The LFS is based on a multi-stage area sample of private dwellings and a list sample of non-private dwellings and covers about 0.45% of the population of Australia. Households are interviewed each month for eight months, with one-eighth of the sample being replaced each month. In February 2006, the number of fully responding individuals was 63,831.
The Labour Mobility survey is conducted on 7/8ths of the LFS sample and covers both urban and rural areas in all states and territories, but excludes people living in very remote areas of Australia. Information is collected about people aged 15 years and over who, within the 12 months to February 2006, either had a change of employer/business in their main job, or had some change in work with their current employer/business for whom they had worked for one year or more. In February 2006, the number of fully completed interviews (after taking into account scope, coverage and subsampling exclusions) was 35,637.
The scope of the LFS was people aged 15 years and over and excluded the following:
Additional exclusions for the Labour Mobility survey were:
- members of the permanent defence forces
- certain diplomatic personnel of overseas governments, customarily excluded from the census and estimated population counts
- overseas residents in Australia
- members of non-Australian defence forces (and their dependants).
- students at boarding schools
- institutionalised persons (e.g. patients in hospitals; residents of homes, such as retirement homes and homes for persons with disabilities; and inmates of prisons)
- persons living in very remote parts of Australia who would otherwise have been within scope of the survey. The exclusion of these persons will only have a minor impact on any aggregate estimates that are produced from the Labour Mobility survey for individual states and territories, with the exception of the Northern Territory where such persons account for around 23% of the population.
WEIGHTING ESTIMATION AND BENCHMARKING
Weighting is the process of adjusting results from a sample survey to infer results for the total population. To do this, a weight is allocated to each sample unit. The weight is a value which indicates how many population units are represented by the sample unit. Separate weights were calculated for LFS and Labour Mobility samples (as some units were in scope for LFS but not for Labour Mobility). The LFS weighting method ensures that LFS estimates conform to the benchmark distribution of the population by age, sex and geographic area, and also LFS region by sex (two sets of benchmarks). Weights are allocated to each sample respondent according to their state/territory of selection, state/territory of usual residence, part of state of usual residence, age group and sex. The weights are calculated using the inverse of the probabilities of selection, adjusted for any under-enumeration and non-response.
The Labour Mobility survey is benchmarked to LFS estimates for the following variables: state of usual residence, part of state of usual residence, sex, age group and labour force status.
Benchmarking to LFS estimates accounts for the one eighth of the sample where the Labour Mobility survey is not conducted and for non-respondents to the Labour Mobility survey. The Labour Mobility survey weighting excludes all residents in institutions, boarding schools, and very remote areas because the sample scope excludes these people.
Survey estimates of the number of people with a particular characteristic are obtained by summing the weights of people who have that characteristic.
For more information on weights, see Using the CURF Microdata.
RELIABILITY OF THE ESTIMATES
Since the information on the CURF is based on information from a sample of dwellings, any statistics produced from the CURF will be subject to sampling error and non-sampling error.
Sampling error is the difference between the survey estimate and the value that could have been produced had all dwellings in scope of the survey been included. One measure of the likely difference is given by the standard error (SE), which indicates the extent to which an estimate might have varied because only a sample of dwellings was included.
There are about two chances in three (67%) that a sample estimate will differ by less than one SE from the number that would have been obtained if all dwellings had been included, and about 19 chances in 20 (95%) that the difference will be less than two SEs. Another measure of the likely difference is the relative standard error (RSE), which is obtained by expressing the SE as a percentage of the estimate. Generally, only estimates with RSEs less than 25% are considered sufficiently reliable for most purposes.
Tables of standard errors are provided in the Technical Notes of the publications Labour Force Survey, Australia, February 2006 (cat. no. 6202.0) and Labour Mobility, Australia, February 2006 (cat. no. 6209.0), which are provided on the CURF CD-ROM. These figures do not give a precise measure of the SE for a particular estimate but will provide an indication of its magnitude.
Non-sampling error arises from inaccuracies in collecting, recording and processing the microdata. These inaccuracies may occur in any enumeration, whether it be a full count or a sample. Every effort is made to keep the non-sampling error to a minimum by careful design of questionnaires, intensive training and supervision of interviewers, and effective processing procedures.
Estimates are based on information collected in the survey month, and, due to seasonal factors, they may not be representative of other months of the year.
Further information on the survey methodology can be found in: