What the Annual Enterprise Survey measures
The Annual Enterprise Survey (AES) provides financial information by industry and sector groups. This includes measures of financial performance and financial position. Output variables include income, expenditure, profit, purchases of fixed assets, and equity. From this data, economic ratios such as the return on assets and profit margin on sales can be derived. The AES data also forms the basis of national accounting variables, such as value-added, gross output, and gross fixed capital formation.
The information contained in the tables in this release is only a sample of the information available. Further information is available on Statistics New Zealand's website (www.stats.govt.nz) or on request.
The target population for AES is all economically significant businesses (see definition below) operating within New Zealand. However, some industries are excluded on pragmatic grounds. In total, AES is estimated to cover approximately 90 percent of New Zealand's gross domestic product (GDP).
The Australian and New Zealand Standard Industrial Classification 2006 (ANZSIC06) industry exclusions are:
- residential property operators (L671100)
- foreign government representation (O755200)
- religious services (S954000)
- private households employing staff and undifferentiated goods- and service-producing activities of households for own use (S960100-300).
Design of the Annual Enterprise Survey
The AES was designed as the principal collection vehicle of data used in the compilation of New Zealand's national accounts. The data collected feeds into the calculation of the economy's GDP, through the current price annual industry accounts, which are compiled within an input-output framework. The AES has experienced significant change in sample design for the 2009 financial year, and notes about these changes are explained in the next section of Technical notes.
The AES collects financial data for most of the industries operating in the New Zealand economy. The AES industries are based on ANZSIC06. The AES survey is designed at approximately the four-digit ANZSIC level, or 113 industries. Data at lower levels can also be produced (subject to confidentiality constraints) but it may have considerably higher sample errors. In addition, limited analysis has been conducted at this level.
The population for the AES 2009 financial year is 453,409 units and consists of:
- 289,864 (63.9 percent) sourced from IR 10 information
- 20,513 (4.5 percent) sourced from the postal survey
- 3,134 (0.7 percent) sourced from other Statistics NZ surveys
- 563 units (0.1 percent) sourced from Ministry of Economic Development data
- 139,335 (30.7 percent) non-sample units.
In AES 2009, the 20,513 postal survey unit responses are weighted to represent the 139,335 non-sample units. The corporate response rate required for the postal collection is set at 85 percent of the industry's goods and services tax (GST) sales. In 2009 this response rate was 91 percent, compared with 90 percent in 2008.
The population for this survey is selected from the Statistics NZ Business Frame.
The Business Frame is a database of all known individual private and public sector businesses and organisations engaged in the production of goods and services in New Zealand that meet significance criteria. The Business Frame provides a consistent reference to standard classifications, which facilitates the integration of statistical outputs and allows it to be used as a classification tool. It also provides links to all economic and financial survey data and the tax system, which allows more effective use of tax data to reduce respondent load.
The structure of each business on the Business Frame consists of an enterprise, a kind-of-activity unit (KAU), and a geographic unit. These are collectively referred to as statistical units. Larger or more complex businesses may have a number of statistical units. Each of the statistical units is given an industry classification based on its predominant activity. Different divisions of a company may be spread across several industries, depending on how the company has been structured. The collection unit for the AES is the KAU. By definition, a KAU is engaged in predominantly one activity for which a single set of accounting records is available.
The AES uses a stratified sample design to select the sample from units on the Business Frame. Each industry contains between one and four strata, defined by size of turnover (sourced from GST information) and rolling mean employment. Each industry has a full coverage stratum made up of large units with significant economic activity within their industry group. The remaining strata contain a sample of medium-sized units, which are weighted to represent non-sampled units. For example, a unit may have a weight of five, meaning it represents itself and four other businesses. Smaller businesses have less chance of being selected, and consequently when selected have larger weights representing more units. Most industries also have a tax strata for smaller units, where IR 10 information is used instead of a postal survey response.
The wide range of activities undertaken by New Zealand businesses makes it necessary to have different types of questionnaires. All questionnaires capture financial performance and position information, but the format and the wording of the questionnaires are tailored to suit different groups of businesses.
