Hidden Factor estimation in Dynamic Generalized Factor Analysis Models
Giorgio Picci, Lucia Falconi, Augusto Ferrante, Mattia Zorzi
TL;DR
This paper explores the estimation of hidden factors in Dynamic Generalized Factor Analysis models using a generalized Kalman filtering approach, highlighting the importance of the pure filter for consistent estimation.
Contribution
It introduces a generalized Kalman filtering method for hidden factor estimation and demonstrates the pure filter's consistency over the one-step predictor.
Findings
The pure filter provides consistent estimates of hidden factors.
The one-step predictor is not suitable for consistent estimation.
Asymptotic properties of the proposed method are discussed.
Abstract
This paper deals with the estimation of the hidden factor in Dynamic Generalized Factor Analysis via a generalization of Kalman filtering. Asymptotic consistency is discussed and it is shown that the Kalman one-step predictor is not the right tool while the pure filter yields a consistent estimate.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsControl Systems and Identification · Neural Networks and Applications · Blind Source Separation Techniques