Table 4

Enders–Siklos tests with TAR and M-TAR adjustments (Daily data)

Variables in the co-integrating relationshipCo-integration test statistics
Dependent variableIndependent variablestmaxΦ
A. TAR adjustment
lcamlindo lmalay lphi lsing lthai lviet−2.27***7.94***
lindolcam lmalay lphi lsing lthai lviet−3.38***14.85***
lmalaylcam lindo lphi lsing lthai lviet−3.46***11.90***
lphilcam lindo lmalay lsing lthai lviet−3.83***14.85***
lsinglcam lindo lmalay lphi lthai lviet−3.46***11.90***
lthailcam lindo lmalay lphi lsing lviet−3.83***14.45***
lvietlcam lindo lmalay lphi lsing lthai−3.84***14.20***
B. M-TAR adjustment
lcamlindo lmalay lphi lsing lthai lviet−1.75***8.76***
lindolcam lmalay lphi lsing lthai lviet−3.70***14.78***
lmalaylcam lindo lphi lsing lthai lviet−3.35***11.87***
lphilcam lindo lmalay lsing lthai lviet−3.70***13.78***
lsinglcam lindo lmalay lphi lthai lviet−3.35***11.87***
lthailcam lindo lmalay lphi lsing lviet−3.63 ***14.41***
lvietlcam lindo lmalay lphi lsing lthai−3.35***12.87***

Note(s): The lag used for each test is determined using the general-to-specific method (Ng and Perron, 1995) with a maximum lag order of 8 allowed. The null hypothesis under test is no co-integration. Panels A and B present results based on distributions of critical values with adjustments for the TAR and M-TAR categories, respectively. Approximate critical values for the tmax and Φ tests are taken from Tables 5 and 6 in Enders and Siklos (2001). Statistical significance is indicated by triple asterisks (***) for the 1% level

or Create an Account

Close Modal
Close Modal