|Page tools: Print Page Print All|
4 In the Labour Force Survey, coverage rules are applied which aim to ensure that each person is associated with only one dwelling, and hence has only one chance of selection. The chance of a person being enumerated at two separate dwellings in the one survey is considered to be negligible. See paragraph 45 for information about the effect of the coverage rules on family statistics.
5 Persons who are away from their usual residence for six weeks or less at the time of interview are enumerated at their usual residence (relevant information may be obtained from other usual residents present at the time of the survey).
6 Labour Force Survey estimates of persons employed, unemployed and not in the labour force are calculated in such a way as to add up to the independently estimated distribution of the usually resident population aged 15 years and over by age and sex. This procedure compensates for under-enumeration in the survey, and leads to more reliable estimates. Persons who, at the time of interview, are overseas for more than six weeks but for less than 12 months are included in the independent population statistics (benchmarks) and are thus provided for in the calculation of the estimates. The benchmarks are the latest available estimates at the time the Labour Force Survey is conducted, but they usually differ from the official population estimates subsequently published in Australian Demographic Statistics (Cat. no. 3101.0) because they are derived from incomplete information about population changes.
REVISION OF POPULATION BENCHMARKS
7 Survey estimates are not revised for the usually small amendments of population benchmarks arising from new data on deaths and overseas and internal migration. Revisions are made, however, after each Census of Population and Housing, and when population estimation bases are reviewed. These revisions affect original, seasonally adjusted and trend estimates. The last such revision was made in February 1999 to take account of the results of the 1996 Census of Population and Housing. This revision affected all the monthly estimates from January 1995 to January 1999.
8 Population benchmarks used in the estimation of Labour Force Survey data are compiled according to place of usual residence. An explanation of the place of usual residence conceptual basis for population estimates is given in Information Paper: Demographic Estimates and Projections:– Concepts, Sources and Methods (cat. no. 3228.0) which is available on the ABS website www.abs.gov.au under Statistical Concepts Library.
HISTORY OF THE SURVEY
9 National surveys were conducted in February, May, August and November each year from 1964 to February 1978. The survey has been conducted on a monthly basis since February 1978.
10 The questionnaire used in the survey for the collection of labour force data has been revised from time to time. Details of these changes have been published in Information Paper: Questionnaires Used in the Labour Force Survey (cat. no. 6232.0) in March 1978, December 1981, August 1984, June 1986, June 1991, March 1993 and May 2001.
11 From April 2001, the Labour Force Survey has been conducted using a redesigned questionnaire containing additional data items and some minor definitional changes. Core labour force series have been revised for the period April 1986 to March 2001 to ensure continuity. For details, see Information Paper: Implementing the Redesigned Labour Force Survey Questionnaire (cat. no. 6295.0).
INCLUSION OF CONTRIBUTING FAMILY WORKERS
12 In April 1986, the questionnaire was revised following the extension of the definition of employed persons to include persons who worked without pay between 1–14 hours per week in a family business or on a farm (i.e. contributing family workers). This definition aligned the Australian labour force concepts with the set of definitions adopted by the 13th International Conference of Labour Statisticians in October 1982.
13 Previously, contributing family workers who worked 1–14 hours, or who had such a job but were not at work, were defined as either unemployed or not in the labour force, depending on whether they were actively looking for work.
COMPARABILITY OF SERIES
14 As a result of changes in coding methods, estimates classified by industry, occupation and status in employment data from February 2000 onwards are not strictly comparable with earlier periods. For details on the changes to industry and occupation refer to the article in the November 1999 issue of Labour Force, Australia (cat. no. 6203.0). For details of the change to status in employment see the article in the May 2000 issue of Labour Force, Australia (cat.no. 6203.0).
15 In March 1994, Relationship in household and Family type classifications were introduced to align with ABS standards. From April 2001, same sex couples are included in couple families; previously these persons were included in One-parent families or as a Non-family member.
SURVEY SAMPLE REDESIGN
16 Following each Population Census, the ABS reselects the Labour Force Survey sample to take into account the new information which is obtained from the Census. The sample that was used in the Labour Force Survey from September 1992 to August 1997 has been replaced by a new sample selected using information collected in the 1996 Census. The new sample was phased in over the period September 1997 to April 1998. For additional information, see Information Paper: Labour Force Survey Sample Design, 1997 (cat. no. 6269.0).
