Statistical analysis of factor models of high dimension

2012/02/01 by Jushan Bai, Kunpeng Li · 17 citations
Mathematics · Economics, Econometrics and Finance · #Statistical Methods and Inference #Financial Risk and Volatility Modeling #Statistical Methods and Bayesian Inference

paper · doi:10.1214/11-aos966

Abstract

This paper considers the maximum likelihood estimation of factor models of high dimension, where the number of variables (N) is comparable with or even greater than the number of observations (T). An inferential theory is developed. We establish not only consistency but also the rate of convergence and the limiting distributions. Five different sets of identification conditions are considered. We show that the distributions of the MLE estimators depend on the identification restrictions. Unlike the principal components approach, the maximum likelihood estimator explicitly allows heteroskedasticities, which are jointly estimated with other parameters. Efficiency of MLE relative to the principal components method is also considered.

Citations

• The Generalized Dynamic-Factor Model: Identification and Estimation

Cited by

• Large covariance estimation through elliptical factor models
• A Latent Variable Framework for Scaling Laws in Large Language Models
• Adaptive Estimation in Structured Factor Models with Applications to Overlapping Clustering
• Causal Inference on Sequential Treatments via Tensor Completion
• Estimating the true number of principal components under the random design
• Statistical Inferences Using Large Estimated Covariances for Panel Data and Factor Models
• Factor analysis in high dimensional biological data with dependent observations
• A Riemannian Factor Model for Manifold-Valued Time Series
• Robust high dimensional factor models with applications to statistical machine learning
• Item Response Theory -- A Statistical Framework for Educational and Psychological Measurement
• High-Dimensional Spatial Autoregression with Latent Factors by Diversified Projections
• Learning Latent Factors From Diversified Projections and Its Applications to Over-Estimated and Weak Factors
• Detecting approximate replicate components of a high-dimensional random vector with latent structure
• Estimating and accounting for unobserved covariates in high dimensional correlated data
• Identifiability and Inference for Generalized Latent Factor Models
• Large-dimensional Factor Analysis without Moment Constraints
• Factor Models for High-Dimensional Tensor Time Series

Related

• Efficient Estimation of Approximate Factor Models via Regularized Maximum Likelihood
• Asymptotic equivalence of Principal Components and Quasi Maximum Likelihood estimators in Large Approximate Factor Models
• A two-way factor model for high-dimensional matrix data
• Optimal Estimation of Large-Dimensional Nonlinear Factor Models
• High Dimensional Factor Analysis with Weak Factors