The AES is designed to measure industry levels for a given year. Incremental improvements in measurement, sample design, classification, and data collection may influence the inter-period movements, particularly over longer time periods. Work has been done to minimise the impact of these changes and present a consistent time series in the published tables.
Redesign of the Annual Enterprise Survey in 2009
The AES was last redeveloped in 1999. In 2009, Statistics NZ reviewed the survey against current and future user needs, and subsequently introduced a number of methodological changes for the 2009 financial year.
These changes were implemented to improve data quality, enhance business processes, and reduce respondent load.
Due to the new design, there was a significant impact on some industries' time-series figures published for the 2008 financial year relative to the 2009 financial year. Where possible these changes have been backdated. Users should note that the most significant difference between the 2008 and the 2009 designs is the introduction of an industry design for financial position data.
The following are the key changes that users of AES data should be aware of:
increased use of administrative data (IR 10 information): In the 2009 AES the number of units sourced from IR 10 information increased significantly. In the 2009 financial year we sourced nearly 290,000 units from IR 10 information, compared with 220,000 units in the 2008 financial year.
a decrease in the size of the AES postal sample in 2009: The increased use of administrative data helped decrease the size of the postal sample. The postal sample consisted of 22,509 units in the 2008 financial year, down to 20,513 units in the 2009 financial year.
re-optimisation of the AES sample: Over time, sampling methodologies designed at an industry level can become outdated, particularly for industries that have significant changes in structure. For the 2009 AES, all industry level sample designs were investigated, and optimised where neccessary. This process, along with the increased use of administrative data, has improved the levels of measured sample error across most industries in the AES.
designing for financial position data at an industry level, where previously this was designed at institutional sector level: Since 1999, the sample design for financial position data was at institutional sector level, using the New Zealand Institutional Sector Classification as the basis, while financial performance data was at industry level. An increased demand for financial position data from our users has led to a design for both financial performance and financial position data on an industry basis.
change to the area of the random number line which postal units are selected: Units are selected into the AES postal sample based on a random number assigned to them when they are first birthed onto the Business Frame. As part of the re-optimisation of the postal sample for 2009, the sample design for AES has moved its boundaries on the random number line for units which are not automatically selected into full coverage selection for the Annual Enterprise survey within their industry. This has meant a significant rotation in sampled units between the 2008 financial year and the 2009 financial year.
a new system for processing administrative data and more modelling of the administrative (IR 10) information: To decrease respondent load, Statistics NZ aims to increase the use of administrative data in the future. As part of this process, Statistics NZ has developed a new processing system for editing and imputation of all IR 10 data. This has meant new statistical methods have been introduced to process this increased use of IR 10 data more efficiently. Where there were significant gaps between what an IR 10 could not deliver compared with a postal survey, then attempts have been made to model these gaps. The two main areas affected by this are discussed below:
- There is a change to the methodology used to model additions and disposals estimates from units sourced from IR 10 data. Historically, units sourced from tax data were either calculated as showing net additions or net disposals. From 2009, data sourced from IR 10 data is now modelled to show both total additions and total disposals separately. This has had a significant impact on the values for both additions and disposals in the agricultural industries.
- From the 2009 AES we have introduced modelling for margin variables (ie sales of goods for resale versus sales of goods manufactured) from IR 10 data based on responses to the postal survey. Previously, no attempt was made to model a margin split from tax data, and data was assigned to the predominant activity. For example, if the unit was in a wholesaling industry, all sales were classified to sales of goods for resale.
For further information on the redesign implemented in the 2009 financial year, contact Nicholas Cox: firstname.lastname@example.org
Change in calculation of surplus before income tax
In this release, a change was made to the calculation of surplus before income tax. In previous years, operating surplus was calculated as:
(Total income less total expenditure) + salaries and wages to working proprietors
From this release, surplus before income tax will be calculated as:
(Total income less total expenditure) + or - change in stocks
Structural change in the construction division
In the 2009 financial year, a significant restructure occurred in the construction division. The result of this restructure is that some data captured in the construction industry in both the 2008 and 2007 financial years, will now be captured as part of the central government industry for the 2009 financial year forward.
