The Generalized Dynamic Factor Model: Representation Theory

Forni, Mario; Lippi, Marco

doi:10.1017/s0266466601176048

Cited by 298 publications

(223 citation statements)

References 9 publications

Supporting

Mentioning

217

Contrasting

Unclassified

Order By: Relevance

“…Early references on large ‘generalised’ or ‘approximate’ dynamic factor models are Forni and Reichlin (), Forni et al . (), Forni and Lippi (), Stock and Watson (, b ) and Bai and Ng ().…”

mentioning

confidence: 99%

No News in Business Cycles

Forni

Gambetti

Sala

2014

Econ J

Self Cite

View full text Add to dashboard Cite

A structural factor-augmented VAR model is used to evaluate the role of ‘news shocks’ in generating the business cycle. We find that existing small-scale VAR models are affected by ‘non-fundamentalness’ and therefore fail to recover the correct shock and impulse response functions; news shocks have a smaller role in explaining the business cycle than previously found in the literature; their effects are essentially in line with what predicted by standard theories and a substantial fraction of business cycle fluctuations are explained by shocks unrelated to technology

show abstract

mentioning

confidence: 99%

No News in Business Cycles

Forni

Gambetti

Sala

2014

Econ J

Self Cite

View full text Add to dashboard Cite

show abstract

“…An intermediate model allowing for some dynamics is the restricted factor model where q dynamic factor are expressed with r static factors, q< r (Forni et al ., ; Bai and Ng, ). A dynamic version of the approximate factor model, called the generalized dynamic factor model, has weekly cross‐correlated idiosyncratic components (see Forni and Lippi, ; Forni et al ., ). Byrne, Fazio and Fiess (), Chen et al .…”

Section: Review Of the Empirical Literaturementioning

confidence: 99%

What Drives Commodity Returns? Market, Sector or Idiosyncratic Factors?

Vivian

Wohar

2019

Oxf Bull Econ Stat

View full text Add to dashboard Cite

This paper examines the relationship between 43 commodity returns using a dynamic factor model with time varying stochastic volatility. The dynamic factor model decomposes each commodity return into a common (market), sector‐specific and commodity‐specific component. It enables the variance attributed to each component to be estimated at each point in time. We find the return variation explained by the common factor has increased substantially for the recent period and is statistically significant for the vast majority of commodities since 2004 (at each point in time) This phenomenon is the strongest for non‐perishable products. We link the amount of variation explained by the common factor to economic variables.

show abstract

“…The estimateĉ in this case can be obtained by taking the T -dimensional vector f and the T × T diagonal matrix A in the iterative algorithm (9) In this particular instance, it is natural to assume that the factors f t and covariates w t are correlated. We therefore estimated R z (t) by using (14). For each case of w t , the possible values of r range from 0 to 10.…”

Section: Application 2: Analysis Of the Number Of Default In Japanmentioning

confidence: 99%

Model selection for generalized linear models with factor‐augmented predictors

Ando

Tsay

2009

Appl Stoch Models Bus & Ind

View full text Add to dashboard Cite

This paper considers generalized linear models in a data-rich environment in which a large number of potentially useful explanatory variables are available. In particular, it deals with the case that the sample size and the number of explanatory variables are of similar sizes. We adopt the idea that the relevant information of explanatory variables concerning the dependent variable can be represented by a small number of common factors and investigate the issue of selecting the number of common factors while taking into account the effect of estimated regressors. We develop an information criterion under model mis-specification for both the distributional and structural assumptions and show that the proposed criterion is a natural extension of the Akaike information criterion (AIC). Simulations and empirical data analysis demonstrate that the proposed new criterion outperforms the AIC and Bayesian information criterion. as the LASSO technique for linear regression model may be used to overcome this difficulty. See Tibishirani [2]. In this paper, we focus on GLM models and take another approach to achieve dimension reduction. Specifically, we adopt the idea of principal component regression and assume that a small number of common factors of the explanatory variables are sufficient to describe the relevant information concerning the dependent variable. The common factors are latent variables and must be constructed from the observable explanatory variables. In this way, our approach is related to factor models.Factor models have a long history in statistical analysis. In recent years, they have attracted substantial attention as a useful tool to dimension reduction and/or statistical forecasting in the data-rich environment. See, for instance, . The use of factor models in GLM analysis, however, is less studied. The goal of our study is to close this gap.In time series analysis, when the number of explanatory series N and the sample size T increase at a similar rate, dynamic factor models and diffusion-index models have been proposed to improve the accuracy of prediction. See, for instance, Stock and Watson [23]. Applications of such models often involve a two-step procedure. In the first step, one uses principal component analysis or its variant to transform the explanatory observations into common factors. Certain criteria are then used to select the number of common factors, e.g. the scree plot. In the second step, one applies the least-squares method to fit a linear model for the dependent variable using the selected principal components along with some pre-determined variables as regressors. The pre-determined variables may include lagged values of the dependent variable. The fitted model is then used to make statistical prediction. This approach is plausible and, indeed, can be justified asymptotically under certain regularity conditions. See, for instance, Stock and Watson [22]. However, the selection of the number of common factors, or more precisely the choice of common factors, deserves a careful investi...

show abstract

The Generalized Dynamic Factor Model: Representation Theory

Cited by 298 publications

References 9 publications

No News in Business Cycles

No News in Business Cycles

What Drives Commodity Returns? Market, Sector or Idiosyncratic Factors?

Model selection for generalized linear models with factor‐augmented predictors

Contact Info

Product

Resources

About