Bridging factor and sparse models
From MaRDI portal
Abstract: Factor and sparse models are two widely used methods to impose a low-dimensional structure in high-dimensions. However, they are seemingly mutually exclusive. We propose a lifting method that combines the merits of these two models in a supervised learning methodology that allows for efficiently exploring all the information in high-dimensional datasets. The method is based on a flexible model for high-dimensional panel data, called factor-augmented regression model with observable and/or latent common factors, as well as idiosyncratic components. This model not only includes both principal component regression and sparse regression as specific models but also significantly weakens the cross-sectional dependence and facilitates model selection and interpretability. The method consists of several steps and a novel test for (partial) covariance structure in high dimensions to infer the remaining cross-section dependence at each step. We develop the theory for the model and demonstrate the validity of the multiplier bootstrap for testing a high-dimensional (partial) covariance structure. The theory is supported by a simulation study and applications.
Recommendations
Cites work
- A diagnostic criterion for approximate factor structure
- Analytical nonlinear shrinkage of large-dimensional covariance matrices
- ArCo: an artificial counterfactual approach for high-dimensional panel time-series data
- Central limit theorem and bootstrap approximation in high dimensions: near \(1/\sqrt{n}\) rates via implicit smoothing
- Common risk factors in the returns on stocks and bonds
- Confidence Intervals for Diffusion Index Forecasts and Inference for Factor-Augmented Regressions
- Do We Exploit all Information for Counterfactual Analysis? Benefits of Factor Models and Idiosyncratic Correction
- Dynamic factor models with infinite-dimensional factor space: asymptotic analysis
- Economic Predictions With Big Data: The Illusion of Sparsity
- Estimation and Inference in Large Heterogeneous Panels with a Multifactor Error Structure
- Estimation of High Dimensional Mean Regression in the Absence of Symmetry and Light Tail Assumptions
- Factor-Adjusted Regularized Model Selection
- Forecasting Using Principal Components From a Large Number of Predictors
- Gaussian approximation for high dimensional time series
- Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors
- Heteroskedasticity and Autocorrelation Consistent Covariance Matrix Estimation
- Improved central limit theorem and bootstrap approximations in high dimensions
- Inference on Causal and Structural Parameters using Many Moment Inequalities
- Inferences in panel data with interactive effects using large covariance matrices
- Inferential Theory for Factor Models of Large Dimensions
- Large covariance estimation by thresholding principal orthogonal complements. With discussion and authors' reply
- Linear regression for panel with unknown number of factors as interactive fixed effects
- Nearly optimal central limit theorem and bootstrap approximations in high dimensions
- Noisy matrix decomposition via convex relaxation: optimal rates in high dimensions
- On the conditions used to prove oracle results for the Lasso
- On the Convergence Rate in the Central Limit Theorem for Weakly Dependent Random Variables
- On the network topology of variance decompositions: measuring the connectedness of financial firms
- Oracle inequalities for high dimensional vector autoregressions
- Panel data models with interactive fixed effects
- Partial correlation estimation by joint sparse regression models
- Predicting the VIX and the volatility risk premium: the role of short-run funding spreads volatility factors
- Regularized estimation of high‐dimensional vector autoregressions with weakly dependent innovations
- Shrinkage estimation of large covariance matrices: keep it simple, statistician?
- Shrinkage tuning parameter selection with a diverging number of parameters
- Statistical foundations of data science
- The generalized dynamic factor model: identification and estimation
Cited in
(17)- Sparse factor model based on trend filtering
- Non-parametric regression among factor scores: motivation and diagnostics for nonlinear structural equation models
- Testing for sparse idiosyncratic components in factor-augmented regression models
- Inference for time-varying factor models under local stationarity
- The dynamic, the static, and the weak: factor models and the analysis of high-dimensional time series
- A refined bootstrap procedure for high-dimensional factor-augmented regression models
- Consistent model selection for factor-augmented regression within hierarchical factor structures
- Self-normalized Cramér type moderate deviation theorem for Gaussian approximation
- Estimation of large covariance matrices with mixed factor structures
- Estimating time-varying networks for high-dimensional time series
- Distributional counterfactual analysis in high-dimensional setup
- Supervised factor modeling for high-dimensional linear time series
- Portfolio selection revisited
- Counterfactual Imputation: Comments on “Imputation of Counterfactual Outcomes when the Errors are Predictable” by Silvia Gonçalves and Serena Ng
- Precision Least Squares: Estimation and Inference in High-Dimensions
- Detecting Giver and Receiver Spillover Groups in Large Vector Autoregressions
- High-dimensional inference for single-index models with latent factors
This page was built for publication: Bridging factor and sparse models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6183755)
