6203.0 - Labour Force, Australia, Feb 2003  
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 28/03/2003  Ceased
   Page tools: Print Print Page Print all pages in this productPrint All

Note: The Labour Force Survey product set is changing in 2003.

FINAL ISSUE

This is the final issue of Labour Force, Australia (cat. no. 6203.0). Statistics included in this publication will continue to be available in the future, from a variety of sources. For subscribers to this publication, information on the various options available has been provided either on the flysheet included with this issue (for those receiving hardcopy versions) or via email (for those receiving the Acrobat pdf version). For example, subscribers may choose to switch their subscription to the new quarterly publication Australian Labour Market Statistics (cat. no. 6105.0), subscribe to new or existing electronic products, or receive a refund.

Further information on the new Labour Force Survey product set is detailed in the Information Paper: Changes to Labour Force Survey Products (cat. no. 6297.0) available free from the ABS web site (Themes - Labour). Any queries on the new product set should be directed to Lorraine Cornehls (email: lorraine.cornehls@abs.gov.au; telephone: 02 6252 6079).


NOTES ON ESTIMATES

A new sample for the Labour Force Survey is being introduced progressively over the period November 2002 to June 2003. See paragraphs 13 to 15 of the Explanatory Notes or Information Paper: Labour Force Survey Sample Design (cat. no. 6269.0) for details.

Following the regular annual seasonal reanalysis, the total published growth in employment, seasonally adjusted, over the four months from November 2002 to February 2003 (coinciding with the introduction of a little more than half the new sample), is 193,700.

To assist in the interpretation of the published estimates, the ABS is investigating the labour force characteristics of the new sample in comparison with the sample that it is replacing. Analyses to date have used alternative methods that place greater emphasis on the sample that is common between consecutive months of the survey.

The matched rotation group method calculates monthly movements using the 7/8th of the sampled dwellings that are common between consecutive months under the LFS rotation scheme. This method produces an increase in employment (seasonally adjusted) over the last four months of about 30,000 less than the published estimate. However, some caution should be used in interpreting matched rotation group estimates, as they have a tendency to underestimate employment growth. If an adjustment were made for this effect, the estimated change in employment from the matched rotation group estimate would be closer to the published figure.

Composite estimation, a technique which does not exhibit this effect, produces an estimate of employment growth over the last four months that is broadly similar to the currently published figure. For information about matched rotation group and composite estimates, see the article in the May 1998 issue of Australian Economic Indicators (cat. no. 1350.0).

While additional sampling error is expected during implementation of the new sample, there is no evidence from these analyses that the change in sample has materially affected estimates of employment growth. Further analyses are being undertaken, and the ABS will publish the results when they are completed.


STATE INQUIRIES

For further inquiries about labour force data, contact Labour Force Inquiries in ABS State offices: Sydney 02 9268 4633, Melbourne 03 9615 7073, Brisbane 07 3222 6068, Adelaide 08 8237 7365, Perth 08 9360 5304, Hobart 03 6220 5876, Darwin 08 8943 2120, Canberra 02 6207 0283.


For further information about these and related statistics, contact Marjory Smith on Canberra 02 6252 6525, or the National Information Service on 1300 135 070.


SEASONAL REANALYSIS OF MONTHLY LABOUR FORCE SURVEY ESTIMATES


INTRODUCTION

Each year, all seasonally adjusted and trend Labour Force Survey (LFS) estimates are reanalysed and revised back to February 1978 after the application of updated seasonal factors. Revisions resulting from the 2003 reanalysis were released electronically on 6 March 2003. This article explains the annual seasonal reanalysis process and the methodology for seasonal and trend series adjustment applied to LFS estimates.

The impact of the revisions is illustrated in the table at the end of this article, where the revised estimates are compared with previously published estimates for selected seasonally adjusted series.


