On Selecting Stable Predictors in Time Series Models

2019/05/18 by Avleen S. Bijral, Bijral, Avleen S.
Computer Science · Mathematics · #Anomaly Detection Techniques and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Methodology (stat.ME) #Statistical Methods and Inference #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.1905.07659

openalex publication_date 2019/05/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We extend the feature selection methodology to dependent data and propose a novel time series predictor selection scheme that accommodates statistical dependence in a more typical i.i.d sub-sampling based framework. Furthermore, the machinery of mixing stationary processes allows us to quantify the improvements of our approach over any base predictor selection method (such as lasso) even in a finite sample setting. Using the lasso as a base procedure we demonstrate the applicability of our methods to simulated and several real time series datasets.

Related

• Model selection for weakly dependent time series forecasting
• Model Selection for Time Series Forecasting: Empirical Analysis of\n Different Estimators
• Model combinations through revised base-rates
• Model Selection for Unit-root Time Series with Many Predictors
• On LASSO for Predictive Regression