17 The sampling fractions for each State/Territory differ in order to yield reliable estimates of the main labour force aggregates for each State and Territory. The sampling fraction for Victoria changed from 1 in 242 to 1 in 257.
18 In addition to the introduction of the new sampling fraction, the labour force dissemination regions were reviewed in order to maintain consistency with the Australian Standard Geographical Classification (ASGC), 1996.
19 More information on the changes to regional boundaries is available in the Information Paper: Regional Labour Force Statistics, September 1997 (cat. no. 6262.0). Details of the changes to LGA boundaries in Victoria are available in Statistical Geography, Victoria (cat. no. 1103.2).
20 Detailed maps of the new Labour Force Dissemination Regions are presented at the end of this publication.
RELIABILITY OF THE ESTIMATES
21 Estimates in this publication are subject to two sources of error:
22 As the above problems are compounded when the statistics are disaggregated to regional data, users are particularly advised to treat month-to-month movements for regional data with caution. (See the following paragraphs for more detail on determining the reliability of month-to-month movements.)
STANDARD ERROR TABLES
23 To assist you in determining the reliability of the various estimates contained in this publication, tables of standard errors of level estimates and month-to-month movements are included in Appendixes 1 and 2 on pages 36 and 37 respectively.
24 Use the table of standard errors of level estimates to determine the accuracy of most estimates contained in this publication. Use the tables of month-to-month movements to determine the accuracy of estimates when comparing one month's figures with another. This is particularly important with month-to-month movements in determining whether or not the estimates indicate a significant change has occurred.
25 To use the tables, locate the figure in the Size of estimate column which is nearest in value to the estimate you wish to use. If you are comparing movements use the larger estimate. Read across the table until you find the column for the geographic area covered by the estimate concerned. This figure is one standard error.
26 There are approximately two chances in three that the true value which the estimate is attempting to measure is within plus or minus one standard error of the estimate. There are approximately nineteen chances in twenty that the true value is within plus or minus twice this amount.
One standard error on a published estimate for Victoria is 1,650. The diagram shows the probable location of the true value which the estimate is attempting to measure.
27 A similar technique is used for month-to-month movements of estimates. After finding the standard error of the larger of the two estimates from the table of month-to-month movements of estimates (as in paragraph 25) compare the movement to one standard error; if the movement is larger, this indicates a likelihood that a change has occurred. If the movement is larger than two standard errors, then this is a fairly reliable indicator of the change.
28 If comparing quarterly movements multiply the standard error by a factor of 1.04 before comparing it to the movement. For 12 monthly movements multiply by a factor of 1.36 before making the comparison.
29 Another useful measure of reliability is relative standard error (RSE). The relative standard error of an estimate is the amount by which an estimate is likely to vary (one standard error) as a percentage of its size.
30 To calculate the relative standard error of an estimate, divide one standard error of the estimate by the estimate and multiply by 100.
31 Estimates with a relative standard error of 10% or less can be regarded as statistically reliable enough for most uses. Estimates with a relative standard error of 25% or more should not be regarded as reliable and care should be exercised when using them. All such estimates in this publication have been marked with an asterisk (*).
32 For this survey this warning applies to estimates of 4,500 or less for Victoria. Different geographic areas have different points at which the 25% relative standard error cut off takes effect. These are listed in Appendix 1.
DIFFERENCES BETWEEN LABOUR FORCE SURVEY ESTIMATES AND OTHER ESTIMATES
33 The results of the 1996 Census of Population and Housing show that labour force estimates derived from the Census differ from those derived from the Labour Force Survey.
34 The broad concepts underlying the measures of the labour force and its components, employment and unemployment, are similar in the Census and the survey.
35 There are considerable differences in both the collection methodology adopted (including the detailed questions asked) and estimation procedures. Factors contributing to differences in estimates include under-enumeration in the Population Census for which census labour force estimates have not been adjusted, the use in the Labour Force Survey of population benchmarks derived from incomplete information about population change (see paragraph 6), the inclusion of permanent defence forces in census estimates, the personal interview approach adopted in the survey as opposed to self-enumeration of census schedules, differing questions used to determine labour force characteristics, and differing methods of adjustment for non-response to the survey or Census.
