Accurate Confidence Regions for Principal Components Factors*

2021/04/23 by Javier Maldonado, Esther Ruiz · 2 citations
Economics, Econometrics and Finance · #Financial Risk and Volatility Modeling #Monetary Policy and Economic Impact #Spatial and Panel Data Analysis

paper · doi:10.1111/obes.12436

openalex publication_date 2021/04/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

Abstract In dynamic factor models, factors are often extracted using principal components with their asymptotic confidence regions having empirical coverages below the nominal ones when the temporal dimension is small. We propose a subsampling procedure to compute the factor loadings uncertainty and correct the asymptotic covariance matrix of the extracted factors. We show that the empirical coverages of the modified confidence regions are closer to the nominal ones than those of asymptotic regions and asymptotically valid bootstrap regions. The results are empirically illustrated obtaining confidence intervals of the underlying factor in a system of Spanish macroeconomic variables.

Citations

• Strictly Proper Scoring Rules, Prediction, and Estimation
• Subsampling Versus Bootstrapping in Resampling-Based Model Selection for Multivariable Regression
• The World Is Not Enough! Small Open Economies and Regional Dependence

Cited by

• Economic Growth Vulnerability Across Euro Area Countries
• Heterogeneous economic growth vulnerability across Euro Area countries under stressed scenarios

Related

• A novel algorithm for confidence sub-contour box estimation: an\n alternative to traditional confidence intervals
• Approximate Factor Models with Weaker Loadings
• When can weak latent factors be statistically inferred?
• Dealing with idiosyncratic cross-correlation when constructing confidence regions for PC factors
• Augmented Factor Models with Applications to Validating Market Risk Factors and Forecasting Bond Risk Premia