Application And Research Of Time Series Analysis In China’s Consumer Price Index

The consumer price index is an index generally prepared by the countries in the world, it can be used to analyze the basic dynamics of the market price, is an important basis for the government to formulate the price policy and wage policy.In order to accurately grasp the trend of changes in the consumer price index, we establish a model to predict China’s consumer price index data by the method of time series analysis.Time series analysis is one of the most important tools for economy research, which describes the variation of data with time, and used to forecast economic data. However, due to the market and the state policy factor, economic data will often show the randomness. The traditional linear time series analysis will not be able to reflect the intrinsic characteristics of the economic data. In recent years, the emergence of nonlinear and non-parametric time series analysis method is precisely to make up for this shortcoming, it is widely used in the economic field, especially in the financial market. Readers are referred to Tong(1990) and Priestley(1988) for details on nonlinear time series analysis. Tj(?)stheim(1994) gives an excellent review on recent developments in nonlinear time series analysis.Firstly, we introduce the notions and characters of the stationary time series and the time series analysis methods, as well as some commonly used time series models. Secondly, we introduce the modeling theory of the linear auto-regressive modei and the non-parametric regression model, including data preprocessing before modeling, model identification, parameter estimation and model prediction. Then, we establish the linear auto-regressive model and the non-parametric regression model on the data of China’s consumer price index in2004-2009, and the OLS estimation, the orthogonal sequence estimation and spline estimation were used to fit and predict respectively. Finally, compared the simulated and predicted results, the result show that the nonparametric auto-regressive model is superior to the linear auto-regressive model, and it is better in reflecting the nonlinear characteristics of China’s consumer price index.