36 The Labour Force Survey provides detailed and up-to-date estimates of employment and unemployment for Australia, States and regions, whereas the Census of Population and Housing provides counts for small areas but in less detail than is available from the survey.
37 These considerations should be borne in mind when comparisons are made between Population Census and Labour Force Survey estimates.
38 Comparability with estimates produced from the quarterly Survey of Employment and Earnings is affected by the use of different survey methodology and definitions. The Labour Force Survey provides estimates of people in jobs whereas the Survey of Employment and Earnings provides an estimate of the number of jobs held by employees. A more detailed description of the differences between these two series is available on request.
39 Seasonally adjusted series are published in Table 2. Seasonal adjustment is a means of removing the estimated effects of normal seasonal variation from the series so that the effects of other influences on the series can be recognised more clearly. Seasonal adjustment does not remove the irregular or non-seasonal influences which may be present in any particular month. This means that month-to-month movements of the seasonally adjusted estimates may not be reliable indicators of trend behaviour. For example, irregular factors unrelated to the trend account for more than half the seasonally adjusted movement with the following frequency:
Unemployment: 8 in 10 monthly movements
Unemployment rate: 7 in 10 monthly movements
Participation rate: 9 in 10 monthly movements
40 Seasonal factors are reviewed annually to take account of each additional year's original data. Information about the most recent annual review of seasonal factors was published in a feature article in the February 2001 issue of Labour Force, Australia (cat. no. 6203.0). An additional review was conducted following the revision of series associated with the introduction of the redesigned questionnaire in April 2001, (see paragraph 11). The results of this additional review were used to compile the seasonally adjusted and trend estimates in this publication.
41 Smoothing seasonally adjusted series produces a measure of trend by reducing the impact of the irregular component of the series. The monthly trend estimates are derived by applying a 13-term Henderson-weighted moving average to all months except the last six. The last six monthly trend estimates are obtained by applying surrogates of the Henderson average to the seasonally adjusted series. These trend series are used to analyse the underlying behaviour of the series over time. Table 3 shows trend estimates for the past 15 months. Trend series graphs are shown on page 1. Long term data are available on the ABS on-line data dissemination service, AusStats.
42 While this smoothing technique enables estimates to be produced which include the latest month, it does result in revisions to the most recent months as additional observations become available. Generally, subsequent revisions become smaller, and after three months or two quarters have a negligible impact on the series. There will also be revisions as a result of the annual review of seasonal factors mentioned above in paragraph 40.
43 Users may wish to refer to the ABS publication A Guide to Interpreting Time Series—Monitoring 'Trends', an Overview (cat. no. 1348.0) for further information about trend estimates.
LABOUR FORCE STATUS AND OTHER CHARACTERISTICS OF FAMILIES
44 As a part of survey procedures, family relationships are determined each month, enabling both the estimation of persons cross-classified by their relationship in the household and the estimation of families. In this publication, Table 5 shows the labour force status and relationship in the household of individuals. The new classification FAMILY TYPE, and information on families rather than the household relationship of individuals, is contained in Labour Force, Australia (cat. no. 6203.0).
45 Because of the coverage rules, persons who usually live with other members of their family may, at the time of the survey, be enumerated as not living with all the usual members of their family. This situation is more likely for persons who are enumerated as visitors to other private dwellings or as persons staying in non-private dwellings (hotels, hospitals, etc.). The determination of family structure and family characteristics in such cases is difficult. Thus, survey questions used to determine family relationships are restricted to persons enumerated as usual residents of private dwellings. That is, the following persons are excluded:
46 In addition, in those households where it was not possible to obtain information relating to all the usual residents, no family information was recorded. Thus persons living in households which include a member of the permanent defence forces, who is outside the scope of the population survey, are excluded from survey questions used to determine family relationships because family information could not be obtained from each usual resident. Similarly households which, at the time of the survey, have one or more of their usual residents away for more than six weeks, are excluded from the family relationship questions. This also applies to households from which an incomplete or inadequate questionnaire was obtained for any usual resident in on scope and coverage. Generally, relationship in household is determined for more than 90% of all civilians aged 15 and over.
