TESTING HYPOTHESES ABOUT THE NUMBER OF FACTORS IN LARGE FACTOR MODELS

By A. Onatski. 2009

468 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Finance, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/87aa94cde6322df6306270bbd9e64abc4999f606

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

Determining the number of groups in latent panel structures with an application to income and democracy (2017, methodology): “See, for example, Pesaran, Smith, and Im (1996), Phillips and Sul (2003), Pesaran and Yamagata (2008), and Su and Chen (2013), among others.”
On Time-Varying Factor Models: Estimation and Testing ∗ (2017, methodology): “However, the criteria proposed by Bai and Ng (2002), Onatski (2009) and Ahn and Horenstein (2013) work poorly except for the case of small structural changes ( = 1).”
Specification Test for Panel Data Models with Interactive Fixed Effects (2014, unknown): “If the panel data model is static and the regressors are strictly exogenous as in Pesaran (2006) and Bai (2009), we can rely on the usual notion of strong mixing and allow serial correlation in the error terms.”
Random matrix theory in statistics: A review (2014, methodology): “RMT has been used to explain the bias of arbitrage pricing models in finite samples (Harding, 2008; Onatski, 2012) and in determining the number of significant factors (Onatski, 2009, 2010).”
Dynamic factor model with infinite‐dimensional factor space: Forecasting (2016, methodology): “Again, 2We have run some experiments with other criteria, such as Alessi et al. (2010), Onatski (2009), with no significant differences. no lags for the factors or the variable to be predicted are allowed.”
Universality of covariance matrices (2011, background): “They have manifold applications in various applied fields; see [7, 22, 23, 24] for an extensive account on statistical applications, [21, 29] for applications in economics and [30] in population genetics to name a few.”
Estimating Number of Factors by Adjusted Eigenvalues Thresholding (2019, methodology): “Onatski (2009) proposed a test statistic T ON = max r min i ≤ r max ( ˆ λ i − ˆ λ i +1 ) / (ˆ λ i +1 − ˆ λ i +2 ) to test the number of common factors where ˆ λ i is the i th largest eigenvalue of the estimated covariance matrix, and r min and r max are pre-speciﬁed lower and upper bounds of the…”
Hypothesis Tests for Principal Component Analysis When Variables are Standardized (2019, methodology): “Several methods exist for determining the number of components in factor analysis (Bai and Ng 2002; Kritchman and Nadler 2008; Onatski 2009; Owen and Wang 2016; Passimier et al. 2017).”
On factor models with random missing: EM estimation, inference, and cross validation (2020, background): “Hallin and Líska (2007), Onatski (2009, 2010, 2012), and Ahn and Horenstein (2013), among others.”
A diagnostic criterion for approximate factor structure (2016, methodology): “Conditional linear factor models aim at capturing the time-varying influence of financial and macroeconomic variables in a simple setting (see e.g. Shanken (1990), Cochrane (1996), Ferson and Schadt (1996), Ferson and Harvey (1991, 1999), Lettau and Ludvigson (2001), Petkova and Zhang (2005)).”
Factor Models with Local Factors — Determining the Number of Relevant Factors (2021, methodology): “8Under more restrictive assumptions on the error terms, Onatski (2010) proposes an appealing way to calibrate the tuning parameter Q, exploiting the shape of the eigenvalue distribution of the idiosyncratic noise at their edge, that unfortunately is no longer valid in the setup of this paper.”
Dynamic Factor Models with Infinite-Dimensional Factor Space: Asymptotic Analysis (2017, background): “…q. Denoting by A(L) and R the (infinite) matrices on the left- and right-hand sides of (1.6), 2Criteria to determine q without assuming (1.2) or (1.3) are obtained in Hallin and Lǐska, 2007 and Onatski, 2009. respectively, and letting Zt = A(L)xt, it follows that Zt = Rut + A(L)ξ t. (1.7) Under…”
Tracy-Widom Distribution for the Largest Eigenvalue of Real Sample Covariance Matrices with General Population (2014, methodology): “ny real systems, however, Σ 0 is usually unknown. In particular, ζ +, E + and γ 0 of, e.g., (2.16), are unknown and the largest eigenvalue µ 1 may not directly be used as a test statistics. Following [40], we observe that E + and γ 0 are eliminated under the null hypothesis in the test statistics R ”
Exponent of Cross-Sectional Dependence: Estimation and Inference (2016, unknown): “Methods used to determine the number of factors in large data sets, discussed in, e.g., Bai and Ng (2002), Onatski (2009) and Kapetanios (2010), are invalid and will select the wrong number of factors, even asymptotically.15 Finally, the use of estimated factors in regressions for forecasting or…”