Based On Dynamic Regression Model An Empirical Study On The Forecast And Analysis Of Gross Regional Product In Hebei Province

Gross domestic product(GDP)not only plays an important role in measuring the level of economic development of a country or region,bust also provides a reference for the deployment of its strategic policies and macroeconomic policies.For Hebei Province,the long-term extensive development of traditional industries leads to the environmental pollution and waste of resources.This situation has become the vital restrictive factors affecting the development of high-quality resources such as culture and tourism,and dragging down the transformation and upgrading of Hebei Province.Therefore,the gross domestic product forecasting is a fundamental part for the optimization of industrial structure and the sustainable development of Hebei Province.Based on the time series analysis,this paper introduces a autoregressive integrated moving average model to predict the GDP of Hebei Province.Considering the impact of many factors on the GDP,the three major industrial added values are selected as input variables.The dynamic regression model was constructed and further optimized by the Akaike Information Criterion and the Schwarz Criterion to predict the GDP of Hebei Province.Through the prediction results,this paper will provide guidance for the optimization of industrial structure and the formulation of macroeconomic policies of Hebei Province.The governing study details of this thesis are shown as follows:Firstly,based on the one-dimensional time series analysis theory,the autoregressive integrated moving average model is constructed by R language software.The pure randomness test,stationarity test,model fitting,parameter estimation and significance test of the GDP of Hebei Province from 1993 to 2016 were carried out.The model was used to predict the GDP of Hebei Province in 2017.The effectiveness of the autoregressive integrated moving average model is further demonstrated by comparing the predicted and actual values of the GDP in Hebei Province in 2017.Secondly,based on the theory of multivariate time series analysis,the three major industrial added value is selected as the input sequence,and the GDP of Hebei Province is used as the response sequence.The dynamic regression model isconstructed by R language software.Taking the total production value of Hebei Province from 1993 to 2016 and the added value of the three major industries as the research object,pure randomness test,stationarity test,model fitting and significance test were carried out.The model is optimized by the Akaike Information Criterion and the Schwarz Criterion.It is demonstrated that the dynamic regression model is better than the summation autoregressive moving average model,and the dynamic regression model with the first industry added value as the input sequence is the most accurate.The three major industrial added value is selected as the input sequence of the dynamic regression model.The purpose is to understand the distribution of the three major industries in Hebei Province and the GDP of the three major industries and Hebei Province through the prediction and analysis of the GDP of Hebei Province.The correlation between them will guide the optimization of industrial structure in Hebei Province,improve the scientific level of government management,and reduce the blindness of decision-making.The research will further improve the application of time series analysis in GDP forecasting,broaden the application scope of dynamic regression model,and provide theoretical basis and decision-making basis for urban industrial structure optimization and macroeconomic formulation.