Modeling and forecasting dynamic conditional correlations with opening, high, low, and closing prices
提出一种新的动态条件相关模型，利用每日开盘、最高、最低和收盘价信息同时改进方差和相关性估计，实证表明在条件协方差矩阵估计和预测上显著优于传统模型。
Models for variances and covariances of asset returns are crucial in risk management and asset allocation. Traditionally, these models were based on daily returns. Daily opening, high, low and closing (OHLC) prices have been sometimes used in multivariate volatility models for variances, but not for correlations. We therefore suggest a new version of the Dynamic Conditional Correlation (DCC) model wherein information from daily OHLC prices is utilized in both variance and correlation equations. The model is evaluated for two datasets: five exchange traded funds and five currencies. The results show that in terms of conditional covariance matrix estimates and forecasts the proposed model significantly outperforms, not only the standard DCC model, but also models that incorporate OHLC prices only in the variance equation.