Page 369 - Contributed Paper Session (CPS) - Volume 2
P. 369
CPS1888 Chen C. et al.
distribution of the two-monthly data, in the same industry, over the
same reporting period.
∑
̂ = ∗ =1 , 0
, 0
∑ + ∑ + ∑
=1 , 0 =1 , −1 =1 , −2
Where
= ℎ
= ℎ {1, … , } ℎ ℎ ℎ
ℎ
= {1, … , }, ℎ ℎ ℎ
ℎ
0 = ℎ ℎ ℎ ℎ 2 ℎ ℎ ℎ ℎ
−1 = ℎ ℎ 0; −2 = ℎ ℎ 1
Secondly, where GST data has not yet been received, we forwardcast the two-
monthly equivalent GST values using the corresponding movements derived
from the simple two-monthly filers, until the reference quarter in which the
two monthly filers have filed their GST returns.
̂ ℎ 2 3 ℎ ℎ
, 0
̂ = { ̂ , 0 (1 + ∆ ) ℎ 1 ℎ ℎ 1 ℎ
1
2
̂ (1 + ∆ ) (1 + ∆ ) 2 3 ℎ ℎ
, 0 1 2
Where
∆ =
1 = ℎ ℎ 0
2 = ℎ ℎ 1
Then we apply the modelling ratio, which have already been derived for
transforming two-month filers to obtain the estimated quarter GST value of
the six-monthly filer of interests. The six-monthly data has been through
several data manipulations, therefore evaluating the quality of the estimates
is complicated. However, as the contribution of six-monthly filers subject to
this method is generally very small, the estimates do not have material impact
at output level.
Combined sources approach - The combined sources approach uses the
GST data in conjunction with data from other sources (either administrative or
358 | I S I W S C 2 0 1 9
