Filtering via Simulation: Auxiliary Particle Filters

Read full paper →
Authors
M. Pitt, Neil Shephard
Journal
Journal of the American Statistical Association
Year
1999
Citations
2,261

Abstract

This article analyses the recently suggested particle approach to filtering time series. We suggest that the algorithm is not robust to outliers for two reasons: the design of the simulators and the use of the discrete support to represent the sequentially updating prior distribution. Here we tackle the first of these problems.

Filtering via Simulation: Auxiliary Particle Filters | Steady Practice | SteadyPractice