Confidence Intervals for Diffusion Index Forecasts and Inference for Factor-Augmented Regressions

By Jushan Bai, Serena Ng. 2006

656 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Finance, Statistics and Probability

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

In Finance

In Statistics and Probability

Citations in the corpus

Principal Components and Regularized Estimation of Factor Models (2017, methodology): “Bai and Ng (2006) shows that the APC estimate e F can be used in place of the latent F , and inference can proceed as though F was known provided √ → 0.”
Matrix Completion, Counterfactuals, and Factor Analysis of Missing Data (2019, methodology): “The theory in Bai and Ng (2006) can then be used to construct prediction intervals.”
Grouped Patterns of Heterogeneity in Panel Data (2015, background): “18 Secondly, the argument leading to the exponential rate of convergence of the misclassification probability (15) relies on the assumption that errors are i.”
The empirical risk–return relation: A factor analysis approach ☆ (2006, methodology): “Bai and Ng (2005) show that the least squares estimates from factor-augmented forecasting regressions are √ T consistent and asymptotically normal, and that pre-estimation of the factors does not affect the consistency of the second-stage parameter estimates.”
Principal Components Estimation and Identication of the Factors (2011, methodology): “Similarly, if √ T/N → 0 and H−1 = Ir +Op(δ−2NT ), then √ T (λ̃i − λi) = (F ′F T )−1 1√ T T∑ t=1 Fteit + op(1) (11) because F ′F/T = Ir and √ T (H−1 − Ir) = op(1) if √ T/N → 0.”
Non-Stationary Dynamic Factor Models for Large Datasets (2016, neutral): “Third, our asymptotic results could be straightforwardly extended to estimation of IRFs in a non-stationary Factor Augmented VAR setting (see Bai and Ng, 2006, for the stationary case) and form the theoretical foundation of the existing empirical studies based non-stationary factor models (see…”
Forecasting with Factor-Augmented Regression: A Frequentist Model Averaging Approach, Second Version (2013, neutral): “T 1/2/N → 0 condition used in Bai and Ng (2006).”
Real-Time Measurement of Business Conditions (2007, neutral): “…popular dynamic factor framework, whether from the “small data” perspective of Geweke (1977), Sargent and Sims (1977), Stock and Watson (1989, 1991), and Diebold and Rudebusch (1996), or the more recent “large data” perspective of Forni et al. (2000), Stock and Watson (2002), and Bai and Ng (2006).”
Detecting big structural breaks in large factor models (2014, methodology): “…illustrate the consequences of having big breaks in the factor loadings, consider the following simple Factor Augmented Regression (FAR) model (s e Bai and Ng, 2006): yt = a ′Ft +b′Wt +ut , t = 1,2, ..,T (12) whereWt is a small set of observable variables and ther × 1 vectorFt contains ther…”
DYNAMIC FACTOR MODELS (2018, background): “Bai (2003) provides limiting distributions for the estimated factors and common components Bai and Ng (2006a) provide improved rates, specifically N → ∞, T → ∞, and N 2 /T → ∞, under which is consistent and can be treated as data in subsequent regressions; they also provide results for construction…”
Asymptotic distribution of factor augmented estimators for panel regression (2012, background): “√ T/N → 0 and N, T →∞ are sufficient under regularity for replacing unobservable common factors with the PC estimate in time series models (Stock and Watson, 2002; Bernanke, Boivin, and Eliasz, 2005; Bai and Ng, 2006).”
Forecasting US Recessions: The Role of Sentiment (2014, neutral): “1 for the exact static factor model and extended to the approximate static factor model of Chamberlain and Rothschild (1983) by Stock and Watson (2002b), Bai (2003), and Bai and Ng (2006).”
Macro Factors in Bond Risk Premia (2005, methodology): “Our use of dynamic factor analysis is an application of statistical procedures developed elsewhere for the case where both the number of economic time series used to construct common factors, N , and the number of time periods, T , are large and converge to infinity (Stock and Watson 2002a, 2002b; B”
Systemic Risk and the Macroeconomy: An Empirical Evaluation (2016, positive): “…use of PCA to aggregate information among a large number of predictor variables is well-understood for least squares forecasting (see Stock and Watson (2002) and Bai and Ng (2006)), and the use of PCA factors as dependent variables in quantile regression has been proposed by Ando and Tsay (2011).”