SEASONAL REANALYSIS

Seasonal adjustment is a means of removing the estimated effects of regular seasonal variations from a time series of data, so that the effects of other influences on the series can be recognised more clearly. The seasonally adjusted estimates also reflect the sampling and non-sampling errors present in the original data.

As with most ABS seasonally adjusted series, LFS seasonal factors are reviewed annually. This process assesses possible changes in seasonality, taking into account the most recent year’s data, in order to derive the seasonal adjustment factors for the coming year and any revisions to seasonal factors for previous years.


Seasonally adjusted series

For Australia, seasonally adjusted estimates for employed persons are obtained by adding the following independently adjusted series for males and females:

  • aged 15 to 19 employed full time;
  • aged 20 and over employed full time; and
  • employed part time.

Original estimates of married females employed full time and employed part time are also independently seasonally adjusted, but are not used in the calculation of total female seasonally adjusted employment.

Seasonally adjusted estimates for unemployed persons are obtained by adding the following independently adjusted series for males and females:
  • aged 15 to 19 looking for full-time work;
  • aged 20 and over looking for full-time work; and
  • looking for part-time work.

Original data for males and females aged 15 to 19 looking for first full-time job are also seasonally adjusted, but are not used in the calculation of the aggregate estimates. The series for married females looking for full-time and part-time work are also independently adjusted, but are not used in the calculation of total female seasonally adjusted unemployment.

Seasonally adjusted estimates for the labour force are formed by adding the seasonally adjusted component series for the employed and unemployed. Seasonally adjusted unemployment rates are calculated using seasonally adjusted unemployment and labour force estimates. Seasonally adjusted participation rates are calculated using seasonally adjusted labour force and unadjusted population estimates. Seasonally adjusted unemployment to population ratios are calculated using seasonally adjusted unemployment and unadjusted population estimates.

For the states and territories, seasonally adjusted estimates of employment and unemployment are obtained by the addition of the independently adjusted series for males and females. Estimates of males and females employed full time are also adjusted, but are not used to generate total employment estimates.

Given that estimates for Australia, States and Territories are adjusted independently, the addition of seasonally adjusted estimates across all States and Territories will not generally equal the seasonally adjusted Australian total. Seasonally adjusted estimates for the Northern Territory and the Australian Capital Territory are not published due to the high level of revision to these estimates after each seasonal reanalysis. See paragraph 40 of the Explanatory Notes for further information.

Seasonally adjusted estimates of long-term unemployment are obtained by independently adjusting the original series for males and females unemployed for 52 weeks and under 104 weeks; and the series for males and females unemployed for 104 weeks and over. Total long-term unemployment estimates are the aggregation of these component series.

The employed persons series for each ANZSIC Industry Division is independently seasonally adjusted. For this reason, the sum of seasonally adjusted employment estimates for Industry Divisions will not generally equal the seasonally adjusted estimate of total employment. For further information on the seasonal adjustment process, contact the Assistant Director, Time Series Analysis on 02 6252 6345.


Future developments

Evolving seasonal patterns cause revisions to seasonal factors. If reanalyses were conducted more frequently than annual, the seasonal factors would stabilise sooner. The option of conducting seasonal reanalyses each month (for a monthly series) or each quarter (for a quarterly series) is called concurrent reanalysis. After discussion with users over the past year, concurrent reanalysis will be implemented into Labour Force Survey statistics within the next year.


Trend series

Smoothing the seasonally adjusted series produces a ‘trend’ series by reducing the impact of the irregular movements in the series. A trend series is useful for analysing the underlying behaviour of the series over time.

For monthly series, a 13-term Henderson-weighted moving average is applied to the seasonally adjusted series, for 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, and are revised as later data become available. For quarterly series, a 7-term Henderson moving average is applied to the seasonally adjusted series, with surrogate weights for the current end of the time series. See paragraphs 38 and 39 of the Explanatory Notes for further information.

For the purpose of deriving trend estimates only, seasonally adjusted observations are modified prior to the application of the Henderson weights, in instances where there have been unusually large identified outliers.

