Information about the Retail Trade Survey

Document Map

Jump to: Availability

Jump to:Design

Jump to:Output Variables

Jump to:Guide To Interpreting Data

Jump to:Customised Output

Jump to:Catalogue & Reference Numbers

Jump to:Commercially Available Tables

Jump to:Other Comments

Jump to:Classification(s) Used

Jump to:Glossary of Terms

Jump to:Contact Details

Availability

Valid From: ..	03/31/1954
To: ..	Ongoing
Frequency: ..	Monthly

---

Design
Purpose: The purpose of the survey is to provide a leading indicator of economic activity. Results from the survey provide a valuable guide to retail trading and general economic conditions within New Zealand.

General Information ..
Target Population

The target population for this survey is all Geographic Units (GEOs) operating in New Zealand that are classified on Statistics New Zealand's Business Frame (BF) to the Australian and New Zealand Standard Industrial Classifications (ANZSIC) below:

• Retail Trade (ANZSIC division G),
• Accommodation, Cafes and Restaurants (ANZSIC division H), or
• Personal Services (ANZSIC subdivision 95 of division Q).

Only enterprises with a turnover of $30,000 or more are eligible for selection.

The Retail Sector is defined as those businesses primarily selling goods and services to final consumers. Therefore in addition to households it includes expenditure by:
- non-private households living in hotels, boarding houses, hospitals etc.
- businesses, clubs, trusts and other purchasers outside the household sector
- expenditure by overseas residents while visiting New Zealand.

Industry descriptions
A geographic unit is included in an industry based on its predominant activity in terms of sales. For example, a footwear store will sell shoes and boots, but it may also sell bags and other accessories. It will be classified to the footwear industry if most of its sales income comes from the sale of shoes. The 24 industries are defined as follows:

Industry	ANZSIC Code
G0111 Supermarket and grocery stores	G511010 Supermarkets
	G511020 Groceries and dairies
G0121 Fresh meat, fish, poultry, fruit & vege retailing	G512100 Fresh meat, fish and poultry retailing
	G512200 Fruit and vegetable retailing
G0122 Liquor retailing	G512300 Liquor retailing
G0123 Other food retailing	G512400 Bread and cake retailing
	G512600 Milk vending
	G512900 Specialised food retailing nec
G0124 Takeaway food retailing	G512510 Fish and chips, hamburger and ethnic food takeaway stores
	G512520 Chicken takeaway stores
	G512530 Ice-cream parlours and mobile ice-cream vendors
	G512540 Pizza takeaway stores
	G512590 Other takeaway food stores (including sandwiches and savouries) nec
G0131 Department stores	G521000 Department stores
G0141 Furniture and floor coverings retailing	G523100 Furniture retailing
	G523200 Floor covering retailing
G0142 Hardware retailing	G523300 Domestic hardware and houseware retailing
G0143 Appliance retailing	G523400 Domestic appliance retailing
	G523500 Recorded music retailing
G0144 Recreational goods retailing	G524100 Sport and camping equipment retailing
	G524200 Toy and game retailing
	G524300 Newspaper, book and stationery retailing
	G524400 Photographic equipment retailing
	G524500 Marine equipment retailing
G0151 Clothing and softgoods retailing	G522100 Clothing retailing
	G522300 Fabrics and other soft good retailing
G0152 Footwear retailing	G522200 Footwear retailing
G0153 Chemist retailing	G525100 Pharmaceutical, cosmetic and toiletry retailing
G0154 Household equipment repair services	G526100 Household equipment repair services (electrical)
	G526900 Household equipment repair services nec
G0159 Other retailing	G525200 Antique and used good retailing
	G525300 Garden supplies retailing
	G525400 Flower retailing
	G525500 Watch and jewellery retailing
	G525900 Retailing nec
G0161 Motor vehicle retailing	G531100 Car retailing
	G531200 Motor cycle dealing
	G531300 Trailer and caravan dealing
G0162 Automotive fuel retailing	G532100 Automotive fuel retailing
G0163 Automotive electrical services, smash repairing and tyre retailing	G532200 Automotive electrical services
	G532300 Smash repairing
	G532400 Tyre retailing
G0164 Automotive repair and services nec	G532900 Automotive repair and services nec
H0111 Accommodation	H571010 Hotels (accommodation)
	H571020 Motels and motor inns
	H571030 Hosted accommodation
	H571040 Backpacker and youth hostels
	H571050 Caravan parks and camping grounds
	H571090 Accommodation nec
H0121 Bars and clubs	H572000 Pubs, taverns and bars
	H574000 Clubs (hospitality)
H0122 Cafes and restaurants	H573000 Cafes and restaurants
Q0111 Personal and household goods hiring	Q951100 Video hire outlets
	Q951900 Personal and household goods hiring nec
Q0112 Other personal services	Q952100 Laundries and dry-cleaners
	Q952200 Photographic film processing
	Q952300 Photographic studios
	Q952400 Funeral directors, crematoria and cemeteries
	Q952500 Gardening services
	Q952600 Hairdressing and beauty salons
	Q952900 Personal services nec

