dLagM: An R package for distributed lag models and ARDL bounds testing

Area of Science:

• Econometrics
• Time Series Analysis
• Statistical Software

Background:

• Distributed lag models and autoregressive distributed lag (ARDL) models are crucial for analyzing time series data.
• Exploring short and long-run relationships in time series requires robust modeling techniques.
• Existing software may lack comprehensive features for implementing various distributed lag models and ARDL bounds testing.

Purpose of the Study:

• Introduce the R package dLagM for implementing distributed lag models and ARDL bounds testing.
• Provide a user-friendly and flexible tool for time series regression and cointegration analysis.
• Propose and implement a new search algorithm for specifying ARDL bounds testing orders.

Main Methods:

• Implementation of finite linear, polynomial, Koyck, and ARDL models within the dLagM package.
• Development and application of a novel search algorithm for ARDL bounds testing order selection.
• Benchmarking dLagM package features against established software for distributed lag and ARDL analysis.

Main Results:

• The dLagM package offers a comprehensive environment for various distributed lag models and ARDL bounds testing.
• A new algorithm for ARDL order specification is successfully implemented and demonstrated.
• The package's performance and features are validated through illustrative datasets and comparative analysis.

Conclusions:

• The dLagM R package provides a valuable and efficient tool for time series econometrics research.
• The novel ARDL order selection algorithm enhances the practical application of cointegration analysis.
• dLagM offers a competitive alternative to existing software for distributed lag and ARDL modeling.