Determining the Number of Factors in Approximate Factor Models

By Jushan Bai, Serena Ng. 2000

4,054 citations recorded by the source corpus.

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

Citations in the corpus

Principal Components and Regularized Estimation of Factor Models (2017, methodology): “Bai and Ng (2002) suggests a class of consistent factor selection criteria, that is, rules that yield r such that prob( r = r ) → 1 as N, T → ∞ . b b While criteria in this class have little diﬃculty singling out the dominant factors, they tend to be too liberal.”
Sufficient Forecasting Using Factor Models (2015, methodology): “It follows that ∥Λ̂b − Λb∥ = ∥(̂B′̂B)−1B̂′ − (B′B)−1B′∥ = ∥(̂B′̂B)−1B̂′ − (B′B)−1B̂′∥ + ∥(B′B)−1B̂′ − (B′B)−1B′∥ ≤ ∥(̂B′̂B)−1 − (B′B)−1∥ · ∥̂B∥ + ∥(B′B)−1∥ · ∥̂B′ − B′∥ = Op(p−1ωp,T ) · Op(p1/2) + Op(p−1) · Op(p1/2ωp,T ) = Op(p−1/2ωp,T ). which completes the proof of Lemma A.4.”
Identification and estimation of a large factor model with structural instability (2017, positive): “Define r̃ as the estimated number of factors using the information criteria in Bai and Ng (2002), we will have lim (N,T )→∞ P (r̃ = r + q1) = 1, since model (2) can be equivalently represented as model (3).”
Country spreads and emerging countries (2003, positive): “7 Bai and Ng (2002) propose a procedure to determine the number of factors in the static model.”
Autoregressive models for matrix-valued time series (2018, background): “, 2015; Song and Bickel, 2011, among others), and (ii) statistical or dynamic factor models (Bai and Ng, 2002; Fan et al., 2013; Forni et al., 2005; Lam and Yao, 2012; Lam et al., 2011; Wang et al., 2019, among others). In most of these studies, the multiple observations at each time point are treat”
Business Cycle Transmission from the US to Germany: A Structural Factor Approach (2007, positive): “ˆˆ ttt Χ−Υ=Ξ The number of static principal components r is determined by means of the formal criteria derived by Bai and Ng (2002).”
Bank Regulation, the Quality of Institutions, and Banking Risk in Emerging and Developing Countries: An Empirical Analysis (2014, methodology): “In several surveys, Barth et al. (2004; 2008) collected detailed and comprehensive information on bank regulation and supervision for more than 107 countries between 1999 and 2008. Barth et al. (2004) report that policies that induce accurate information disclosure and (incentives for) private secto”
Modeling frailty-correlated defaults using many macroeconomic covariates (2011, methodology): “To determine the number of factors we compute the panel information criteria (IC) as suggested by Bai and Ng (2002). The information criteria suggest two common factors, which together capture about 44% of the total variation in the macro panel.”
A Robust Criterion for Determining the Number of Static Factors in Approximate Factor Models (2008, positive): “All six criteria by Bai and Ng [2002] search for the number of static factors that minimizes the mean squared distance between observed data and their common part as estimated by static principal components.”
Determining the Number of Factors from Empirical Distribution of Eigenvalues (2010, methodology): “Theorem 1. Let model ( 2 ) satisfy Assumptions 1 and 2, and let fT(n);n 2 Ng be a”
Incorporating Global Industrial Classification Standard Into Portfolio Allocation: A Simple Factor-Based Large Covariance Matrix Estimator With High-Frequency Data (2016, neutral): “More recent work, including Bai (2003), Bai and Ng (2002), and Stock and Watson (2002), establishes the asymptotic theory, though their focus is not on the consistency under matrixwise norms.”
Alternative Approaches to Estimation and Inference in Large Multifactor Panels: Small Sample Results with an Application to Modelling of Asset Returns (2005, positive): “This can be done using the criteria advanced in Bai and Ng (2002) .”
Boom or Gloom? Examining the Dutch Disease in Two-Speed Economies (2014, methodology): “For both the Australian and the Norwegian data sets, different test statistics, see Bai and Ng (2002), suggest between 3 and 8 static factors.”