Second-Order Filter Distribution Approximations for Financial Time Series With Extreme Outliers
含极端异常值金融时间序列的二阶滤波分布近似
Particle filters are regularly used to obtain the filter distributions associated with state–space financial time series. The most common use today is the auxiliary particle filter (APF) method in conjunction with a first-order Taylor expansion of the log-likelihood. We argue that for series such as stock returns, which exhibit fairly frequent and extreme outliers, filters based on this first-order approximation can easily break down. However, an APF based on the much more…