Using the Henderson weights, trend series are produced corresponding to each of the component seasonally adjusted series identified above. Like their seasonally adjusted counterparts, aggregate level trend data are the addition of these component series. Trend unemployment rates are calculated by dividing trend unemployment by trend labour force estimates. Trend participation rates and unemployment to population ratios are derived by applying Henderson weights to the respective seasonally adjusted rate and ratio series.


RELEASE OF REVISED DATA

Revised seasonally adjusted and trend labour force data were released electronically on 6 March and were subsequently included in the February 2003 issue of Labour Force, Australia, Preliminary (cat. no. 6202.0) released on 13 March 2003. Revised estimates from February 1978 to January 2003 are available on AusStats, floppy disk or as a special data service. Revised seasonal adjustment factors from February 1978 to January 2004 are available on floppy disk or as a special data service.

Other series

For the LFS, only major National and State/Territory series are subject to seasonal and trend adjustment. Other LFS series can be adjusted on a consultancy basis by contacting the person listed below.


FURTHER INFORMATION

For further information about revised labour force estimates, contact Peter Bradbury on 02 6252 6525 or email peter.bradbury@abs.gov.au.

TABLE 1. LABOUR FORCE SURVEY SEASONAL REANALYSIS, FEBRUARY 2003: DIFFERENCE BETWEEEN PREVIOUSLY PUBLISHED AND REVISED SEASONALLY ADJUSTED ESTIMATES OF EMPLOYED PERSONS, UNEMPLOYED PERSONS, UNEMPLOYMENT RATE AND PARTICIPATION RATE
Employed Persons ('000) Previously
Unemployed Persons ('000) Previously
Published
Revised
Difference (a)
Published
Revised
Difference (a)
2001
January
9,115.5
9,109.8
-5.8
615.7
615.6
-0.1
February
9,117.7
9,113.8
-3.9
647.5
647.3
-0.2
March
9,127.4
9,113.8
-13.7
633.5
640.4
6.9
April
9,159.1
9,165.3
6.2
660.5
663.4
2.9
May
9,155.9
9,151.6
-4.3
668.3
665.5
-2.8
June
9,147.3
9,151.5
4.2
675.8
674.8
-1.0
July
9,133.4
9,138.3
4.8
673.8
678.7
4.9
August
9,194.1
9,187.7
-6.4
671.3
670.4
-0.8
September
9,158.6
9,161.8
3.3
662.6
664.0
1.4
October
9,179.4
9,184.6
5.2
693.6
691.9
-1.7
November
9,191.8
9,198.8
7.1
670.9
668.1
-2.8
December
9,199.0
9,203.3
4.3
665.3
656.6
-8.7
2002
January
9,262.7
9,253.7
-9.0
692.5
692.6
0.1
February
9,283.1
9,277.7
-5.4
652.5
651.8
-0.8
March
9,304.3
9,289.3
-15.0
622.3
630.2
7.9
April
9,260.8
9,267.6
6.8
621.6
624.0
2.4
May
9,305.2
9,300.8
-4.4
622.5
619.1
-3.4
June
9,317.8
9,323.1
5.3
643.9
642.8
-1.1
July
9,289.5
9,293.9
4.4
609.4
614.1
4.7
August
9,378.0
9,370.9
-7.0
622.7
620.2
-2.6
September
9,347.3
9,350.8
3.5
617.1
619.6
2.4
October
9,363.1
9,369.8
6.7
598.6
596.9
-1.8
November
9,423.6
9,429.8
6.2
616.8
614.1
-2.7
December
9,475.6
9,481.8
6.2
628.4
619.2
-9.2
2003
January
9,586.6
9,575.8
-10.8
619.9
619.7
-0.2
Unemployment Rate (%) Previously
Participation Rate (%) Previously
Published
Revised
Difference (a)
Published
Revised
Difference (a)
2001
January
6.3
6.3
0.0
63.5
63.5
0.0
February
6.6
6.6
0.0
63.7
63.6
0.0
March
6.5
6.6
0.1
63.6
63.5
0.0
April
6.7
6.7
0.0
63.9
63.9
0.1
May
6.8
6.8
0.0
63.8
63.8
0.0
June
6.9
6.9
0.0
63.8
63.8
0.0
July
6.9
6.9
0.0
63.6
63.6
0.1
August
6.8
6.8
0.0
63.9
63.8
0.0
September
6.7
6.8
0.0
63.5
63.6
0.0
October
7.0
7.0
0.0
63.8
63.8
0.0
November
6.8
6.8
0.0
63.6
63.7
0.0
December
6.7
6.7
-0.1
63.6
63.5
0.0
2002
January
7.0
7.0
0.0
64.1
64.0
-0.1
February
6.6
6.6
0.0
63.9
63.9
0.0
March
6.3
6.4
0.1
63.8
63.7
0.0
April
6.3
6.3
0.0
63.4
63.5
0.1
May
6.3
6.2
0.0
63.6
63.6
-0.1
June
6.5
6.5
0.0
63.7
63.8
0.0
July
6.2
6.2
0.0
63.3
63.3
0.1
August
6.2
6.2
0.0
63.8
63.8
-0.1
September
6.2
6.2
0.0
63.5
63.6
0.0
October
6.0
6.0
0.0
63.4
63.5
0.0
November
6.1
6.1
0.0
63.8
63.9
0.0
December
6.2
6.1
-0.1
64.2
64.1
0.0
2003
January
6.1
6.1
0.0
64.7
64.7
-0.1
(a) Calculated on unrounded estimates


