|Page tools: Print Page Print All|
5 The following shows the level at which retail trade statistics are released and defines each industry subgroup in terms of ANZSIC 2006 classes:
SCOPE AND COVERAGE
6 The scope of the Retail Business Survey is all employing retail trade businesses who predominantly sell to households. Like most Australian Bureau of Statistics (ABS) economic surveys, the frame used for the Survey is taken from the ABS Business Register which includes registrations to the Australian Taxation Office's (ATO) pay-as-you-go withholding (PAYGW) scheme. Each statistical unit included on the ABS Business Register is classified to the ANZSIC industry in which it mainly operates. The frame is supplemented with information about a small number of businesses which are classified to a non-retail trade industry but which have significant retail trade activity.
7 The frame is updated quarterly to take account of new businesses, businesses which have ceased employing, changes in industry and other general business changes. The estimates include an allowance for the time it takes a newly registered business to get on to the survey frame. Businesses which have ceased employing are identified when the ATO cancels their Australian Business Number (ABN) and/or PAYGW registration. In addition, businesses with less than 50 employees which do not remit under the PAYGW scheme in each of the previous five quarters are removed from the frame.
8 To improve coverage and the quality of the estimates and to reduce the cost to the business community of reporting information to the ABS, turnover for franchisees is collected directly from a number of franchise head offices. The franchisees included in this reporting are identified and removed from the frame.
STATISTICAL UNITS DEFINED ON THE ABS BUSINESS REGISTER
9 The ABS uses an economic statistics units model on the ABS Business Register to describe the characteristics of businesses, and the structural relationships between related businesses. The units model is also used to break groups of related businesses into relatively homogeneous components that can provide data to the ABS.
10 The units model allocates businesses to one of two sub-populations. The vast majority of businesses are in what is called the ATO Maintained Population, while the remaining businesses are in the ABS Maintained Population. Together, these two sub-populations make up the ABS Business Register population.
11 Most businesses and organisations in Australia need to obtain an ABN, and are then included on the ATO Australian Business Register. Most of these businesses have simple structures; therefore the unit registered for an ABN will satisfy ABS statistical requirements. The businesses with simple structures constitute the ATO Maintained Population, and the ABN unit is used as the statistical unit for most economic collections.
12 For the population of businesses where the ABN unit is not suitable for ABS statistical requirements, the ABS maintains its own units structure through direct contact with each business. These businesses constitute the ABS Maintained Population. This population consists typically of large, complex and diverse businesses. The statistical unit used in the Retail Business Survey for this population is the Type of Activity Unit. The Type of Activity Unit is comprised of one or more business entities, sub-entities or branches of a business entity within an Enterprise Group that can report production and employment data for similar economic activities. When a minimum set of data items are available, a Type of Activity Unit is created which covers all the operations within an ANZSIC subdivision and the unit is classified to that subdivision. Where a business cannot supply adequate data for each industry, a Type of Activity Unit is formed which contains activity in more than one industry subdivision.
13 The Survey is conducted monthly primarily by telephone interview although a small number of questionnaires are mailed to businesses. The businesses included in the survey are selected by random sample from a frame stratified by state, industry and business size. The survey uses annualised turnover as the measure of business size. For the ATO Maintained Population, the annualised turnover is based on the ATO's Business Activity Statement item Total sales and for the ABS Maintained Population a modelled annualised turnover is used. For stratification purposes the annualised turnover allocated to each business is not updated each quarter as to do so would result in increased volatility in the estimates.
14 Each quarter, some businesses in the sample are replaced, at random, by other businesses so that the reporting load can be spread across smaller retailers. This sample replacement occurs in the first month of each quarter which may increase the volatility of estimates between this month and the previous month especially at the state by industry subgroup level.
15 Generalised regression estimation methodology is used for estimation. For estimation purposes, the annualised turnover allocated to each business is updated each quarter.
16 Most businesses can provide turnover on a calendar month basis and this is how the data are presented. When businesses cannot provide turnover on a calendar month basis, the reported data and the period they relate to are used to estimate turnover for the calendar month.
17 Most retailers operate in a single state/territory. For this reason, estimates of turnover by state/territory are only collected from the larger retailers which are included in the survey each month. These retailers are asked to provide turnover for sales from each state/territory in which the business operates. Turnover for the smaller businesses is allocated to the state of their mailing address as recorded on the ABS Business Register.
