• Management & Information Systems Review
• /
• v.33 no.5
• /
• pp.249-260
• /
• 2014

This paper explores the relationship between firm-specific volatility and some firm characteristics such as size, the market-to-book ratio of equity, PER, PBR, PCR, PSR and turnover in KOSDAQ market. In addition, I investigate whether portfolios with difference to realized range-based volatility and firm-specific volatility have different investment performance using CAPM and FF-3 factor model. The main findings of this study can be summarized as follows. First, firm-specific volatility have mostly positive relationship between firm-specific volatility and some firm characteristics. Second, this study found that realized range-based volatility and firm-specific volatility are positively related to expected return. It means that portfolios with high idiosyncratic volatility have significantly higher expected return than portfolios with low firm-specific volatility.

• The Korean Journal of Financial Management
• /
• v.26 no.2
• /
• pp.181-201
• /
• 2009

This study is on the forecasting performance analysis of range volatility estimators(Parkinson, Garman and Klass, and Rogers and Satchell) relative to historical one using two-scale realized volatility estimator as a benchmark. American sub-prime mortgage loan shock to Korean stock markets happened in sample period(January 2, 2006~March 10, 2008), so the structural change somewhere within this period can make a huge influence on the results. Therefore sample was divided into two sub-samples by May 30, 2007 according to Zivot and Andrews unit root test results. As expected, the second sub-sample was much more volatile than the first sub-sample. As a result of forecasting performance analysis, Rogers and Satchell volatility estimator showed the best forecasting performance in the full sample and relatively better forecasting performance than other estimators in sub-samples. Range volatility estimators showed better forecasting performance than historical volatility estimator during the period before the outbreak of structural change(the first sub-sample). On the contrary, the forecasting performance of range volatility estimators couldn't beat that of historical volatility estimator during the period after this event(the second sub-sample). The main culprit of this result seems to be the increment of range volatility caused by that of intraday volatility after structural change.

• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.69-81
• /
• 2019

We consider bivariate long range dependent (LRD) time series forecasting using a deep learning method. A long short-term memory (LSTM) network well-suited to time series data is applied to forecast bivariate time series; in addition, we compare the forecasting performance with bivariate fractional autoregressive integrated moving average (FARIMA) models. Out-of-sample forecasting errors are compared with various performance measures for functional MRI (fMRI) data and daily realized volatility data. The results show a subtle difference in the predicted values of the FIVARMA model and VARFIMA model. LSTM is computationally demanding due to hyper-parameter selection, but is more stable and the forecasting performance is competitively good to that of parametric long range dependent time series models.