Uncertain panel regression analysis with application to the impact of urbanization on electricity intensity

This study aims to establish uncertain econometrics by exploring uncertain panel regression analysis firstly, and applies it to dealing with an economic issue on electricity intensity and urbanization. A theoretical model of uncertain panel regression analysis is firstly created, and its relevant parameter estimation, residual analysis, forecasting and hypothesis test are further proposed accordingly. Afterwards, the new uncertain panel regression model is empirically applied to examining the impact of urbanization on electricity intensity (EI) among China’s cities. Data are collected from 28 prefecture cities in China from 2006 to 2018. The results reveal that both urbanization (substituted by urban population) and industrial structure (substituted by the proportion of secondary industry and tertiary industry in GDP) have negative effects on EI, but the opening degree of a city (substituted by the proportion of total import and export trade in GDP) has a positive effect on EI. Moreover, forecasting on EI for the 28 cities in 2019 as well as for a new city, Lanzhou, in 2019 are further made finally.