摘要
The paper investigates the impact of jumps in forecasting covolatility, accommodating leverage effects. We modify the preaveraged truncated covariance estimator of Koike (2016) such that the estimated matrix is positive definite. Using this approach, we can disentangle the estimates of the integrated covolatility matrix and jump variations from the quadratic covariation matrix. Empirical results for three stocks traded on the New York Stock Exchange indicate that the cojumps of two assets have a significant impact on future covolatility, but the impact is negligible for forecasting weekly and monthly horizons.