Finite mixture model: a comparison method for nonlinear time series data

摘要

Global Financial Crisis 2009 caused the finance collapse in Asia countries. The crisis leads to the economic and financial time series confronted with structural changes or jumps during the time. Stock price and exchange rate play a crucial role as symbol of development for a country's economy. Hence, it is critical to investigate the relationship between these two variables. A two-component finite mixture model is used to examine this issue. In spite of that, maximum likelihood estimation and Bayesian method are applied to fit the finite mixture model. Additionally, this paper concerns on investigating the developing Asian countries since they are easily affected by economic changes of the western countries. In relation to the results, there is a positive relation between the exchange rate and stock price for Malaysia, Thailand, Philippines and Indonesia. Also, this paper highlighted that Bayesian method is superior to maximum likelihood in modelling nonlinear time series data although both methods provided roughly equal results.