FORECASTING STOCK PRICE INDEX USING BAYESIAN COMBINATION APPLIES IN INDONESIA STOCK EXCHANGE (IDX) JULY 1st 1997 - FEBRUARY 17th 2012

Khieng, Channa (2012) FORECASTING STOCK PRICE INDEX USING BAYESIAN COMBINATION APPLIES IN INDONESIA STOCK EXCHANGE (IDX) JULY 1st 1997 - FEBRUARY 17th 2012. S2 thesis, UAJY.

	Text (Halaman Judul) 0MM01418.pdf Download (300kB)
	Text (Bab I) 1MM01418.pdf Download (309kB)
	Text (Bab II) 2MM01418.pdf Download (643kB)
	Text (Bab III) 3MM01418.pdf Restricted to Registered users only Download (261kB)
	Text (Bab IV) 4MM01418.pdf Restricted to Registered users only Download (494kB)
	Text (Bab V) 5MM01418.pdf Download (1MB)

Abstract

Forecasting of stock price index is measuring the level of stock prices; in addition, its practical application is to compare values at different points in time. Using Bayesian combination in this paper, it is a mixture approach to forecast based on a distribution state planetary of predictive models. We use Bayesian Model Averaging (BMA) to forecast real-time measures of stock price index, employing a large number of real and financial indicators. This aim of this study is to analyze forecasting stock price index in Indonesia Stock Exchange (IDX) index. Moreover, the forecasted time series data is an important issue in finance. It can put forward an up-to-date review of approximation approaches available for the Bayesian implication of Generalized Autoregressive Conditional Hereroskedasticity (GARCH) models. They may be important nonlinearities, asymmetries, and long memory properties in the volatility process. We will introduce GARCH models that give the alternative volatility forecasting models. They can involve that constant updating of parameter estimates. We will explain how to measure and model volatility is an important issue in finance. BMA can give us good reason to improve forecasting when we change away from linear models and average over requirement let GARCH effects in the modernizations to log-volatility. Therefore, BMA consistently dispenses a high posterior weight to models that infer of GARCH models.

Actions (login required)

View Item