Inverse Gaussian Regression And Bayesian Analysis For The Consumer Price Indices Of China

The aim of this thesis is to model the expected number of the CPI of China for the period (2001-2012) and to identifying the main groups, categories and their subcategories that causing CPI inflation in order to assist the economic policy makers for developing appropriate policies to reduce the CPI inflation.In this study we propose Inverse Gaussian distribution and Bayesian approach to model the distribution of Consumer Price Indices (CPI)of china for the period (2001-2012) in a multi way contingency table. The market basket includes eight main groups of goods and services and in each main group there are categories and subcategories.During the period from2001-2012, the results show that the CPI decreased in2001-2006and2011, while reached highest at2007-2008, and resumed their upward trend in2012, the most important main group that drove CPI inflation were the Food and residence. These two categories account the half proportion of the CPI. The Vegetables; Dried and Fresh Melons and Fruits in Food basket and Fuel (a main component of the Water, Electricity and Fuel price index in the Residence basket and the main component of the Fuel and parts price index in Transportation basket) were the major contributor to the overall increased in the CPI. According to the data that has been analyzed, without food and fuel inflation, there was a minor inflation in China. The non-inclusion of house prices, which is the third pillar after Food and Fuel in causing the inflation, leads CPI to be under the influence of both Food and Fuel, which gives an incomplete picture and distorting for the CPI.