Forecasting Using Principal Components From a Large Number of Predictors

By James H. Stock, Mark W. Watson. 2002

3,141 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Finance, Management Science and Operations Research

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 Management Science and Operations Research

Citations in the corpus

Principal Components and Regularized Estimation of Factor Models (2017, methodology): “ Consistent 24 with previous studies, some series are transformed by taking logs and ﬁrst diﬀerencing before the factors are estimated. The panel is not balanced, we use the EM algorithm suggested in Stock and Watson (2002a) which imputes the missing values from the factor model and iterate till con”
Sufficient Forecasting Using Factor Models (2015, methodology): “…(Fama and French, 1992; Carhart, 1997; Fama and French, 2015; Hou et al., 2015), large-scale multiple testing (Leek and Storey, 2008; Fan et al., 2012), high-dimensional covariance matrix estimation (Fan et al., 2008, 2013), and forecasting using many predictors (Stock and Watson, 2002 a , b ).”
On Time-Varying Factor Models: Estimation and Testing ∗ (2017, background): “Stock and Watson (2002, 2009) argue that when the factor loadings undergo small instabilities, the estimated factors obtained via the conventional principal component analysis (PCA) are still consistent.”
A Quasi–Maximum Likelihood Approach for Large, Approximate Dynamic Factor Models (2012, neutral): “A similar model has been used, for example, in Stock and Watson (2002a) .”
Challenges of Big Data Analysis (2013, neutral): “The ADHD-200datasetissimilarlystructured;yet,it includesdiagnosticinformationondiseasestatus suchashumanIQ.”
Model-Based Clustering of Non-Gaussian Panel Data Based on Skew-t Distributions (2010, methodology): “For example, dynamic factor models as in Stock and Watson (2002) and Forni et al. (2005) are an alternative way to induce dimension reduction, especially when used in the context of macroeconomic forecasting.”
Financial development and the FDI-growth nexus: the Malaysian experience (2009, methodology): “Hence, we develop a composite measure for financial development using principal component analysis (see, e.g. Demetriades and Luintel, 1997, 2001; Stock and Watson, 2002a, b; Ang and McKibbin, 2007).”
Confidence Intervals for Diffusion Index Forecasts and Inference for Factor-Augmented Regressions (2006, methodology): “(1) and (2) constitutes the ‘diffusion index forecasting model’ (DI) of Stock and Watson (2002a) .”
Panel Vector Autoregressive Models: A Survey (2013, neutral): “…in the applied macroeconometric literature because they capture the idea that the comovements present in a large set of series may be driven by a small number of latent variables, and because they are relatively easy to specify and estimate (Forni et al., 2000 and 2005; Stock and Watson, 2002).”
Financial liberalization, financial sector development and growth: Evidence from Malaysia (2007, neutral): “of uncorrelated variables, known as principal components (see Stock and Watson, 2002a, b).”