dLagM

dLagM implements distributed lag models and autoregressive distributed lag (ARDL) bounds testing to model delayed effects of independent variables on dependent variables and to assess short-term dynamics and long-term equilibrium (cointegration) relationships in time series data.

Key Features:

• Model Implementation: Supports finite linear, polynomial, Koyck, and ARDL distributed lag model specifications.
• ARDL Bounds Testing: Provides functions for ARDL bounds testing to assess cointegration and long-term relationships between time series variables.
• Innovative Search Algorithm: Implements a search algorithm to specify ARDL orders for bounds testing, improving model selection efficiency and accuracy.
• Benchmarking Capabilities: Has been benchmarked against mainstream software tools for implementing distributed lag models and ARDLs.

Scientific Applications:

• Econometrics: Analyze economic indicators and forecast future trends by quantifying short- and long-term relationships.
• Environmental science: Study environmental changes and quantify their long-term impacts on ecosystems using temporal dependency models.
• Epidemiology: Investigate disease spread patterns and evaluate effects of public health interventions over time.
• Bioinformatics: Explore gene expression dynamics and other temporal biological processes through distributed lag and ARDL analyses.

Methodology:

Uses distributed lag models (finite linear, polynomial, Koyck) and autoregressive distributed lag (ARDL) bounds testing to model delayed effects, examine short-run dynamics and long-term (cointegration) relationships, and employs a search algorithm to specify ARDL orders.