Dissertation
Dissertation > Economic > Economic planning and management > Economic calculation, economic and mathematical methods > Economic and mathematical methods

The Research of Markov Switching Cointegration Model

Author WangZuoZuo
Tutor ChenHuaYou
School Anhui University
Course Basic mathematics
Keywords Time series Cointegration Vector Error Correction Model Bayesian estimation Gibbs sampling
CLC F224
Type Master's thesis
Year 2011
Downloads 67
Quotes 0
Download Dissertation

The existence of price adjustment transaction costs and the sudden change of economic policy in real economy makes the long-term equilibrium relationship between variables not often occur in every period. Based on this, Markov Switching Vector Error Correction Model is more suited to describe this long-term equilibri-um relationship of real economies.So, it has been increasingly widely used in the economic fields. But, most scholars use maximum likelihood estimation method to estimation the model. Because the model is complex, the maximum likelihood estimation is correspondingly time-consuming, and the accuracy of the estimation is not too high. Bayesian estimation combine with the data and the the prior distri-bution information of parameters,and can do simple processing for missing data, censored data, so relative to the maximum likelihood estimation method Bayesian estimation has an unparalleled advantage.so we try the Bayesian method through Gibbs sampling in this article to estimate the parameters. The main content of this paper is as follows:(ⅰ) In Chapter 1, we first briefly introduce the definition of cointegration, in-troduces Vector error correction model and the improved model Markov Switching Vector Error Correction Model, and look back the backgrounds, the application and research progresses of some questions on Markov Switching Vector Error Correc-tion Model that we study.(ⅱ) In Chapter 2, we study Markov Switching Vector Error Correction Mod-el, and try the Bayesian method through Gibbs sampling to estimate the unknown parameters of model, and give the specific step to estimate parameters. (ⅲ) In Chapter 3, we confirm the estimation is valid by simulating random numbers using statistical software.

Related Dissertations
More Dissertations