A0508
Title: High-dimensional vector autoregression with common response and predictor factors
Authors: Xiaoyu Zhang - Tongji University (China) [presenting]
Abstract: The reduced-rank vector autoregressive (VAR) model can be interpreted as a supervised factor model, where two-factor modellings are simultaneously applied to response and predictor spaces. A new model called vector autoregression is introduced, with common response and predictor factors, to explore the common structure between the response and predictors in the VAR framework further. The new model can provide better physical interpretations and improve estimation efficiency. In conjunction with the tensor operation, the model can easily be extended to any finite-order VAR model. A regularization-based method is considered for the high-dimensional estimation with the gradient descent algorithm, and its computational and statistical convergence guarantees are established. For data with pervasive cross-sectional dependence, a transformation for responses is developed to alleviate the diverging eigenvalue effect. Moreover, additional sparsity structure is considered in factor loading for the case of ultra-high dimensions. Simulation experiments confirm the theoretical findings, and a macroeconomic application showcases the appealing properties of the proposed model in structural analysis and forecasting.