LABOUR MARKET IN BRIEF

TREND ESTIMATES

The trend estimate of employed persons has been increasing since December 2000, reaching 9,559,600 in February 2003. Full-time employment rose to 6,834,400 and part-time employment rose to 2,725,200. The trend estimate of unemployment rose slightly to stand at 614,400 in February 2003. The trend unemployment rate in February 2003 fell marginally to 6.0%. The male and female unemployment rates remained at 6.2% and 5.9% respectively. The trend participation rate in February 2003 rose to 64.5%. The female participation rate rose to 56.8% and the male participation rate rose to 72.4%.


EMPLOYMENT

The seasonally adjusted estimate of employment decreased by 12,300 to 9,563,500 in February 2003. Full-time employment increased by 10,000 to 6,852,100, with female full-time employment increasing by 13,300 to 2,332,200 and male full-time employment decreasing by 3,300 to 4,519,900. Part-time employment decreased by 22,300 to 2,711,400. Female part-time employment decreased by 15,500 to 1,945,900, and male part-time employment decreased by 6,700 to 765,500.


UNEMPLOYMENT

The seasonally adjusted estimate of unemployment decreased by 10,000 to 609,700 in February 2003. The number of unemployed persons seeking full-time work decreased by 8,600 to 458,200, and the number of unemployed persons seeking part-time work decreased by 1,400 to 151,600.


UNEMPLOYMENT RATE

The seasonally adjusted unemployment rate decreased by 0.1 percentage point to 6.0% in February 2003. The male and female rates both decreased by 0.1 percentage point to 6.1% and 5.8% respectively.

Graph: Unemployment rate - Trend - Seasonally adjusted



PARTICIPATION RATE

The seasonally adjusted labour force participation rate decreased by 0.2 percentage points to 64.4% in February 2003. The male participation rate decreased by 0.3 percentage points to 72.3%, and the female participation rate decreased by 0.1 percentage point to 56.8%.


PRINCIPAL LABOUR FORCE SERIES

PERSONS EMPLOYED BY STATE: TREND SERIES

New South Wales

From a low of 2,542,700 in February 1993, the trend estimate of employment in New South Wales generally rose to 3,056,600 in August 2000. While the trend fell slightly to 3,038,400 in January 2001, it has since risen to stand at 3,174,800 in February 2003.

