National Accounts- Quarterlies March 2023 Data Collection

Gross domestic product: March 2023 quarter – changes and data updates Introduction Gross domestic product (GDP) sources and methods are thoroughly documented (see: Quarterly gross domestic product: Sources and methods (second edition), with a further update in Quarterly gross domestic product: Sources and methods (fifth edition). Overview of sources and methods for quarterly gross domestic product: Updates and COVID-19 adjustments provides a summary of the sources and methods and also includes information about where we have used alternative indicators to better capture the impacts of COVID-19 on economic activity. The quarterly indicators used when compiling our estimate of GDP are the best that we have available at that point in time. We usually face trade-offs between timeliness and the quality, coverage, length of historical series, and/or conceptual alignment of available data sources to the component it is meant to represent. As a result, the methodologies that we use vary depending on the data available and are underpinned by certain assumptions. In normal periods of activity, these assumptions provide us with reasonable estimates of activity. In periods of abrupt disruption (such as the COVID-19 alert level 4 lockdowns) some of these relationships have weakened or no longer hold. Changes made due to COVID-19 We’ve continued to review and refine approaches applied in each of the quarters from March 2020 to March 2023 by confronting our usual quarterly indicators against other data sources to identify instances where our usual quarterly indicators were unable to represent the actual level of activity through the quarter. Where necessary, we have again used alternative indicators to ensure the effects of the COVID pandemic and related restrictions on activity are appropriately measured. This includes appropriately measuring activity during the easing of such restrictions. For some components we are still using alternative indicators rather than our usual method. We will only return to our usual method for a component when doing so does not introduce an artificial level shift in the series. Overview of sources and methods for quarterly gross domestic product: Updates and COVID-19 adjustments is an updated guide to the concepts and methods we are using to compile gross domestic product (GDP). Seasonal adjustment additive outlier treatment Sharp changes in activity pose challenges for our usual seasonal adjustment processes. Over recent periods, we have applied additive outlier treatment to our headline GDP estimates, as well as to those industries and components with major impacts from border closures or domestic COVID-19 restrictions. This has had the effect of subduing the impact of unusual data points on the seasonal adjustment process. As a result, the seasonally adjusted results during the COVID-19 pandemic largely reflected the level of economic activity relative to the usual seasonality prior to the pandemic. The irregular impacts of COVID-19 largely finished in the June 2022 quarter. However, in some cases, multiple quarters of unaffected activity may need to be seen before the seasonal adjustment algorithm can appropriately interpret new data. Before publishing estimates of December 2022 quarter GDP, we carried out testing on a range of hypothetical outcomes for future quarters and stopped additive outlier treatment for each series where we were confident there is sufficient data for seasonal adjustment to perform better without additive outliers. This testing showed that for the majority of affected series we should stop applying additive outliers in the September 2022 quarter, allowing data points from September 2022 onwards to contribute to the seasonal adjustment process. These recommendations were implemented in Gross domestic product: December 2022 quarter. After March 2023 quarter input data was finalised, we repeated this testing. As a result, we have removed additive outliers from September 2022 onwards for the following series: total exports of goods and services (current and constant price) total imports of goods and services (current and constant price). Additionally, we have made a change to additive outlier treatment of gross national expenditure (current and constant price) in order to align with the treatment of gross domestic product (expenditure measure). This change is intended to improve the coherence between seasonally adjusted series. We expect to undertake further review of the seasonal adjustment and additive outlier settings before future releases, particularly for the June 2023 quarter release when we will have a full year of data available following the end of COVID-19 related disruptions and associated response measures. At this stage, there are limited data points from September 2022 onwards that are contributing to the seasonal adjustment. These points are quite influential in the decomposition into trend, seasonal and irregular components. As additional data points are added in future quarters, we expect greater-than-usual revisions to seasonal factors. This will result in further updates to the seasonally adjusted growth rates from prior to COVID-19 through to the latest quarters. Over time, the estimation of trend and seasonality will stabilise as post-COVID patterns become more established. For a small number of component series, the testing results indicate that we should continue to apply additive outliers in all quarters, for the time being. These series include: value added for the Retail trade sub-industry imports and exports of services, travel services and transport services (in current and constant prices). For these series there are level shifts apparent that may require more complex modelling in the seasonal adjustment process, or more data points available to have confidence in the impact of changing additive outlier settings on the separation of trend, seasonal and irregular components for recent quarters. For the impacted imports and exports series, we continue to retain identical additive outlier