Note: nec = not elsewhere classified

Retail Trade Regional Council Areas

	TLA	Region
Auckland Regional Council Area
Rodney District	4	1
North Shore City	5	1
Waitakere City	6	1
Auckland City	7	1
Manakau City	8	1
Papakura District	9	1
Franklin District*	10	1 and 2
Waikato Regional Council Area
Franklin District*	10	2 and 1
Thames-Coromandel District	11	2
Hauraki District	12	2
Waikato District	13	2
Matamata-Piako District	15	2
Hamilton City	16	2
Waipa District	17	2
Otorohanga District	18	2
South Waikato District	19	2
Waitomo District*	20	2 and 4
Taupo District*	21	2 and 4
Rotorua District*	24	2 and 4
Wellington Regional Council Area
Tararua District	41	3
Kapiti Coast District	43	3
Porirua City	44	3
Upper Hutt City	45	3
Lower Hutt City	46	3
Wellington City	47	3
Masterton District	48	3
Carterton District	49	3
South Wairarapa District	50	3
Remainder of North Island
Far North District	1	4
Whangarei District	2	4
Kaipara District	3	4
Waitomo District*	20	4 and 2
Taupo District*	21	4 and 2
Western Bay of Plenty District	22	4
Tauranga District	23	4
Rotorua District*	24	4 and 2
Whakatane District	25	4
Kawerau District	26	4
Opotiki District	27	4
Gisborne District	28	4
Wairoa District	29	4
Hastings District	30	4
Napier City	31	4
Central Hawkes Bay District	32	4
New Plymouth District	33	4
Stratford District	34	4
South Taranaki District	35	4
Ruapehu District	36	4
Wanganui District	37	4
Rangitikei District	38	4
Manawatu District	39	4
Palmerston North City	40	4
Tararua District	41	4
Horowhenua District	42	4
Canterbury Regional Council Area
Kaikoura District	54	5
Huranui District	58	5
Waimakairi District	59	5
Christchurch City	60	5
Banks Peninsula District	61	5
Selwyn District	62	5
Ashburton District	63	5
Timaru District	64	5
Mackenzie District	65	5
Waimate District	66	5
Waitaki District*	68	5 and 6
Remainder of South Island
Tasman District	51	6
Nelson City	52	6
Marlborough District	53	6
Buller District	55	6
Grey District	56	6
Westland District	57	6
Waitaki District*	68	6 and 5
Cental Otago District	69	6
Queenstown Lakes District	70	6
Dunedin City	71	6
Clutha District	72	6
Southland District	73	6
Gore District	74	6
Invercargill City	75	6

Districts that do not fall completely into one region have been indicated with an asterisk.

Statistical Unit

Geographic Unit (GEO)

Statistical Units and the Business Frame
Prior to December 1996 the survey was selected from the Business Directory (BD). The Business Frame (BF) superseded the BD in December 1996. The statistical units on the BF are enterprises, kind-of-activity units and geographic units. These replace enterprises, accounting units and activity units, respectively, on the BD. The underlying concepts are unchanged.

Selection Unit

Enterprise

Enterprises on the BF considered for selection are those that have one or more retailing geographic units and have an annual GST turnover of more than $30,000. If an enterprise is selected then all of its retail geographic units are included in the survey.

