6302.0 - Average Weekly Earnings, Australia, May 2014 Quality Declaration
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 14/08/2014
|Page tools: Print Page Print All|
IN THIS ISSUE
TREATMENT OF SURVEY OUTLIERS
Since the beginning of the survey, surprise outliering has been used as the sole methodology to identify and reduce the impact on the estimates of a business whose weighted survey response is an outlier i.e significantly different to businesses in a group with similar characteristics (based on employment size, state and industry). Surprise outliering involves treating the identified outlier as if it were the only extreme unit in the group's population. The outlier is given a weight of one and the weights of the other units in the group are adjusted upwards accordingly. From the May 2014 issue, winsorisation methodology has been introduced as the primary method to treat outliers in AWE. Winsorisation moderates the impact of an outlier business without the harsh impact of the surprise outliering approach. This improved methodology will provide more stable time series estimates. Surprise outliering will continue to be used for a small number of extreme values that may not be sufficiently moderated by the winsorisation method. For further information, see paragraphs 36 to 38 of the Explanatory Notes.
The frequency of the average weekly earnings series changed from quarterly to biannual in 2012. The May 2012 publication was the final quarterly issue and the November 2012 the first produced on a biannual basis. For full details on the change in frequency, refer to the Information Paper: Changes to Average Weekly Earnings, Australia, April 2012 (cat. no. 6302.0.55.002).
SEASONALLY ADJUSTED AND TREND ESTIMATES
As part of the transition to a biannual frequency, an assessment was conducted in 2012 on the feasibility of releasing biannual seasonally adjusted and trend estimates. It was determined that reducing the frequency of collection did not eliminate observed seasonality for some time series leaving 27 biannual series needing seasonal adjustment. All other series are no longer seasonally adjusted and where this is applicable the seasonally adjusted estimate will be exactly equal to the original series estimate. Relevant series are annotated in the time series spreadsheets.
In addition, the change in frequency resulted in a slight change in the level of seasonally adjusted and trend estimates and, therefore, new series were produced and first released in the November 2012 edition. The series commence with May 2012 data. Those users seeking historical seasonally adjusted and trend estimates will be required to access past AWE editions, which are available by clicking the past and future releases tab at the top of this page. It is advised that seasonally adjusted and trend estimates produced before and after the May 2012 edition are not directly comparable. For further details on seasonally adjusted and trend estimates, refer to paragraphs 55 to 64 in the Explanatory Notes.
These documents will be presented in a new window.