Dynamic Factor Analysis in the Presence of Missing Data
Digital Academic REpository of VU University Amsterdam (Vrije Universiteit Amsterdam)Published 6 February 2009Open access
Borus Jungbacker, Siem Jan Koopman, Michel van der Wel
Citations10
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A new model representation for the dynamic factor model is proposed that allows the Kalman filter and related smoothing methods to evaluate the likelihood function and to produce optimal factor estimates in a computationally efficient way when missing data is present.
Abstract
textabstractWe develop a new model representation for high-dimensional dynamic multi-factor models. It allows the Kalman filter and related smoothing methods to produce optimal estimates in a computationally efficient way in the presence of missing data. We discuss the model in detail together with the implementation of methods for signal extraction and parameter estimation. The computational gains of the new devices are presented based on simulated data-sets with varying numbers of missing entries
Keywords
MathematicsBusiness, Management and Accounting
Journal of the Royal Statistical Society Series B (Statistical Methodology)Maximum Likelihood from Incomplete Data Via the <i>EM</i> Algorithm
49,657 Citations1977A. P. Dempster, N. M. Laird +1 more
Cambridge University Press eBooksNumerical optimization
14,107 Citations2021W. John Braun, Duncan J. Murdoch
Journal of the Operational Research SocietyForecasting, Structural Time Series Models and the Kalman Filter
4,809 Citations1991Robert Fildes, Andrew Harvey +2 more
Journal of the American Statistical AssociationForecasting Using Principal Components From a Large Number of Predictors
2,984 Citations2002James H. Stock, Mark W. Watson
Journal of Business and Economic StatisticsMacroeconomic Forecasting Using Diffusion Indexes
2,585 Citations2002James H. Stock, Mark W. Watson
Springer texts in statisticsTime Series Analysis and Its Applications
2,002 Citations2010Robert H. Shumway, David S. Stoffer
Characteristics of Time Series * Time Series Regression and ARIMA Models * Dynamic Linear Models and Kalman Filtering * Spectral Analysis and Its Applications.
The Review of Economics and StatisticsThe Generalized Dynamic-Factor Model: Identification and Estimation
1,715 Citations2000Mario Forni, Marc Hallin +2 more
Journal of Time Series AnalysisAN APPROACH TO TIME SERIES SMOOTHING AND FORECASTING USING THE EM ALGORITHM
1,492 Citations1982Robert H. Shumway, David S. Stoffer
Business Cycle Modeling Without Pretending to Have Too Much A Priori Economic Theory
662 Citations1977Christopher A. Sims, Thomas J. Sargent
IEEE Transactions on Information TheoryEvaluation of likelihood functions for Gaussian signals
541 Citations1965Fred C. Schweppe
Time-varying finite-dimensional Markov models are discussed as they lead to a direct mechanization for the required conditional expectation and a simple example of a multipath communication system is discussed and an explicit mechanization indicated.
The Review of Economics and StatisticsA Quasi–Maximum Likelihood Approach for Large, Approximate Dynamic Factor Models
519 Citations2011Catherine Doz, Domenico Giannone +1 more
Journal of EconometricsAlternative algorithms for the estimation of dynamic factor, mimic and varying coefficient regression models
476 Citations1983Mark W. Watson, Robert F. Engle
The paper suggests using the EM methods to quickly locate a neighborhood of the maximum and calculate the information matrix, a derivative-free method based on the method of Scoring.
Journal of the American Statistical AssociationA One-Factor Multivariate Time Series Model of Metropolitan Wage Rates
447 Citations1981Robert F. Engle, Mark W. Watson
Journal of Applied EconometricsMAXIMUM LIKELIHOOD ESTIMATION OF FACTOR MODELS ON DATASETS WITH ARBITRARY PATTERN OF MISSING DATA
359 Citations2012Marta Bańbura, Michèle Modugno
The expectation maximization algorithm is modified in order to estimate the parameters of the dynamic factor model on a dataset with an arbitrary pattern of missing data and the model is extended to the case with a serially correlated idiosyncratic component.
Journal of the American Statistical AssociationLinear Dynamic Recursive Estimation from the Viewpoint of Regression Analysis
241 Citations1972David B. Duncan, Susan D. Horn
This work presents the relevant random-β regression theory as a natural extension of conventional fixed- β regression theory and derives the optimal recursive estimators in terms of the extended regression theory for a typical form of the recursive model.
International Economic ReviewBayesian Leading Indicators: Measuring and Predicting Economic Conditions in Iowa
214 Citations1998Christopher Otrok, Charles H. Whiteman
Journal of EconometricsExtensions of estimation methods using the EM algorithm
187 Citations1991Paul A. Ruud
The clarifications of the EM algorithm lead to several applications of the algorithm to models that have appeared to be less tractable and an estimation method based on simulations.
American Economic Journal MacroeconomicsRelative Goods' Prices, Pure Inflation, and The Phillips Correlation
163 Citations2010Ricardo Reis, Mark W. Watson
Digital Academic REpository of VU University Amsterdam (Vrije Universiteit Amsterdam)Likelihood-based Analysis for Dynamic Factor Models
99 Citations2008Borus Jungbacker, Siem Jan Koopman
Digital Academic REpository of VU University Amsterdam (Vrije Universiteit Amsterdam)Filtering and smoothing of stae vector for diffuse state space models
91 Citations2003Siem Jan Koopman, J. Durbin
The B E Journal of MacroeconomicsOn the cyclicality of real wages and wage differentials
8 Citations2017Christopher Otrok, Panayiotis M. Pourpourides