Collection Unit

Geographic Unit

Under Coverage

The retail trade survey does not include:

• Property and dwelling rents
• Purchase of houses
• Property maintenance services
• Electricity and gas
• Public transport, local and overseas
• Medical services
• Leisure and recreational services
• Insurance services
• Enterprises that do not meet the significance criteria in terms of GST turnover.

Population and Sample Size

About 3,500 enterprises (between 9,000 and 10,000 GEOs) have been selected in the postal sample from the entire population, and approximately 37,000 enterprises have their data modelled from tax data.

Seasonal Adjustment

The seasonally adjusted series is what we would expect if no climatic or calendar effects were present. To allow direct comparison between figures from different periods, seasonally adjusted retail sales are published. The X12-ARIMA package is used to produce the seasonally adjusted and trend estimates, from August 1998 onwards. This is an upgrade of the X11-ARIMA package which was previously used. All seasonally adjusted figures are subject to revision each month. The industry series have always been seasonally adjusted, while the regional series were first seasonally adjusted for the November 1998 month.

Trend Estimates

A trend estimate is one in which both the seasonal and irregular components have been removed. Trend estimates reveal the underlying direction of movements in a series. Trend estimates indicate turning points more accurately than seasonally adjusted estimates. The retail trade trend series is also calculated using the X12-ARIMA seasonal adjustment package (X11-ARIMA prior to August 1998). It is based on optimal weighted moving averages of the seasonally adjusted series with an adjustment for outlying values. Trend estimates towards the end of the series incorporate new data as it becomes available and can therefore change as more observations are added to the series. Revisions can be particularly large if an observation is treated as an outlier in one period, but is found to be part of the underlying trend as further observations are added to the series. All trend estimates are subject to revision each month but normally only the last two or three estimates are likely to be substantially altered.

Retail Trade Deflators

In the Consumers Price Index (CPI) a basket of goods and services is taken and the price changes for that basket are measured. When retail sales are altered for price changes, a smaller basket of goods than the CPI is used. These are called the retail trade price deflators. The deflators were updated during the 2003 redesign of the Retail Trade Survey and again, in the September 2006 quarter, following a major review of the CPI.

Constant Price Estimates

A constant price estimate, is one in which the portion of a sales movement caused by price changes has been removed. It is calculated by dividing the sales series by a price deflator.

Starting with the December 2006 quarter, the methodology used to calculate the retail trade survey constant price series changed. Under the new methodology the current price series is divided by the price deflator, and then the seasonal adjustment and trend estimate steps are performed. Before December 2006 the current price series was seasonally adjusted prior to the figures being deflated to create the constant price series. The new methodology, deflating the current price series before calculating seasonal adjustment and trend estimates, removes any residual seasonality that may be introduced by the deflators.

The new methodology has been applied to all time periods since September 1995.

Linking

When the survey was redesigned in 2003, adjustments were made as part of the linking process to account for differences in the two surveys arising from the removal of the estimated effect of the decay in the old series. There was a dual run of the old and new surveys in the August, September and October 2003 months.

"Linking" essentially is smoothing back estimates obtained from the new up-to-date sample to adjust the old survey results for the deterioration due to "decay" in the old survey. A sample is said to "decay" as it may not reflect all the structural changes occurring in the economy, with the passage of time.

The linked series represents data obtained from the new survey population/industry/region. This series includes estimated (backcast) values for periods prior to the start of the new survey in the October 2003 month. The linked series is back-cast to May 1995.


EA/RT/01T for sales from single and multi geographic unit enterprises in monthly Retail Trade Survey
EA/RT/01ST for sales and stocks from single and multi geographic unit enterprises in monthly Retail Trade Survey

---

Output Variables

Output variables are pieces of individual information that can be extracted from the survey/output data. Often output variables can be cross tabulated with other output variables, for example sales by industry classification. The list below contains all current and past output variables which have been released for this survey/output.