DEFINITION OF TURNOVER
18 Turnover includes:
SEASONAL ADJUSTMENT AND TREND ESTIMATION
19 Seasonally adjusted estimates are derived by estimating and removing systematic calendar related effects from the original series. In the Retail trade series, these calendar related effects are known as:
20 Each of these influences is estimated by separate factors which, when combined, are referred to as the combined adjustment factors. The combined adjustment factors are based on observed patterns in the historical data. It is possible that with the introduction of ANZSIC 2006 from July 2009 the historical patterns may not be as relevant to some series. For example Watch and jewellery retailing moved from the Other retailing n.e.c industry subgroup to the Footwear and other personal accessory retailing industry subgroup under ANZSIC 2006. The seasonal patterns for other businesses in the Footwear and other personal accessory retailing industry subgroup appear to differ from watch and jewellery retailers. The combined adjustment factors will evolve over time to reflect any new seasonal or trading day patterns, although in this example, an estimate for this impact (seasonal break) has been implemented in the combined adjustment factors.
21 The following Retail trade series are directly seasonally adjusted:
22 A "two-dimensional reconciliation" methodology is used on the seasonally adjusted time series to force additivity - that is, to force the sum of fine-level (state by industry subgroup) estimates to equal the Australian, state and industry subgroup totals. The industry group totals are derived from the lower level estimates.
23 Quarterly seasonally adjusted series used in the compilation of the chain volume measures are the sum of their applicable monthly series.
24 Autoregressive integrated moving average (ARIMA) modelling can improve the revision properties of the seasonally adjusted and trend estimates. ARIMA modelling relies on the characteristics of the series being analysed to project future period data. The projected values are temporary, intermediate values, that are only used internally to improve the estimation of the seasonal factors. The projected data do not affect the original estimates and are discarded at the end of the seasonal adjustment process. The retail collection uses an individual ARIMA model for each of the industry totals and state totals. The ARIMA model is assessed as part of the annual reanalysis.
25 In the seasonal adjustment process, both the seasonal and trading day factors evolve over time to reflect changes in spending and trading patterns. Examples of this evolution include the slow move in spending from December to January; and, increased trading activity on weekends and public holidays. The Retail series uses a concurrent seasonal adjustment methodology to derive the combined adjustment factors. This means that data from the current month are used in estimating seasonal and trading day factors for the current and previous months. For more information see Information paper: Introduction of Concurrent Seasonal Adjustment into the Retail Trade Series (cat. no. 8514.0).
26 The seasonal and trading day factors are reviewed annually at a more detailed level than possible in the monthly processing cycle. The annual reanalysis can result in relatively higher revisions to the seasonally adjusted series than during normal monthly processing. For Retail Trade, the results of the latest review are normally included in the July issue based on data up to June. However for ANZSIC 2006 series, the seasonal reanalysis was based on data up to November 2008.
27 The seasonally adjusted estimates still reflect the sampling and non-sampling errors to which the original estimates are subject. This is why it is recommended that trend series be used with the seasonally adjusted series to analyse underlying month-to-month movements.
28 The trend estimates are derived by applying a 13-term Henderson moving average to the seasonally adjusted monthly series and a 7-term Henderson moving average to the seasonally adjusted quarterly series. The Henderson moving average is symmetric, but as the end of a time series is approached, asymmetric forms of the moving average have to be applied. The asymmetric moving averages have been tailored to suit the particular characteristics of individual series and enable trend estimates for recent periods to be produced. An end-weight parameter 2.0 of the asymmetric moving average is used to produce trend estimates for the Australia, State and Australian industry group totals. For the other series a standard end-weight parameter 3.5 of the asymmetric moving average is used. Estimates of the trend will be improved at the current end of the time series as additional observations become available. This improvement is due to the application of different asymmetric moving averages for the most recent six months for monthly series and three quarters for quarterly series. As a result of the improvement, most revisions to the trend estimates will be observed in the most recent six months or three quarters.
29 Trend estimates are used to analyse the underlying behaviour of the series over time. As a result of the introduction of The New Tax System, a break in the monthly trend series has been inserted between June and July 2000. Care should therefore be taken if comparisons span this period. For more details refer to the Appendix in the December 2000 issue of this publication.
