2020/10/15 by William B. Nicholson, Nicholson, William B., Xiaohan Yan +1
Decision Sciences · Mathematics · #Applications (stat.AP) #FOS: Computer and information sciences #Fractional Differential Equations Solutions #Machine Learning (stat.ML) #Methodology (stat.ME) #Probabilistic and Robust Engineering Design #Statistical Methods and Inference
paper · pdf · doi:10.48550/arxiv.2010.07594
openalex publication_date 2020/10/15 · openalex created_date 2020/10/22 · openalex updated_date 2026/07/28
Many recent developments in the high-dimensional statistical time series literature have centered around time-dependent applications that can be adapted to regularized least squares. Of particular interest is the lasso, which both serves to regularize and provide feature selection. The lasso requires the specification of a penalty parameter that determines the degree of sparsity to impose. The most popular penalty parameter selection approaches that respect time dependence are very computationally intensive and are not appropriate for modeling certain classes of time series. We propose enhancing a canonical time series model, the autoregressive model with exogenous variables, with a novel online penalty parameter selection procedure that takes advantage of the sequential nature of time series data to improve both computational performance and forecast accuracy relative to existing methods in both a simulation and empirical application involving macroeconomic indicators.