Variable Name	Description
Sales	Derived variable. The value of sales of goods and services for the month or quarter (linecode 0100). Sales are released by industry in actual, seasonally adjusted, constant price, and per capita terms, and by region in actual and seasonally adjusted terms. A quarterly trend series which removes seasonal and irregular effects is also produced. The sales value for each industry is calculated by summing all the weighted sales values for each unit in the industry. The weighted value for each unit is calculated by multiplying the sales value for each unit by the weight on the unit record dataset. NB. Sales are GST exclusive.
Stocks	Derived variable. Trading stocks, finished goods and work in progress, materials, fuels etc. on hand at the end of the quarter. Stocks are released by industry. The stocks value for each industry is calculated by summing all the weighted stocks values for each unit in the industry. The weighted value for each unit is calculated by multiplying the stocks value for each unit by weight.
Deflators	Derived Variable Retail trade deflators are maintained for each industry and are available on a quarterly basis. Retail trade deflators are based on subgroups of the consumers price index.
Industry	Classification Variable
	The Retail Trade Survey is classified by 24 industries. These are: Supermarket and grocery stores , Fresh produce retailing, Liquor retailing, Other food retailing, Takeaway food retailing, Department stores, Furniture and floor coverings retailing, Hardware retailing, Appliance retailing, Recreational goods retailing, Clothing and softgoods retailing, Footwear retailing, Chemist retailing, Household equipment repair services, Other retailing, Motor vehicle retailing, Automotive fuel retailing, Auto electric services, smash repair and tyre retailing, Auto repairs and services nec, Accommodation, Bars and clubs, Cafes and restaurants, Personal and household goods hiring, Other personal services.
Region	Classification Variable The Retail Trade Survey is classified by six geographic regions. These are: the Auckland regional council area; the Waikato regional council area; the Wellington regional council area; the remainder of the North Island; the Canterbury regional council area; and the remainder of the South Island.

Changes in Output Variables over time

---

Guide to Interpreting Data

Summary of Changes to Survey/Output ..Leap year adjustments - March quarter 2000

An adjustment has been introduced to remove the effect of the extra day in the leap year March quarters from the seasonally adjusted sales series. The method chosen was to apply a factor of 91/90 to the actual sales data for the 91 day leap year quarter before performing the seasonal decomposition. The modal number of days was used in quarter 1 (90 days) in preference to the mean number (90.25 days) to represent the average quarter 1. This method also treats every day of the week as having equal influence on the sales figure.

Trading day adjustments, as used in the monthly series, were considered . However, the quarterly series is too short to produce reliable X-12-ARIMA-generated trading day weights, and the monthly trading day weights were inappropriate for the X-12-ARIMA decomposition of the quarterly series. Another option considered was to apply factors to each of the March quarters to achieve standard 90.25 number of days. This had the disadvantage of affecting a leap year adjustment to all of the March quarters' seasonally adjusted series - both leap year and non-leap year.

An adjustment was introduced because without it the estimate for movements can be misinterpreted. The March 2000 quarter has 1 percent extra days compared with most other March quarters. This calendar effect would appear in the irregular component, thereby inflating the seasonally adjusted value for the March 2000 quarter. By adopting this method of adjusting for this calendar effect, a more meaningful estimates of the sales movement is available.

September 2003 Re-Design

The previous RTS series was based on a statistical sample that was first surveyed in the May 1995 month. The last month of the old RTS was the October 2003 month. The RTS was a panel survey. Businesses had one chance of selection at their birth, and those that were introduced then remained in the sample until either they ceased operation in the retail industry or the panel was reselected. If a business changed owner but stayed within the retail industry then this business stayed within the sample.

Over time, sample designs become less effective in representing the current population. While the original samples are maintained to include a representative selection of new businesses, periodically, panel samples need to be refreshed to reflect changes in the composition of the population.

The RTS was redesigned in 2003 to provide better and more up-to-date coverage of the retail population. The new RTS design will, over time, allow changes in the composition of the population to be better represented in the survey.

Changes to the RTS included:

• a redesign of the survey questionnaire;
• additional industry detail as the basis for the sample design;
• the use of administrative (tax) data for small to medium-sized businesses in place of direct surveying;
• the adoption of periodic re-selection of the survey sample population;
• the use of bi-variate stratification in the sample design;
• improvements in non-response imputation methodologies.

These changes were made to ensure that the future estimates produced from the RTS continue to accurately reflect activity in the retail sector of the New Zealand economy.