Graph: Persons employed: Trend Series - New South Wales



Victoria

The trend estimate of employment in Victoria rose strongly from a low of 1,927,900 in May 1993, to 2,069,300 in June 1995. Growth then slowed until mid 1997. Since then the trend has risen steadily to stand at 2,418,200 in February 2003.

Graph: Persons employed: Trend Series - Victoria



Queensland

The trend estimate of employment in Queensland has generally been rising since February 1993, when it stood at 1,361,400. The strongest growth over this period was recorded between mid 1993 and mid 1995. Following a small decrease in late 2000, the trend has been steadily increasing and stood at 1,805,000 in February 2003.

Graph: Persons employed: Trend Series - Queensland



South Australia

The trend estimate of employment in South Australia, although fluctuating, generally rose from a low of 633,500 in February 1993 to 682,000 in August 2000. After a small decrease in late 2000, the trend estimate has risen to stand at 707,100 in February 2003.

Graph: Persons employed: Trend Series - South Australia



Western Australia

The trend estimate of employment in Western Australia has generally been rising since February 1993, when it stood at 750,300. The strongest period of growth occurred prior to mid 1995. Since then the trend estimate has increased at a slower rate, and stood at 978,200 in February 2003.

Graph: Persons employed: Trend Series - Western Australia



Tasmania

From a high of 202,200 in January 1996, the trend estimate of employment in Tasmania fell sharply to 192,200 in August 1997. The trend then generally rose to 201,700 in January 2001, before falling to 197,800 in March 2002. Since then the trend has risen to stand at 200,500 in February 2003.

Graph: Persons employed: Trend Series - Tasmania



Northern Territory

The trend estimate of employment in the Northern Territory, although fluctuating, increased from a low of 72,300 in March 1994 to 96,100 in February 1999. The trend then fell to 90,100 in June 2000, before generally rising to stand at 99,600 in February 2003.

Graph: Persons employed: Trend Series - Northern Territory



Australian Capital Territory

The trend estimate of employment for the Australian Capital Territory increased from a low of 150,600 in June 1993 to 158,700 in October 1995, before falling to 150,800 in November 1996. The trend estimate then increased to 171,000 in October 2000, before falling to 166,300 in July 2001. Since then the trend has generally increased to stand at 173,900 in February 2003.

Graph: Persons employed: Trend Series - Australian Capital Territory



Australia

The trend estimate of employed persons generally rose from a low of 7,634,000 in January 1993 to 9,129,300 in September 2000. The trend then fell to 9,112,900 in December 2000, before rising to stand at 9,559,600 in February 2003.

Graph: Persons employed: Trend Series - Australia



PRINCIPAL LABOUR FORCE SERIES: TREND SERIES

Unemployment

The trend estimate of unemployed persons peaked at 920,600 in September 1993, before falling rapidly to 728,100 in July 1995. The trend then rose slowly reaching 771,800 in February 1997, before falling to 590,900 in September 2000. The trend then rose to 675,900 in October 2001, before falling to stand at 614,400 in February 2003.

Graph: Unemployment: Trend series



Unemployment Rate

The trend unemployment rate fell rapidly from 10.7% in August 1993 to 8.1% in July 1995. The trend then rose slowly until February 1997, before falling to 6.1% in September 2000. The trend rate then rose to 6.9% in September 2001, before falling to 6.0% in February 2003.

Graph: Unemployment Rate: Trend Series



Participation Rate

The trend estimate of the participation rate rose from 62.3% in April 1993 to 63.7% in November 1995. Apart from a small increase in mid 1998, the trend then generally fell to 63.0% in April 1999. The trend then increased to 63.8% in July 2000, and remained relatively steady for two years. The trend has since risen to stand at 64.5% in February 2003.

Graph: Participation Rate: Trend Series