Template-type: ReDIF-Paper 1.0
Author-Name: Neil Shephard
Author-Workplace-Name: Nuffield College and Dept of Economics, University of Oxford
Author-Email: neil.shephard@nuffield.ox.ac.uk
Title: Martingale unobserved component models
Abstract: I discuss models which allow the local level model, which rationalised exponentially weighted
moving averages, to have a time-varying signal/noise ratio. I call this a martingale component
model. This makes the rate of discounting of data local. I show how to handle such models
effectively using an auxiliary particle filter which deploys M Kalman filters run in parallel
competing against one another. Here one thinks of M as being 1,000 or more. The model is
applied to inflation forecasting. The model generalises to unobserved component models where
Gaussian shocks are replaced by martingale difference sequences.
Classification-JEL: C01; C14; C58; D53; D81
Keywords: auxiliary particle filter; EM algorithm; EWMA; forecasting; Kalman filter; likelihood;
martingale unobserved component model; particle filter; stochastic volatility.
Length: 32 pages
Creation-Date: 2013-02-10
Number: 2013-W01
File-URL: http://www.nuffield.ox.ac.uk/Academic/Economics/Working%20Papers/Documents/2013/ll20130210.pdf
File-Format: application/pdf
Handle: RePEc:nuf:econwp:1301