Back close

Modeling of Multivariate Systems using Vector Autoregression(VAR)

Publication Type : Conference Proceedings

Publisher : i-PACT

Source : 2019 Innovations in Power and Advanced Computing Technologies, i-PACT 2019, 2019.

Url : https://ieeexplore.ieee.org/document/8960145

Campus : Bengaluru

School : School of Engineering

Department : Electronics and Communication

Year : 2019

Abstract : This study revolves around a group of variables which are coming under a single system. The multivariate systems are a group of individual components which works independently but makes the system as a whole. These variables tend to have an effect on the growth of each other within the system. This paper explores the relationship between such systems by developing a mathematical model. A Vector Autoregression (VAR) model is developed for a multivariate system, to analyze the relationship between the systems in the long and short run. The model is then used for forecasting the system. Using the Impulse Response analysis, a conclusion between the interactions of the variables is found. In the long term, the variables tend to be independent of the other variables as they become more stable. In short term, the variables have a dependence within them.

Cite this Research Publication : Harivigneshwar, C. J., Dharmavenkatesan, K. B., Ajith, R., Jeyanthi, R., “Modeling of Multivariate Systems using Vector Autoregression(VAR)”, 2019 Innovations in Power and Advanced Computing Technologies, i-PACT 2019, 2019.

Admissions Apply Now