Page 225 - Contributed Paper Session (CPS) - Volume 8

CPS2256 Norzarita Samsudin
Graph 2: Impulse Response Function: Response on Real GDP

Source: Author’s computation
Note. X is sales value of retail trade; Y is real GDP.

4.5 Variance Decomposition
In Variance Decomposition study, ten quarters period were selected. This
study enabled us to forecast ten quarter ahead on the variance decomposition
of real GDP and sales value of retail trade of Malaysia.
Variance Decomposition of real GDP (Table 6). In short run (period 1),
almost 100 per cent of forecast error variance in real GDP is explained by real
GDP itself. The contribution of retail sales is very small. This implies very weak
influence of this variable in the future. In the long run, the influence of GDP on
itself is still very strong, while contribution of retail sales almost no change.

Table 6: Variance Decomposition of Real GDP
Period S.E. X Y
1 1245.553 1.10E-05 99.99999
5 2863.124 0.155249 99.84475
10 4172.925 0.346001 99.65400
Source: Author’s computation
Note. X is sales value of retail trade; Y is real GDP.

Variance Decomposition of retail trade sales (Table 7). In short run (period
1), almost 100% of forecast error variance in retail sales is explained by retail
sales itself. In the long run, the influence of sales value of retail trade on itself
is gradually decreasing, while contribution of GDP increases to approximately
ten per cent in period ten. This implies real GDP will influence retail trade sales
in the future.

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