FULL-TIME AND PART-TIME WORKERS
Prior to 2002 'full-time or part-time employees in main job' was derived from a self perception question in which all employees were asked 'Is your job full-time or part-time?'. Following the redesign in 2001 of the LFS questionnaire, actual hours worked in main job in the reference week is now collected. From August 2002, data on hours worked in main job are now used to derive full-time or part-time status of employees in main job.
This approach is consistent with the method used in the LFS to derive full-time or part-time status in all jobs. For further details see Glossary entries 'Full-time employees in main job' and 'Full-time workers' in the Employee Earnings, Benefits and Trade Union Membership publication.
Information relating to main and second job earnings that were not provided by respondents have been imputed. Where this was the only information missing from the record, a value has been imputed based on answers provided from another respondent with similar characteristics (referred to as the donor). Donor records were selected for main job imputation by matching information on sex, age, state or territory of usual residence and labour force characteristics (full-time or part-time in main job, industry, occupation, hours worked in main job) of the person with missing information. Donor records were selected for second job imputation by matching information on sex, age, state or territory of usual residence, area of usual residence and owner manager status. Depending on which values are to be imputed, donors are chosen from the pool of individual records with complete information for the block of questions where the missing information occurs.
In 2004, imputation was conducted for main job earnings only. Prior to 2004, imputation was not used, hence employees whose weekly earnings could not be determined were excluded from estimates of mean and median weekly earnings.
The differences between the imputation method used in 2004 and the current imputation methods are that the donors records are now matched, where possible, on a finer level of detail, including but not limited to, sex, state, and age of respondent, whereas in 2004 they were not. These changes in methodology are expected to have improved the imputed earnings data at the unit record level, but should not have much impact on aggregate estimates.
From 2005, imputation has been conducted for both main and second job earnings.
From 2007, as a result of a change in the concept of earnings being measured, employees were asked to include salary sacrifice when estimating their earnings in their main job, and for multiple jobholders, in their second job. In previous years, there has not been any explicit reference to the treatment of salary sacrifice, yet it is probable that some employees were already including amounts of salary sacrifice in their estimates of earnings, depending on how their pay was reported. As a result of this change there has been a break in series.