8508.0 - Information Paper: Seasonal Influences on Retail Trade, 1998  
ARCHIVED ISSUE Released at 11:30 AM (CANBERRA TIME) 01/03/1999   
   Page tools:

INTRODUCTION

1. The December 1998 release of Retail Trade, Australia (ABS Cat. No. 8501.0) recorded growth for the last six months of 1998 as follows:

Table 1 RETAIL TURNOVER ESTIMATES, AUSTRALIA, % CHANGE FROM PREVIOUS MONTH
Original
Seasonally adjusted
Trend estimates
    1998
    July
7.0
2.6
0.6
    August
-3.2
-0.8
0.6
    September
1.6
0.8
0.5
    October
7.2
1.0
0.3
    November
-1.2
0.3
0.2
    December
27.8
-2.1
0.1

2. Some economic commentators queried the seasonally adjusted estimate for December 1998. Their main concerns can be summarised as:
  • the ABS' seasonal adjustment process is not sophisticated enough to reflect changes in shopping patterns,
  • the trading day adjustment is not appropriate for December because Christmas shopping is undertaken regardless of the day of the week Christmas falls on, and
  • the seasonally adjusted estimates for December will be revised upwards.

3. The purpose of this information paper is to address these concerns and to test some of the resulting hypotheses about the Retail turnover estimates.

4. Estimates of Retail turnover in this paper are obtained from the Retail Business Survey which includes: most retailing industries (the most notable exceptions being motor vehicles, boats and service stations); hotels, clubs, cafes, restaurants; and other selected service industries. The Food retailing and Hospitality and services industry groups contribute over 50% of total Retail turnover. The Household good retailing, Other retailing and Department stores groups contribute about another 30% to total turnover.

5. All employing businesses with at least one retail establishment are included in the scope of the survey. All 'large' businesses are included in the survey every month and these businesses contribute approximately 54% of the total turnover estimate.

6. Background material in this paper has been drawn from several articles previously released in Australian Economic Indicators (cat. No 1350.0):
  • A guide to interpreting Time Series (January 1995)
  • Seasonal and Trading Day Influences on Retail Turnover (April 1996)
  • How does Father's Day affect Retail Trade? (December 1996)

Conclusion

There have been criticisms of the accuracy of the December 1998 estimates of retail turnover. Investigations have indicated that the ABS' seasonal adjustment method is sound and accurately reflects historical seasonal and trading day patterns.

Alternative non-data based assumptions could be made in making seasonal adjustments. For example, we could assume there is only a length of month effect in December but even this alternative indicates a decline in seasonally adjusted retail sales between November and December 1998. Nevertheless, the ABS will continue to review the seasonal adjustment methods it uses. One potential area of investigation is revising seasonal adjustment monthly rather than annually.

All time series show some degree of irregularity. Indications are that the December 1998 estimate of monthly retail turnover had a higher than average irregular component. The ABS publishes trend series to help users assess the underlying trend in the face of irregularities in time series.