Grey incidence model for relationship between indicators of panel data and its application

An innovative grey indicator incidence model based on the panel data is presented for the inconsistency of grey relation order resulting from order changing of objects in the grey incidence model of the current panel data. For the difference between the time dimension and the object dimension of panel data, increment and deviation are introduced to respectively represent the development level of the indicator in the time dimension and distribution characteristics of the indicator in the object dimension. This paper also introduces the difference in directions between the above two dimensions to be a judgement standard of positive and negative incidence, and builds an incidence coefficient of the time dimension and object dimension. Moreover, the grey indicator incidence model of panel data is built, and the uniqueness, symmetry and comparability of the model is verified. As a result, the model is applied to the incidence analysis between air quality and concentration of main pollutant for five cities in South-Jiangsu province, verifying that the degree of grey indicator incidence is not related to the objects' order, and indicating the positive and negative incidence between indicators. © 2019, Editorial Office of Control and Decision. All right reserved.