Changes to data on local authorities
The AES uses data from the Local Authority Census (LAC) to produce industry based statistics about local authorities. In 2009, Statistics NZ and the Department of Internal Affairs worked together to redesign the LAC. A larger range of activity and transaction information was introduced with the aim of having the redesigned LAC questionnaire align more closely with the way councils record this data in their accounting systems.
From 2009, the LAC collected targeted rates and general rates separately. Where general rates have not been allocated to an industry, they will appear in the local government administration industry in the AES release. Before 2009, attempts were made to estimate total rates to their respective industries.
For more information on these changes in local authority statistics, see Annual local authority financial statistics: Year ended 2009.
Availability of results
The supplementary tables contain a selection of the tables available. Data is available at the design level (113 industries) upwards, subject to confidentiality. Tables at an even less aggregated level may also be available.
This is the first release of AES results for the 2009 financial year. These results are provisional. They may be revised as further information becomes available over the next two years.
Data collected and information contained in this publication must conform to the provisions of the Statistics Act 1975. This requires that published information maintains the confidentiality of individual respondents.
Detailed information on the following, and other terms, is available on our website or on request.
An enterprise that meets at least one of the following criteria:
- has greater than $30,000 annual GST expenses or sales
- has RMEs greater than three
- is in a GST-exempt industry (except residential property leasing and rental)
- is part of a group of enterprises
- is a new GST registration that is compulsory, special or forced
- is registered for GST and involved in agriculture or forestry.
A single business entity operating in New Zealand either as a legally constituted body such as a company, partnership, trust, local or central government trading organisation, incorporated society, or a self-employed individual.
Kind-of-activity unit (KAU)
A subdivision of an enterprise engaged in predominantly one activity and for which a single set of accounting records is available. This is the statistical unit used in the AES.
Australian and New Zealand Standard Industrial Classification 1996 (ANZSIC96)
The ANZSIC96 was developed for use in Australia and New Zealand for the production and analysis of industry statistics. Prior to 2007 the AES was designed using the ANZSIC96 classification, with some subdivisions and groups re-aggregated to reflect New Zealand operations.
Australian and New Zealand Standard Industrial Classification 2006 (ANZSIC06)
The ANZSIC06 was developed for use in Australia and New Zealand for the production and analysis of industry statistics. The AES from 2007 forward was designed using the ANZSIC06 classification, with some subdivisions and groups re-aggregated to reflect New Zealand operations. Further information on ANZSIC06 is available on our website.
Employee count (EC)
Head count of salary and wage earners sourced from taxation data. EC data is available on a monthly basis. This is mostly employees but can include a small number of working proprietors (who pay themselves a salary or wage).
Rolling mean employment (RME)
RME is a 12-month moving average of the monthly employee count figure, which replaces the numbers of full-time and part-time employees in the AES.
Full-time equivalent (FTE) persons engaged
The total number of full-time employees and working proprietors plus half the number of part-time employees and working proprietors.
Surplus before income tax
(Total income less total expenditure) + or - change in stocks
Surplus per rolling mean employment (RME)
Surplus before income tax divided by rolling mean employment.
Current assets divided by current liabilities.
Current assets less closing stocks divided by current liabilities.
Margin on sales of goods for resale
Sales of goods not further processed less purchases of goods bought for resale, as a percentage of sales of goods not further processed.
Return on equity
Surplus before income tax divided by shareholders' funds.
Return on total assets
Surplus before income tax divided by total assets.
Shareholders' funds divided by total capital and liabilities.
For more information, follow the link from the technical notes of this release on the Statistics NZ website.
Information obtained from Statistics NZ may be freely used, reproduced, or quoted unless otherwise specified. In all cases Statistics NZ must be acknowledged as the source.
While care has been used in processing, analysing and extracting information, Statistics NZ gives no warranty that the information supplied is free from error. Statistics NZ shall not be liable for any loss suffered through the use, directly or indirectly, of any information, product or service.
Timed statistical releases are delivered using postal and electronic services provided by third parties. Delivery of these releases may be delayed by circumstances outside the control of Statistics NZ. Statistics NZ accepts no responsibility for any such delays.