A Quadratic Kalman Filter

39 Pages Posted: 21 Dec 2013 Last revised: 25 Nov 2014

See all articles by Alain Monfort

Alain Monfort

National Institute of Statistics and Economic Studies (INSEE) - Center for Research in Economics and Statistics (CREST); National Bureau of Economic Research (NBER); Maastricht University

Jean-Paul Renne

University of Lausanne - School of Economics and Business Administration (HEC-Lausanne)

Guillaume Roussellet

McGill University - Desautels Faculty of Management

Multiple version iconThere are 2 versions of this paper

Date Written: November 1, 2014

Abstract

We propose a new filtering and smoothing technique for non-linear state-space models. Observed variables are quadratic functions of latent factors following a Gaussian VAR. Stacking the vector of factors with its vectorized outer-product, we form an augmented state vector whose first two conditional moments are known in closed-form. We also provide analytical formulae for the unconditional moments of this augmented vector. Our new quadratic Kalman filter (Qkf) exploits these properties to formulate fast and simple filtering and smoothing algorithms. A first simulation study emphasizes that the Qkf outperforms the extended and unscented approaches in the filtering exercise showing up to 70% RMSEs improvement of filtered values. Second, we provide evidence that Qkf-based maximum-likelihood estimates of model parameters always possess lower bias or lower RMSEs that the alternative estimators.

Keywords: Non-linear filtering, non-linear smoothing, quadratic model, Kalman filter, Pseudo-maximum likelihood

JEL Classification: C32, C46, C53, C57

Suggested Citation

Monfort, Alain and Renne, Jean-Paul and Roussellet, Guillaume, A Quadratic Kalman Filter (November 1, 2014). Available at SSRN: https://ssrn.com/abstract=2369788 or http://dx.doi.org/10.2139/ssrn.2369788

Alain Monfort

National Institute of Statistics and Economic Studies (INSEE) - Center for Research in Economics and Statistics (CREST) ( email )

15 Boulevard Gabriel Peri
Malakoff Cedex, 1 92245
France
+33 1 4117 6079 (Phone)
+33 1 4117 6046 (Fax)

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Maastricht University

P.O. Box 616
Maastricht, Limburg 6200MD
Netherlands

Jean-Paul Renne

University of Lausanne - School of Economics and Business Administration (HEC-Lausanne) ( email )

UNIL, Batiment Internef
Lausanne, 1015
Switzerland

Guillaume Roussellet (Contact Author)

McGill University - Desautels Faculty of Management ( email )

1001 Sherbrooke St. West
Montreal, Quebec H3A1G5 H3A 2M1
Canada

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
356
Abstract Views
2,833
Rank
123,761
PlumX Metrics