Retail Trade Survey: November 2008

All references to sales movements are to seasonally adjusted series unless otherwise stated.

November 2008

Seasonally adjusted total retail sales increased by less than 0.1 percent (less than $1 million) in November 2008 compared with October 2008, following a fall of 1.3 percent in October.

Core retailing, which excludes the four vehicle-related industries, increased by 0.3 percent ($11 million), dominated by supermarket and grocery stores, which rose 2.6 percent ($32 million). This rise was partly offset by falls in accommodation, down 6.6 percent ($15 million) and appliance retailing, down 3.0 percent ($6 million).

The biggest dollar value movements in November 2008 were in vehicle-related industries. On-going volatility in motor vehicle retailing saw a rise of 6.9 percent ($37 million) this month, and a fall in automotive fuel retailing of 7.3 percent ($44 million) reflected lower fuel prices.

Three-quarters of the 24 industries surveyed had sales movements, up or down, of less than $5 million.

Sales trend

The trend in total retail sales was flat. However, the cumulative effect of very small monthly movements has resulted in a decline of 1.0 percent since January 2008. Before this decline the total retail sales trend had been rising since May 1998.

The core retail sales trend has been rising since September 1995, at an average of 0.4 percent per month. However, in the last year and a half, the rate of increase has flattened to a monthly average of 0.2 percent. The last time the core retail trend remained flat for a similar length of time was between mid-1997 and mid-1998.

Motor vehicle retailing

Continued volatility in motor vehicle retailing sales saw a rise of 6.9 percent ($37 million) in November 2008, following a fall of 14.5 percent in October and a rise of 6.1 percent in September.

The trend in motor vehicle retailing sales has been declining since September 2007. The rate of decline between January and July 2008 was the most rapid since the series began in May 1995. However, since July the rate of decline appears to have slowed. The trend remains at its lowest level since September 2001.

Automotive fuel retailing

Automotive fuel retailing sales fell 7.3 percent ($44 million) in November 2008, the biggest monthly fall since the series began in May 1995. This follows a fall of 2.4 percent in October 2008. The lower sales reflect the continuing decreases in the pump prices of petrol and diesel.

The trend in automotive fuel retailing sales has been declining since July 2008 and has fallen 3.0 percent since then.

Supermarket and grocery stores

Supermarket and grocery store sales increased 2.6 percent ($32 million) in November 2008, the biggest monthly increase since February 2007, when sales increased 3.1 percent. The latest month’s increase follows a decrease of 1.0 percent in October 2008.

The trend in supermarket and grocery store sales was flat during the middle part of 2008 but appears to have strengthened since then. However, initial estimates may be revised and should be used with caution until more data points are available

Accommodation

The biggest dollar value fall in the core retail industries in November 2008 was in accommodation, down 6.6 percent ($15 million). This month's fall is the biggest in accommodation since June 2006; it follows a rise of 5.5 percent in October 2008.

The trend in accommodation sales has been rising since February 2000.

Regional estimates

In November 2008 compared with October 2008, sales increased in the North Island and decreased in the South Island. Changes in sales for each region were as follows:

• Auckland up 0.5 percent ($9 million)
• Waikato up 2.8 percent ($14 million)
• Wellington down 1.1 percent ($7 million)
• Remainder of the North Island down 0.1 percent ($2 million)
• Canterbury up 0.1 percent (less than $1 million)
• Remainder of the South Island down 1.1 percent ($8 million).

In Wellington and Canterbury, sales trends continue to increase, although the rate of increase in Canterbury is slowing. Sales trends are declining in Auckland (since November 2007), the remainder of the North Island (since February 2008), and the remainder of the South Island (since March 2008).

In Waikato, between May and September 2008, the sales trend was positive but easing. Since September there are signs that the trend may have begun to decline. However, initial estimates may be revised and should be used with caution until more data points are available.

Note: The trend series in the graph above have been indexed to a base: September 2004 (=1000) for the purpose of comparing regional trends over four years.

Revisions

There were no revisions to the Retail Trade Survey in the November 2008 month.

Comparison statistics

For November 2008 compared with October 2008:

• The Food Price Index rose 0.8 percent.
• New registrations of cars and station wagons (including cars previously registered overseas) fell 23.2 percent to 10,821.
• Seasonally adjusted short-term overseas visitor arrivals rose 0.8 percent.
• The seasonally adjusted value of the retail Electronic Card Transaction (ECT) series fell 2.3 percent, and the seasonally adjusted value of the core retail ECT series fell 0.5 percent.

Long-term comparison:

• Credit card billings in New Zealand (including spending using New Zealand and overseas-issued cards) were down 7.7 percent compared with November 2007.

Other:

• The Reserve Bank of New Zealand's Official Cash Rate was 6.50 percent during November 2008.

Measurement errors

All statistical estimates are subject to measurement errors. These include both sample errors and non-sample errors. In addition, the survey applies imputation methodologies to cope with small firms and non-response. These measurement errors should be considered when analysing the results from the survey. For more information on measurement errors, please refer to the technical notes of this release.

Sample errors

The postal survey was designed to give statistics at the following levels of accuracy (at the 95 percent confidence interval limit):

• 2 percent for sales at the total national retail trade level
• 10 percent for sales at the published national retail industry level.

This means, for example, that there is a 95 percent chance that the true value of total retail trade sales lies within 2 percent of the published estimate.

At the industry level, the following sample errors occurred in the November 2008 month (at the 95 percent confidence interval limit): 

Imputation

Small firms

Small to medium-sized firms are generally not surveyed. Their variables are instead modelled from administrative data (GST) sourced from Inland Revenue. Ratios calculated from the postal sample units are applied to the administrative data to provide an estimate of their variables.

Non-response imputation

Although every attempt is made to achieve a 100 percent response rate, in practice this does not occur. Values for non-responding businesses are estimated by a number of methods, including:

• regression imputation
• historic imputation
• mean imputation.

Regression imputation involves estimating sales from the unit's administrative data (GST sales) based on the relationship shown by similar businesses. Historic imputation involves multiplying their response in the previous period by a non-response factor. The non-response factor is the average movement of similar businesses over the month. Mean imputation involves estimating a value for a unit by using the average value for a set of similar businesses.

Postal response rate

The table below indicates the percentage of sales imputed in the November 2008 month:

For technical information contact: 
Chris Stephenson or Ken Smart 
Christchurch 03 964 8700
Email: info@stats.govt.nz.

Next release ...

Retail Trade Survey: December 2008 quarter will be released on 13 February 2009.