Page 245 - Contributed Paper Session (CPS) - Volume 7

CPS2075 Wan Siti Zaleha W. Z. et al.
fiscal stimulus; monetary stimulus to the economy; and fast growth in other
countries. Cost-push theory indicates that the inflation occurs when the
producers counter the increasing in costs by raising prices to save guard their
profit margins. Among the factors of cost-push inflation are raising labour
costs, expectation of inflation, higher indirect taxes, a fall in the exchange rates
and monopoly employers/profit push inflation.
As Malaysia is an open economy, the exports and imports play important
roles to the inflation. When demand exceeds the domestically produced
goods and services, the gap becomes larger. This will result in the inflationary
situation. In order to fulfil the demand, the country may import and ease the
inflation. On the contrary, the country may export when the domestic supply
of goods and services surpasses the demand and avoid the deflation. A
depreciation of the exchange rate raises the price of imports and cuts the
foreign price of exports. External trade also can cause inflation by the
competition of local production as compared to imported items.

2. Methodology
2.1. The data
To carry out the study on the relationship of inflation with imports and
exports of goods in Malaysia, the variables involved are the Malaysia’s CPI
to measure inflation; and Malaysia’s merchandise imports & exports. The
study uses the monthly data from January 1990 to December 2017 which
were obtained from the DOSM.
2.2. Unit root test
The variables in the regression model have to be stationary in order to
prove that the standard assumptions for asymptotic analysis are valid. To
investigate the stationarity of the data, a univariate analysis of each of the
time series was carried out by testing for the presence of a unit root. This
study used Augmented Dickey‐Fuller (ADF) test as stationary test. If the
series (level) are non‐stationary, the data should first be transformed into
stationary data (using first (or higher) differences) so that further statistical
analysis can be applied.
2.3. Co-integration test
The co‐integration test identifies the existence of long‐run relationship
between the variables under study. This study used both Johansen’s
Maximum Eigenvalue test and the trace test for investigating co‐
integration of the time series. If the test indicates the absence of co‐
integration relation, the model VAR will be used. If otherwise, the model
VECM will be used.
2.4. Causality test
The causality test investigates link between pairs of variables where it
determines whether one time series is useful in forecasting another time

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