treatment between equivalent Gross Domestic Product and Balance of Payments series. Note that we have been able to change our additive outlier treatment for the total exports and imports of goods and services series as the level shifts are not significant at that level of aggregation. This difference in the seasonal adjustment settings at different levels of exports and imports affects the ability to reconcile between the totals and their components. However, we are maximising the accuracy of seasonally adjusted estimates of total exports and imports of goods and services, along with removing a potential source of incoherence between them and total gross domestic expenditure. Incorporating updated Business Financial Data (BFD) Updates due to correction to Wholesale Trade Survey There is an update to gross fixed capital formation of plant, machinery and equipment (PME) due to corrected respondent data in the Wholesale Trade Survey (WTS). This affects the December 2022 quarter. In the December 2022 quarter we had made an adjustment to inventories to reflect the updated WTS. Due to an oversight this adjustment was not applied at the time to PME, which also uses WTS inventories as input data. Incorporating annual agricultural production statistics We incorporated data from Agricultural production statistics: Year to June 2022 (final). The data replaced earlier published data and modelled stock levels. Incorporating the data led to updates to agricultural activity in GDP, and to agricultural inventories in the expenditure measure of GDP. These changes caused updates from the June 2020 quarter onwards. Incorporating updated QBAS data The Quarterly Building Activity Survey (QBAS) has updated data from September 2022 quarter onwards. This has caused changes to both construction and gross fixed capital formation over the same time period. Please see Value of building work put in place: June 2022 quarter for more information. Incorporating updated International Trade data The International Trade has updated data for December 2022. This has caused changes to Imports. Please see International Trade: March 2023 quarter for more information. Changes due to updated indicator data Changes to Gross Fixed Capital Formation – Other Construction We have made improvements via timing adjustments to the data used in measuring rail infrastructure construction. This has caused updates from June 2020 onwards. Changes due to updated respondent information and other source data We received updated respondent information and other source data, causing updates to: Mining – updated MBIE data Manufacturing – updated BFD data Electricity, gas, water and waste services – new and updated Linked Employer-Employee Data (LEED) Retail and accommodation – updated Retail Trade Survey data Information, media, and telecommunications – updated administrative data from Inland Revenue Department Finance and insurance – updated FISIM data, updated Insurance Data Rental, hiring, and real estate services – updated QVNZ data, updated FISIM data Public administration and safety, local government – updated QLAS data Central government administration, defence, and public safety – updated EMS and other input data Central Government final consumption expenditure – updated SABIKS data Local government final consumption expenditure – updated QLAS data Gross fixed capital formation – Non-residential buildings, Residential buildings – updated QVNZ data, Household consumption expenditure – miscellaneous goods and services – updated FISIM data Household consumption expenditure – communications - updated administrative data from Inland Revenue Department Imports and exports – updated FISIM data Unallocated taxes – flow-through from updates to household consumption expenditure Updates to inventories Updates were also made during the process of reconciling change in inventories with other movements in production and expenditure series. This process is designed to minimise inconsistencies in timing and valuation. Updates in applying alternative indicators There have been minor updates to components which use the BFD collection that are not due to the BFD revising, but instead due to other improvements in the processing of BFD data to form our alternative indicators. This has contributed to updates in: Fishing, aquaculture, and agriculture, forestry and fishing support services Construction Transport, postal and warehousing Professional, scientific, technical, administrative and support Services Health care and social assistance Arts, recreation and other services Household consumption expenditure Gross fixed capital formation of intangibles There are updates to the source data used in the composite Household Labour Force Survey – Business Employment Data alternative indicators, causing updates to the following components: Public administration and safety Arts, recreation and other services Revisions table The following table shows previously published and revised quarterly movements for the March 2017 – December 2022 quarters’ GDP and expenditure on GDP (GDE). There were also some changes to earlier quarters, but these were less material. Previously published and updated quarterly movements Gross domestic product Gross domestic expenditure Percentage change from previous quarter Quarter Previously published Updated 15 June 2023 Previously published Updated 15 June 2023 March 2017 1.1 1.1 1.2 1.3 June 2017 1.0 1.0 1.4 1.4 September 2017 0.8 0.7 1.0 0.9 December 2017 1.0 1.0 1.3 1.3 March 2018 0.8 0.8 0.8 1.0 June 2018 1.2 1.2 1.4 1.3 September 2018 0.1 0.0 -0.1 -0.3 December 2018 1.5 1.5 1.7 1.7 March 2019 0.6 0.7 0.6 1.0 June 2019 0.5 0.5 0.6 0.4 September 2019 0.8 0.7 0.8 0.6 December 2019 0.8 0.7 0.5 0.6 March 2020 -1.1 -0.9 -1.3 -0.8 June 2020 -10.3 -10.3 -9.7 -10.0 September 2020 13.9 13.7 14.3 14.0 December 2020 0.0 -0.1 0.1 0.1 March 2021 2.0 2.3 1.5 2.2 June 2021 2.1 1.9 2.5 1.8 September 2021 -4.1 -4.2 -4.5 -4.6 December 2021 3.5 3.5 3.1 3.0 March 2022 -0.5 0.1 -0.6 0.4 June 2022 1.6 1.5 1.9 1.4 September 2022 1.7 1.4 1.9 1.5 December 2022 -0.6 -0.7 -0.8 -0.9 en-NZ