Abstract: We consider forecasting a single time series when there is a large number of predictors and a possible nonlinear effect. The dimensionality was first reduced via a high-dimensional (approximate) factor model implemented by the principal component analysis. Using the extracted factors, we develop a novel forecasting method called the sufficient forecasting, which provides a set of sufficient predictive indices, inferred from high-dimensional predictors, to deliver additional predictive power. The projected principal component analysis will be employed to enhance the accuracy of inferred factors when a semi-parametric (approximate) factor model is assumed. Our method is also applicable to cross-sectional sufficient regression using extracted factors. The connection between the sufficient forecasting and the deep learning architecture is explicitly stated. The sufficient forecasting correctly estimates projection indices of the underlying factors even in the presence of a nonparametric forecasting function. The proposed method extends the sufficient dimension reduction to high-dimensional regimes by condensing the cross-sectional information through factor models. We derive asymptotic properties for the estimate of the central subspace spanned by these projection directions as well as the estimates of the sufficient predictive indices. We further show that the natural method of running multiple regression of target on estimated factors yields a linear estimate that actually falls into this central subspace. Our method and theory allow the number of predictors to be larger than the number of observations. We finally demonstrate that the sufficient forecasting improves upon the linear forecasting in both simulation studies and an empirical study of forecasting macroeconomic variables.
Recommendations
Cites work
- A general framework for multiple testing dependence
- Are more data always better for factor analysis?
- Determining the Dimensionality in Sliced Inverse Regression
- Determining the Number of Factors in Approximate Factor Models
- Determining the Number of Factors in the General Dynamic Factor Model
- Dynamic factor models with infinite-dimensional factor spaces: one-sided representations
- Efficient semiparametric estimation of the Fama-French model and extensions
- Eigenvalue ratio test for the number of factors
- Estimating false discovery proportion under arbitrary covariance dependence
- Estimating the Technology of Cognitive and Noncognitive Skill Formation
- Factor modeling for high-dimensional time series: inference for the number of factors
- Forecasting economic time series using targeted predictors
- Forecasting Using Principal Components From a Large Number of Predictors
- High dimensional covariance matrix estimation using a factor model
- High-dimensional semiparametric Gaussian copula graphical models
- scientific article; zbMATH DE number 991833 (Why is no real title available?)
- scientific article; zbMATH DE number 3942782 (Why is no real title available?)
- scientific article; zbMATH DE number 646819 (Why is no real title available?)
- scientific article; zbMATH DE number 700016 (Why is no real title available?)
- scientific article; zbMATH DE number 3274494 (Why is no real title available?)
- Improved penalization for determining the number of factors in approximate factor models
- Inferential Theory for Factor Models of Large Dimensions
- Large covariance estimation by thresholding principal orthogonal complements. With discussion and authors' reply
- Learning deep architectures for AI
- Measure Theory and Probability Theory
- Nonparametric econometrics. Theory and practice.
- Nonparametric regression with nonparametrically generated covariates
- On almost linearity of low dimensional projections from high dimensional data
- On Sliced Inverse Regression With High-Dimensional Covariates
- Prediction by Supervised Principal Components
- Principal components estimation and identification of static factors
- Projected principal component analysis in factor models
- Regularized rank-based estimation of high-dimensional nonparanormal graphical models
- SEMIPARAMETRIC ESTIMATION OF PARTIALLY LINEAR MODELS FOR DEPENDENT DATA WITH GENERATED REGRESSORS
- Sliced Inverse Regression for Dimension Reduction
- The Rotation of Eigenvectors by a Perturbation. III
- The three-pass regression filter: a new approach to forecasting using many predictors
Cited in
(41)- Canonical thresholding for nonsparse high-dimensional linear regression
- Adaptive estimation in multivariate response regression with hidden variables
- Inference in latent factor regression with clusterable features
- Nearest comoment estimation with unobserved factors
- Maximum likelihood estimation and inference for high dimensional generalized factor models with application to factor-augmented regressions
- Forecasting Using Principal Components From a Large Number of Predictors
- scientific article; zbMATH DE number 7625163 (Why is no real title available?)
- Diagonally Dominant Principal Component Analysis
- Short communication: Deep fundamental factor models
- Noisy matrix completion: understanding statistical guarantees for convex relaxation via nonconvex optimization
- scientific article; zbMATH DE number 7415120 (Why is no real title available?)
- The factor-Lasso and \(k\)-step bootstrap approach for inference in high-dimensional economic applications
- Editors' introduction
- Are bond returns predictable with real-time macro data?
- Generalized Factor Model for Ultra-High Dimensional Correlated Variables with Mixed Types
- Sparse online principal component analysis for parameter estimation in factor model
- Optimal discriminant analysis in high-dimensional latent factor models
- Inferential theory for generalized dynamic factor models
- Power enhancement for testing multi-factor asset pricing models via Fisher's method
- THE LOW-VOLATILITY ANOMALY AND THE ADAPTIVE MULTI-FACTOR MODEL
- Posterior consistency of factor dimensionality in high-dimensional sparse factor models
- Are Latent Factor Regression and Sparse Regression Adequate?
- Nonparametric Estimation and Conformal Inference of the Sufficient Forecasting With a Diverging Number of Factors
- Homogeneity and Structure Identification in Semiparametric Factor Models
- Targeting Predictors Via Partial Distance Correlation With Applications to Financial Forecasting
- Supervised structural learning of semiparametric regression on high-dimensional correlated covariates with applications to eQTL studies
- Dimension Reduction for Fréchet Regression
- High-dimensional overdispersed generalized factor model with application to single-cell sequencing data analysis
- Component-based regression for hybrid data
- A unified generalization of the inverse regression methods via column selection
- Inference for time-varying factor models under local stationarity
- Sparse kernel sufficient dimension reduction
- Probabilistic exponential family inverse regression and its applications
- Integrative factor-adjusted sparse generalized linear models
- SFQRA: scaled factor-augmented quantile regression with aggregation in conditional mean forecasting
- Some theory about efficient dimension reduction regarding the interaction between two responses
- A Bayesian sparse factor model with adaptive posterior concentration
- Matrix-Factor-Augmented Regression
- High-dimensional inference for single-index models with latent factors
- Estimation of the number of factors for high-dimensional data with missing values
- sufficientForecasting
This page was built for publication: Sufficient forecasting using factor models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q75240)
