Page 247 - Contributed Paper Session (CPS) - Volume 7

CPS2075 Wan Siti Zaleha W. Z. et al.
Results of Unrestricted Cointegration Rank Test (Maximum
Eigenvalue)
None 0.0401 13.2401 14.2646 0.0721
At most 1 0.0083 2.6974 3.8415 0.1005
Max-eigenvalue test indicates no cointegration at the 0.05 level
* denotes rejection of the hypothesis at the 0.05 level
**MacKinnon-Haug-Michelis (1999) p-values
According to Table 3.2.2, Trace test and Maximum Eigenvalue test
indicates no co‐integration between CPI & exports. Thus, this study find
that there is no long run relationship between CPI & imports and CPI &
exports.
Table 3.2.2: Cointegration Test Between CPI & Exports
Hypothesized Trace 0.05 Critical
No. of CE(s) Eigenvalue Statistic Value Prob.**
Results of Unrestricted Cointegration Rank Test (Trace)
None * 0.0359 11.8238 15.4947 0.1656
At most 1 5.55E-05 0.0180 3.8415 0.8934
Trace test indicates no cointegration at the 0.05 level
* denotes rejection of the hypothesis at the 0.05 level
**MacKinnon-Haug-Michelis (1999) p-values
Results of Unrestricted Cointegration Rank Test (Maximum Eigenvalue)
None * 0.0359 11.8059 14.2646 0.1181
At most 1 5.55E-05 0.0179 3.8415 0.8934
Max-eigenvalue test indicates no cointegration at the 0.05 level
* denotes rejection of the hypothesis at the 0.05 level
**MacKinnon-Haug-Michelis (1999) p-values
3.3. Causality Test under the Multivariate Vector Autoregressive
Model (VAR) Framework
The co-integration test defined the non-existence of the long-run
relationship between CPI, imports & exports. In order to define the
direction of Granger causality among the variables, a regression model
with Vector Autoregressive Model (VAR) should be established. The
estimation of VAR requires selection of a suitable lag length. The number
of lags in the model is determined accordingly based on the smallest
Akaike Information Criterion (AIC). The smallest AIC for this study is lag
12 for CPI & imports and CPI & exports. The VAR equations are as follows:

234 | I S I W S C 2 0 1 9