KUTLAR, Aziz Sakarya Üniversitesi - İktisadi ve İdari Bilimler Fakültesi - İktisat Bölümü, Turkey , TORUN, Pınar Sakarya Üniversitesi - İktisadi ve İdari Bilimler Fakültesi - İktisat Bölümü, Turkey

SELECTING AN APPROPRIATE GENERALIZED CONDITIONAL HETEROSCEDASTIC MODEL FOR THE DAILY ISE 100 INDEX RETURNS

16851

The objective of this study is to determine the causality relationship between the variables of revenue and uncertainty by using the most appropriate variance model for ISE National 100 Index with the data from 01.Nov.2002 to 08.Aug.2012. This study consists of two main parts. In the first one, TGARCH Model is determined as the most appropriate model ISE National 100 Index by using symmetric and asymmetric GARCH models. In the second part, the causality relationship between the return and risk is analysed as the variances are regarded as the measure of risk which is the variance values obtained from TGARCH Model (1,1). It is concluded that bad news have stronger effects on fluctuations and the returns variable is the Granger cause of the variance variable.

1

Risk , Returns , Heterocadasticity , Granger Causality

Erciyes University Journal Of Economics an‎d Administrative Sciences

24