The Generalized Dynamic-Factor Model: Identification and Estimation
By M. Forni, Marc Hallin, Marco Lippi, L. Reichlin. 2000
1,920 citations recorded by the source corpus.
This paper proposes a factor model with infinite dynamics and nonorthogonal idiosyncratic components. The model, which we call the generalized dynamic-factor model, is novel to the literature and generalizes the static approximate factor model of Chamberlain and Rothschild (1983), as well as the exact factor model la Sargent and Sims (1977). We provide identification conditions, propose an estimator of the common components, prove convergence as both time and cross-sectional size go to infinity at appropriate rates, and present simulation results. We use our model to construct a coincident index for the European Union. Such index is defined as the common component of real GDP within a model including several macroeconomic variables for each European country.
Subfields: Economics and Econometrics, Probabilistic & Bayesian Methods, Time-Series & Forecasting
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Economics and Econometrics
- Jushan Bai
- Serena Ng
- Mark W. Watson
- James H. Stock
- Marco Lippi
- Domenico Giannone
- M. Forni
- Matteo Barigozzi
In Probabilistic & Bayesian Methods
- Jushan Bai
- Mark W. Watson
- George Kapetanios
- James H. Stock
- Serena Ng
- M. Forni
- Matteo Barigozzi
- L. Reichlin
In Time-Series & Forecasting
- Jushan Bai
- Mark W. Watson
- George Kapetanios
- James H. Stock
- Serena Ng
- M. Forni
- Matteo Barigozzi
- L. Reichlin
Citations in the corpus
- Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders (2019, neutral): “Alternative factor models over time are generalized dynamic-factor model (Forni et al., 2000; 2005) or factor-augmented vector autoregressive models (Bernanke et al.”
- Deep Factors for Forecasting (2019, background): “Dynamic factor models (DFMs) have been studied in econo-metrics for decades to model the co-evolvement of multiple time series (Geweke, 1977; Stock & Watson, 2011; Forni et al., 2000; Pan & Yao, 2008).”
- Sufficient Forecasting Using Factor Models (2015, methodology): “For example, Forni et al. (2000, 2015) studied factor estimation based on projection, Liu et al. (2012), Xue and Zou (2012) and Fan et al. (2015b) employed rank-based methods for robust estimation of the covariance matrices, and Connor et al. (2012) applied a weighted additive nonparametric…”
- Random matrix theory in statistics: A review (2014, methodology): “A more enhanced version of the factor analysis model, the so-called dynamic factor model, is used extensively in econometrics, where the factors f are taken to be time-dependent (Forni et al., 2000, 2004, 2005).”
- Identification and Bayesian Estimation of Dynamic Factor Models (2015, methodology): “The model considered in this article has more structures than the generalized dynamic factor model of Forni et al. (2000).”
- On estimation of the noise variance in high dimensional probabilistic principal component analysis (2013, background): “It is, however, desirable to estimate m directly from the data. In the literature, consistent estimators of m have been proposed in the high dimensional context, e.g. in Kritchman and Nadler (2008), Ulfarsson and Solo (2008), Onatski (2009) and Passemier and Yao (2012). As a benchmark work, Bai and ”
- Bi-cross-validation for factor analysis (2015, methodology): “For econometrics applications, there are more methods to estimate the number of factors [19, 3, 23] for dynamic factor models.”
- How Useful is Bagging in Forecasting Economic Time Series? A Case Study of US CPI Inflation (2005, neutral): “2A closely related approach to extracting common components has been developed by Forni et al. (2000, 2001) and applied in Forni et al. (2003). relevant predictors, conduct a two-sided t-test for each predictor and discard all insignificant predictors prior to forecasting.”
- EFFICIENT ESTIMATION OF FACTOR MODELS (2011, methodology): “Besides the principal component method, Forni et al. (2000, 2005) use the dynamic principal component method of Brillinger (1981) to estimate the dynamic factor model.”
- Nonstationary dynamic factor analysis (2006, methodology): “To write an ARMA(p, q) model in state space form, a state vector of dimension max(p, q + 1) (e.g. Akaike, 1974; Gardner et al., 1980; Ansley and Kohn, 1983) gives a minimal representation with uncorrelated errors in the transition and measurement equations.”
- A Quasi–Maximum Likelihood Approach for Large, Approximate Dynamic Factor Models (2012, neutral): “Approximate factor models for dynamic panels have been studied, under similar assumptions, by Bai & Ng (2002, 2006); Forni, Giannone, Lippi, and Reichlin (2007); Forni et al. (2000, 2005); and Stock and Watson (2002a, 2002b).”