه می شود:
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Economic Modelling, Volume 35, September 2013, Pages 231–234
Volatility forecasting is an important issue in empirical finance. In this paper, the main purpose is to apply the model averaging techniques to reduce volatility model uncertainty and improve volatility forecasting. Six GARCH-type models are considered as candidate models for model averaging. As to the Chinese stock market, the largest emerging market in the world, the empirical study shows that forecast combination using model averaging can be a better approach than the individual forecast
Accurate volatility forecasting is one of the key tasks in empirical finance, such as, investment, security valuation, risk management, and monetary policy. Consequently, in the past two decades, forecasting volatility in financial markets has attracted growing attention by academics and practitioners. Engle (1982) first proposed the so-called Autoregressive Conditional Heteroscedasticity (ARCH) model for modeling the asset volatility. A generalization of ARCH, GARCH, was developed by Bollerslev (1986). After that, many general extensions of these fundamental models have been developed, see Francq and Zakoian (2010) for an excellent overview. An excellent review about volatility forecasting using these volatility models was recently reported by Poon and Granger (2003). While the use of models has undeniably led to a better measurement of volatility, it has in turn, given rise to a new problem, “model risk” or “model uncertainty,” which is linked to the uncertainty of the choice of the volatility model itself. The literature revealed that discarding model uncertainty can create a large utility or wealth loss (Doron Avramov, 2002 and Rapach et al., 2009). However, with ignoring model uncertainty, most empirical studies on volatility forecasting focused on choosing the best model among the candidate models where the techniques ranging from in-sample criteria through out-of-sample criteria, such as AIC, BIC, were used. In this paper, instead of choosing the best model, we use the model averaging technique to deal with model uncertainty. Several volatility models are considered to be appropriate candidates for model averaging. Recognizing that numerous empirical studies addressed international stock market volatility, but few focused on the emerging stock markets, we apply the model averaging technique to Chinese stock market. To the best of our knowledge, this is the first study to explore the model averaging technique to forecast Chinese stock market volatility under model uncertainty. This study attempts to enrich the existing literature by investigating the case of China, the largest transitional economy in the world, which has a unique market structure—particularly in the dominance of individual investors over institutional investors in the stock market (Ng and Wu, 2007). The remainder of this paper is organized as follows. Section 2 describes the data and model averaging approach. Section 3 relates the empirical results and forecasting valuation. Finally, conclusions and discussions are included in Section 4.
نتیجه گیری انگلیسی
This paper examines six individual models which are most popular in empirical finance and five combined strategies for forecasting the volatility of Chinese stock market. We find that no individual forecast consistently outperforms all other forecasts across all statistical loss functions, under all the considered cases. In addition, the best model among the candidate models chosen for forecasting is seriously dependent on the choice of training data. If the combined methods are used, the empirical studies show that these forecasts are more accurate than the worst single-model forecasts for all cases and outperform the averaging behaviors of the individual forecast in most cases.