The aim of the study is nonlinearity test of ISE – 100 returns. The most usedly nonlinearity test of BDS test is applied. Data is obtained from the Central Bank of Turkey. Return data is calculated by the difference of natural logarthim of daily closing value. The data has 4352 observations, between the data of 02.01.1989 and 04.07.2006. BDS test is done on the four different error term. Before the ARMA process to make the BDS test days are used as a dummies and error term is obtained by regression. Second data set is ARMA process is done and error term is obtained and then BDS test is applied. Third data set is logarithm of the squared standardized residuals of GARCH (1,1) process. Fourth data set is logarithm of the squared standardized residuals of AR (1) - GARCH (1,1) process. First, second and fourth data sets reject the null hypothesis that means there exist a nonlinear relation. Third data set fail to reject the null hypothesis of iid, for some embedding dimension, that means GARCH (1,1) process removes most of the nonlinearity.
Download Info
To download:
If you experience problems downloading a file, check if you have the
proper application to
view it first. Information about this may be contained
in the File-Format links below. In case of further problems read
the IDEAS help
page. Note that these files are not on the IDEAS
site. Please be patient as the files may be large.