Page 372 - Contributed Paper Session (CPS) - Volume 2

CPS1888 Chen C. et al.
expansion was provided by a significant development in NA to create a
quarterly income measure of GDP (GDPI).
New variables and wider industry coverage were needed to support the
development. Instead of creating a separate collection, we extended our
quarterly managed collection of large and complex businesses to additional
industries in the economy. For the remaining business population, we
investigated the use of GST sales and purchases in combination with salaries
and wages from the Employee Monthly Schedule (EMS) administrative data to
derive estimates for new variables. EMS is a monthly payroll return covering
all employees, capturing taxable and non-taxable earnings.
With the existing methods and systems, we created a new experimental
Business Data Collection. The expanded collection provides additional
quarterly financial indictors including purchases, salaries and wages, and
profit. It also covers most industries in New Zealand’s economy. At the stage,
we are working on officially publishing the collection in 2019 and the data will
feed into NA’s new GDPI measures in 2020.

3.3 Creating new statistical insights
The comprehensive coverage of the GST data has allowed us to produce
estimates at lower levels of detail, therefore delivering new statistical insights
to our customers.
For example, a major earthquake occurred in November 2016 on the
upper east coast of New Zealand’s South Island, centred near the town of
Kaikoura. The earthquake caused damage to many roads on the east coast
of the South Island – isolating the Kaikoura area highlighted in Figure 3 and
lowering their retail activity. However, traffic volumes increased on
alternative routes through the centre of the South Island resulting in
improved sales for businesses in these areas.
Stats NZ produced a map of the affected region, showing retail and
tourism-related sales increases and decreases for small urban areas (e.g.
towns). This analysis would be difficult with a sample-based survey deign, as
a limited sample of businesses drawn at national level would not provide
enough information for us to make statistical inferences for such a small
geographic area.

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