Time-varying forecast combination for high-dimensional data
From MaRDI portal
Abstract: In this paper, we propose a new nonparametric estimator of time-varying forecast combination weights. When the number of individual forecasts is small, we study the asymptotic properties of the local linear estimator. When the number of candidate forecasts exceeds or diverges with the sample size, we consider penalized local linear estimation with the group SCAD penalty. We show that the estimator exhibits the oracle property and correctly selects relevant forecasts with probability approaching one. Simulations indicate that the proposed estimators outperform existing combination schemes when structural changes exist. Two empirical studies on inflation forecasting and equity premium prediction highlight the merits of our approach relative to other popular methods.
Cites work
- \(\ell_1\)-regularization of high-dimensional time-series models with non-Gaussian and heteroskedastic errors
- A Reality Check for Data Snooping
- Asymptotic behavior of bandwidth selected by the cross-validation method for local polynomial fitting
- Complete subset regressions
- Complete subset regressions with large-dimensional sets of predictors
- Determining the Number of Factors in Approximate Factor Models
- Forecasting Using Principal Components From a Large Number of Predictors
- Forecasting using random subspace methods
- Functional index coefficient models with variable selection
- High-dimensional Linear Regression for Dependent Data with Applications to Nowcasting
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- Inference of time-varying regression models
- Least squares after model selection in high-dimensional sparse models
- Model Selection and Estimation in Regression with Grouped Variables
- Model selection and structure specification in ultra-high dimensional generalised semi-varying coefficient models
- Modeling and testing smooth structural changes with endogenous regressors
- Nearly unbiased variable selection under minimax concave penalty
- Nonconcave penalized likelihood with a diverging number of parameters.
- Nonparametric estimation of time varying parameters under shape restrictions
- Nonparametric regression for locally stationary time series
- Non‐parametric detection and estimation of structural change
- One-step sparse estimates in nonconcave penalized likelihood models
- Optimal bandwidth selection in nonparametric regression function estimation
- Oracle inequalities for high dimensional vector autoregressions
- Persistence in forecasting performance and conditional combination strategies
- Random forests
- Risk consistency of cross-validation with Lasso-type procedures
- Shrinkage estimation of the varying coefficient model
- Shrinkage tuning parameter selection with a diverging number of parameters
- Simultaneous analysis of Lasso and Dantzig selector
- Strong oracle optimality of folded concave penalized estimation
- Testing for smooth structural changes in time series models via nonparametric regression
- The Adaptive Lasso and Its Oracle Properties
- Towards a general theory for nonlinear locally stationary processes
- Trending time-varying coefficient time series models with serially correlated errors
- Variable selection and estimation in high-dimensional varying-coefficient models
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
Cited in
(9)- Data-Driven Time Parallelism via Forecasting
- Estimation of high-dimensional dynamic conditional precision matrices with an application to forecast combination
- Multivariate Postprocessing Methods for High-Dimensional Seasonal Weather Forecasts
- Time-varying forecast combination for factor-augmented regressions with smooth structural changes
- Quantile prediction with factor-augmented regression: structural instability and model uncertainty
- Local Predictability in High Dimensions
- Loss given default model for online microloans using neural network based quantile model
- Model averaging for time-varying vector autoregressions
- Consistent nonparametric test for structural change in time series models via Cusum and Fourier transform
This page was built for publication: Time-varying forecast combination for high-dimensional data
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6090590)