47 From April 1991, labour force birthplace data are aggregated according to major groups of the Standard Australian Classification of Countries (SACC) (cat. no. 1269.0) and its predecessor. The SACC was developed by the ABS for use whenever demographic, labour and social statistics are classified by countries.
48 The SACC major groups are based on the concept of geographic proximity. They differ from the country groups presented in this publication prior to April 1991. For example, African countries are now covered by THE MIDDLE EAST AND NORTH AFRICA and AFRICA (EXCLUDING NORTH AFRICA), while Asia has been split into SOUTH-EAST ASIA, NORTH-EAST ASIA and SOUTHERN ASIA. Data for selected individual countries will continue to be available in this publication.
49 From August 1994, Labour Force Survey industry data are classified according to the Australian and New Zealand Standard Industrial Classification (ANZSIC), a detailed description of which appears in ANZSIC 1993 (cat. no. 1292.0). Like the previous Australian Standard Industrial Classification (ASIC), ANZSIC classifies businesses according to their economic activities, in a structure consisting of four levels (Division, Sub-division, Group and Class). Labour Force Survey data are coded at the Group level, as was the practice under ASIC.
50 To enable the conversion of historical data from ASIC to ANZSIC for the period November 1984 to May 1994, a concordance was published in the August 1994 issue of Labour Force, Australia (cat. no. 6203.0) and in the Information Paper: Labour Force Survey: Introduction of ANZSIC for Industry data (Replacement publication) (cat. no. 6259.0). It has been found that the concordance, which was based on preliminary investigations, did not provide the most appropriate conversion for certain Group level industries. An improved concordance has now been applied to historical Labour Force Survey estimates. This concordance was published in the Appendix to the May 1996 issue of Labour Force, Australia (cat. no. 6203.0) and in a further issue of the above Information Paper.
51 From August 1996, Labour Force Survey occupation data are classified according to the Australian Standard Classification of Occupations (ASCO) Second Edition, a detailed description of which appears in ASCO — Australian Standard Classification of Occupations, Second Edition (cat. no. 1220.0). The new version of the classification replaces ASCO First Edition, which was adopted in the survey in August 1986. Like ASCO First Edition, ASCO Second Edition is a skill-based classification of occupations. However, the structure of ASCO Second Edition comprises five hierarchical levels (Major Group, Sub-Major Group, Minor Group, Unit Group and Occupation) compared with four levels in ASCO First Edition (Major Group, Minor Group, Unit Group and Occupation). Under ASCO Second Edition, Labour Force Survey data are coded to the Unit Group level, as was the practice under ASCO First Edition.
52 Users may also wish to refer to the following publications which relate to the labour force and are available on request:
Labour Statistics, Australia (Cat. no. 6101.0) (irregular)
A Guide to Labour Statistics, Australia (Cat. no. 6102.0) (irregular)
Labour Force, New South Wales (Cat. no. 6201.1) (quarterly)
Labour Force, Australia, Preliminary (Cat. no. 6202.0) (monthly)
Labour Force, Australia (Cat. no. 6203.0) (monthly)
Labour Force, Australia, 1978–1995 (Cat. no. 6204.0) (irregular)
Labour Force Projections, Australia (Cat. no. 6260.0) (irregular)
Questionnaires Used in the Labour Force Survey (Cat. no. 6232.0) (irregular)
Regional Labour Force Statistics (Cat. no. 6262.0) (irregular)
Labour Force Survey Sample Design (Cat. no. 6269.0) (irregular)
Measuring Employment and Unemployment (Cat. no. 6279.0) (irregular)
Labour Force Survey Questionnaire Redesign 2000 (Cat. no. 6294.0) (irregular)
Implementing the Redesigned Labour Force Survey (Cat. no. 6295.0) (irregular)
53 Current publications produced by the ABS are listed in the Catalogue of Publications and Products, Australia (Cat. no. 1101.0). The ABS also issues, on Tuesdays and Fridays, a Release Advice (Cat. no. 1105.0) which lists publications to be released in the next few days. The Catalogue and Release Advice are available from any ABS office or from this site.
DATA AVAILABLE ON REQUEST
54 As well as statistics included in this publication, the ABS may have other relevant data available. Inquiries should be made to Information Consultancy, Victoria or to any ABS office.
55 Estimates have been rounded and discrepancies may occur between sums of the component items and totals.
These documents will be presented in a new window.