Econometric Modelling Based on Dynamic Count Regression and China Power Supply Dataset

• Published in: Mathematical problems in engineering Vol. 2022; pp. 1 - 5
• Main Authors: Yan, Yixin, Hu, Jiliang, Chen, Xiding, Kumar, A. P. Senthil
• Format: Journal Article
• Language: English
• Published: New York Hindawi 28.05.2022; Hindawi Limited
• Subjects: Autoregressive models; Consumption; Counting; Decision making; Econometrics; Economic analysis; Economic models; Electricity distribution; Empirical analysis; Expected values; Generalized linear models; Mathematical problems; Power supply; Random variables; Regression analysis; Regression models; Time series; China
• ISSN: 1024-123X; 1563-5147
• DOI: 10.1155/2022/6864015

Traditionally, economic data of power supply is often analyzed through the count regression model due to the type of empirical data in the decision-making process. However, in reality, it is difficult to use count data model for data with autoregressive features. The main reason is that the time series features and autoregressive attributes cannot be controlled through the count regression model, which violates the assumptions set by the model. Therefore, there may be errors in the empirical analysis results. This letter firstly describes the characteristic of the count regression model and the problem, and then we refine the multiplicative autoregressive count model for dynamic count data. The model has desirable theoretical properties and is trivial to incorporate into existing models for the count data. In this study, the multiplicative autoregressive counting model for dynamic counting data is improved. The model has ideal theoretical properties and can be easily incorporated into existing economic models of counting data, especially for power supply policy analyses.