30 For further information on seasonally adjusted and trend estimates, see:
Information Paper: Introduction of Concurrent Seasonal Adjustment into the Retail Trade Series (cat. no. 8514.0)
Information Paper: A Guide to Interpreting Time Series - Monitoring Trends, 2003 (cat. no. 1349.0)
or contact the Assistant Director, Time Series Analysis on Canberra (02) 6252 6345 or by email at <email@example.com>.
ANALYSING TREND ESTIMATES
31 The following terms are used in this publication to describe month to month movements in the trend series:
RELIABILITY OF ESTIMATES
32 There are two types of error possible in estimates of retail turnover:
Non sampling error which arises from inaccuracies in collecting, recording and processing the data. The most significant of these errors are: misreporting of data items; deficiencies in coverage; non-response; and processing errors. Every effort is made to minimise reporting error by the careful design of questionnaires, intensive training and supervision of interviewers, and efficient data processing procedures.
33 Seasonally adjusted and trend estimates and chain volume measures are also subject to sampling variability. For seasonally adjusted estimates, the standard errors are approximately the same as for the original estimates. For trend estimates, the standard errors are likely to be smaller. For quarterly chain volume measures, the standard errors may be up to 10% higher than those for the corresponding current price estimates because of the sampling variability contained in the prices data used to deflate the current price estimates.
34 Estimates, in original terms, are available from the Downloads tab of this publication. Estimates that have an estimated relative standard error (RSE) between 10% and 25% are annotated with the symbol '^'. These estimates should be used with caution as they are subject to sampling variability too high for some purposes. Estimates with a RSE between 25% and 50% are annotated with the symbol '*', indicating that the estimates should be used with caution as they are subject to sampling variability too high for most practical purposes. Estimates with a RSE greater than 50% are annotated with the symbol '**' indicating that the sampling variability causes the estimates to be considered too unreliable for general use.
35 To further assist users in assessing the reliability of estimates, key data series have been given a grading of A to B. Where:
36 The tables below provide an indicator of reliability for the estimates in original terms. The reliability indicator is based on an average RSE derived over four years.
37 Standard errors for the Australian estimates (original data) for November 2009 contained in this publication are:
RELIABILITY OF TREND ESTIMATES
38 The trending process dampens the volatility in the original and seasonally adjusted estimates. However, trend estimates are subject to revisions as future observations become available.
COMPARABILITY WITH OTHER ABS ESTIMATES
39 The estimates of Retail turnover in this publication will differ from sales of goods and services by the Retail trade industry in Business Indicators, Australia (cat. no. 5676.0). This publication presents monthly estimates of the value of turnover of retail businesses, is sourced from the Retail Business Survey, includes the Goods and Services Tax and includes some retail trade businesses classified to a non-retail trade industry but which have significant retail trade activity. Estimates for sales of goods and services in Business Indicators, Australia are sourced from the economy wide Quarterly Business Indicators Survey and exclude the Goods and Services Tax. In addition, the Retail Business Survey does not include all classes in the ANZSIC Retail trade Division but includes Cafes, restaurants and take-away food services from the Accommodation and Food Services Division. The use of different samples in the two surveys also contributes to differences.
40 Quarterly Retail trade chain volume estimates contribute to the quarterly national accounts in two main areas. First, they are an indicator of Household Final Consumption Expenditure in the expenditure side of Gross domestic product. Historically Retail trade estimates contribute about 55-60% of Household Final Consumption Expenditure but this relative contribution can vary from quarter to quarter as household expenditure shifts between retail trade and areas like personal services, travel and leisure activities which are outside the scope of retail trade. Second, Retail trade estimates, along with estimates from Business Indicators, Australia, contribute to estimates for the Retail trade Division in the production side of Gross domestic product.
41 Current publications and other products released by the ABS are available from the Statistics View. The ABS also issues a daily Release Advice on the web site which details products to be released in the week ahead. Users may also wish to refer to the following publications:
42 As well as the statistics included in this and related publications, the ABS may have other relevant data available. Inquires should be made to the National Information and Referral Service on 1300 135 070.
These documents will be presented in a new window.