This paper derives closed-form expressions for the asymptotic covariance matrices of factor loading and uniqueness estimators obtained from several widely used factor extraction methods, including least squares, principal factor, iterative principal component, alpha factor, and image factor analysis. By treating factor solutions as implicitly defined estimators, the proposed framework characterizes the asymptotic behavior of factor loadings and uniquenesses as explicit functions of the asymptotic covariance matrix of the sample covariance or correlation matrix. This approach avoids reliance on likelihood-based information matrices, numerical differentiation, and resampling methods. Consequently, valid statistical inference is feasible under non-Gaussian sampling, serial dependence, and conditional heteroskedasticity, and can be implemented using heteroskedasticit- and autocorrelation-robust or other sandwich estimators of second moments. The framework naturally accommodates applications in which factor analysis is applied to residual covariance matrices arising from multivariate regressions, panel data models, or structural vector autoregressions (SVARs). Monte Carlo simulations demonstrate accurate finite-sample performance, and an empirical illustration shows how the proposed formulas can be implemented in practice. From an econometric perspective, the results are particularly relevant for settings in which factor structures serve as intermediate objects---such as dynamic factor models, factor-augmented regressions, and SVARs---allowing uncertainty in factor estimates to be coherently propagated into impulse response functions, forecast-error variance decompositions, and other nonlinear functionals used in structural inference.
Feature selection, also known as variable selection, is a foundational problem in econometrics, artificial intelligence, and machine learning. However, widely used procedures may be inaccurate, unstable under collinearity, and sensitive to sampling noise and may lack a principled interpretation in terms of how they allocate explanatory power. This paper develops a feature-selection framework that extends a fair-division approach introduced by Hu ([2020, 2025). We represent the explanatory or forecasting performance of feature subsets as payoffs in a coalitional game subject to sampling uncertainty. Candidate features are partitioned into selected and unselected sets according to their fair-division values, defined using a modified Shapley value. Model uncertainty is represented by a beta-binomial distribution over subset size and a uniform distribution over subsets conditional on size. Each feature’s value combines the expected marginal gain from inclusion with the expected opportunity loss associated with exclusion, thereby treating all candidates symmetrically ex ante under a veil-of-ignorance principle. We further propose a sequential selection algorithm that uses a Monte Carlo approximation and a likelihood-ratio screening rule that admits at most one feature per iteration. Across the simulation designs considered, the procedure attains substantially higher exact-identification rates than those of the benchmark methods, including stepwise, unidirectional, GETS-style, and LASSO-based procedures. The paper also examines residual-share-based hyperparameter calibration, computational complexity, selection consistency, and practical implementation considerations.