Detecting big structural breaks in large factor models

Liang, Chen; Dolado, Juan J.; Gonzalo, Jesús

doi:10.1016/j.jeconom.2014.01.006

Cited by 122 publications

(114 citation statements)

References 35 publications

Supporting

Mentioning

110

Contrasting

Order By: Relevance

“…Chen, Dolado, and Gonzalo (2014) show, using simulations, that imposing a priori number of factors that ignores the existence of a large break on Λ can worsen the forecasting power of the factor-augmented regressions. Overestimating the number of factors can help, but this entails more estimation uncertainty that ultimately increases the mean squared predicted errors.…”

Section: Consequencesmentioning

confidence: 97%

“…They also verify the performance of the Bai and Ng (2002) criterion to successfully predict the dimension of the factor space. The second related paper is Chen, Dolado, and Gonzalo (2014), who provide a framework to test for large breaks in factor loadings 1 . They also show that the Bai and Ng (2002) information criteria are likely to overestimate the true number of factors in the presence of large breaks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Selection of the Number of Factors in Presence of Structural Instability: A Monte Carlo study

Takongmo

Stevanović

2016

View full text Add to dashboard Cite

In this paper we study the selection of the number of primitive shocks in exact and approximate factor models in the presence of structural instability. The empirical analysis shows that the estimated number of factors varies substantially across several selection methods and over the last 30 years in standard large macroeconomic and financial panels. Using Monte Carlo simulations, we suggest that the structural instability, expressed as time-varying factor loadings, can alter the estimation of the number of factors and therefore provides an explanation for the empirical findings

show abstract

Section: Consequencesmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

Selection of the Number of Factors in Presence of Structural Instability: A Monte Carlo study

Takongmo

Stevanović

2016

View full text Add to dashboard Cite

show abstract

“…1 . Finally, it is worth noting that Chen, Dolado and Gonzalo (2011) propose a Lagrange Multiplier test for constancy of loadings, in which they regress the first factors over the remaining factors. The logic underlying their test is that under the null of structural stability, the estimated factors are consistent for the "true" ones, and so are orthogonal to each other.…”

Section: Set-upmentioning

confidence: 99%

“…For example, Breitung and Eickmeier (2011) propose tests for the null hypothesis of a structural break in factor loading coefficients. Additionally, direct tests for con-1 stancy of all factor loadings, which allow for some spatial correlation, have recently been suggested by Chen, Dolado and Gonzalo (2011) and by Han and Inoue (2012).…”

Section: Introductionmentioning

confidence: 99%

Testing for structural stability of factor augmented forecasting models

Corradi

Swanson

2014

Journal of Econometrics

View full text Add to dashboard Cite

Mild factor loading instability, particularly if sufficiently independent across the different constituent variables, does not affect the estimation of the number of factors, nor subsequent estimation of the factors themselves (see e.g. Stock and Watson (2009)). This result does not hold in the presence of large common breaks in the factor loadings, however. In this case, information criteria overestimate the number of breaks. Additionally, estimated factors are no longer consistent estimators of "true" factors. Hence, various recent research papers in the diffusion index literature focus on testing the constancy of factor loadings. One reason why this is a positive development is that in applied work, factor augmented forecasting models are used widely for prediction, and it is important to understand when such models are stable. Now, forecast failure of factor augmented models can be due to either factor loading instability, regression coefficient instability, or both. To address this issue, we develop a test for the joint hypothesis of structural stability of both factor loadings and factor augmented forecasting model regression coefficients. The proposed statistic is based on the difference between full sample and rolling sample estimators of the sample covariance of the factors and the variable to be forecasted. Failure to reject the null ensures the structural stability of the factor augmented forecasting model. If the null is instead rejected, one can proceed to disentangle the cause of the rejection as being due to either (or both) of the afore mentioned varieties of instability. Standard inference can be carried out, as the suggested statistic has a chi-squared limiting distribution. We also establish the first order validity of (block) bootstrap critical values. Finally, we provide an empirical illustration by testing for the structural stability of factor augmented forecasting models for 11 U.S. macroeconomic indicators.

show abstract

“…The first formal test was proposed by Breitung and Eickmeier (2011) who considered the problem of testing the loadings associated with the individual variables. This has since been followed up by Chen, Dolado, and Gonzalo (2014) and Han and Inoue (2014) who propose tests for breaks in all loadings jointly, and Yamamoto and Tanaka (2013) who proposed a modified version of the Breitung and Eickmeier (2011) test.…”

Section: Introductionmentioning

confidence: 99%