During the August, September and October 2003 months the RTS was calculated on both the old and new basis. The primary purpose of this 'dual run' was to enable the comparison of the surveys run under the previous and redesigned methods, so that the two series could be linked at a single point in time. This facilitated the production of an analytical back series for the redefined output industries. Another important function of the dual run was to measure level shifts in the results coming from the two different designs, so that the results can be verified and explained.

The dual run exercise highlighted the importance of undertaking regular reselection of panel surveys in order to maintain their representativeness of the contemporary population.

September 2006 - Change to RTS price deflators

In the September 2006 quarter the Retail Trade Survey price deflators were updated, following the implementation of a major review of the Consumers Price Index (CPI).

The deflator for each RTS industry consists of a basket of indexes drawn mainly from the CPI, which measures the rate of price change of goods and services purchased by households. In a few RTS industries, prices collected via the Commodity Price Survey (CPS) – which is used for the Producers Price Index (PPI) – are also used. The PPI outputs index measures changes in the prices received by producers. The CPI indexes and CPS indicators in each deflator's basket represent the goods and services sold by the industry and are weighted to reflect the mix of goods and services sold by the industry.

The CPI review involved updating and reweighting the basket of representative goods and services, and adopting a new expenditure classification. As a result of the CPI review, the regimen and weights of the RTS deflators were also updated although the deflators continue to be expressed on a base of September 1995 quarter (=1000).

December 2006 - Change in constant price calculation

In the December 2006 quarter there was a change in the methodology used to calculate the seasonally adjusted and trend series at September 1995 prices.

Under the new methodology, the seasonal adjustment step is performed after the figures have been deflated to create the constant price series. This removes any residual seasonality that may be introduced by the deflators. Previously, the current price series were seasonally adjusted prior to the figures being deflated to create the constant price series.

The new methodology has been applied to all time periods since September 1995. The change in methodology affects all series on tables 8 and 10 of the quarterly Retail Trade Survey (RTS) releases, as well as the retail sales per head of population at September 1995 prices series on table 4. The new series have been given new series identifiers (see table below) to distinguish them from the old series. The series on table 6 (Actual retail sales at September 1995 prices) are not affected by the new methodology. However, the series identifiers on this table have been changed to maintain consistency between the deflated series.

History

A retail sales and stocks collection was first attempted in 1948 with the New Zealand Retailers Federation. Because of the poor response to the monthly survey, it was abandoned.

Cabinet approval was given to conduct the first quarterly retail trade survey for the three months ended March 1954. The sample was based on the 1953 Census of Distribution. The samples were subsequently re-selected and based on the 1958 and 1968 Censuses of Distribution, respectively. Thirteen different questionnaires were used to cover all storetypes in the initial survey. One questionnaire is used now. The stratification used in the sample selection was the 11 storetype groups, by turnover sizes and by broad locality groups.

The quarterly sample surveys of retail trade were taken until the 1969 December quarter. They were replaced in January 1970 by a monthly sample, with results aggregated to provide quarterly figures.

A redesigned sample, producing statistics for 15 storetypes, was introduced in July 1982. Restaurants and Takeaways, previously part of the Other Food group, formed a separate storetype group and three new storetypes (accommodation, automotive fuel and repairs and liquor) were added giving a total of 15 storetype groups.

Statistics New Zealand introduced a revised sample of stores and made other technical changes to the retail trade survey in March 1990. The changes made resulted in improved statistics on retail activity in New Zealand. In contrast to the previous survey sample, which was based on a random sample of small geographical clusters of area units, the sample was drawn from the business directory, a comprehensive and up-to-date list of all businesses in New Zealand. The use of the business directory as the sample frame, ensured a comprehensive coverage of the retail sector and allowed for the timely inclusion of new businesses.

Following a review of Statistics New Zealand outputs as part of the 1991 Budget, the Minister of Statistics directed that the monthly survey be altered to a quarterly survey, as a cost saving measure. Some objections were received from those who use the survey as a short-term indicator of economic activity. Consequently from July 1992, the survey reverted to a monthly collection of sales with information on stocks being asked each quarter.

The RTS was redesigned and introduced in the May 1995 month. This redesign was undertaken for a number of reasons:

• the last re-design took place in 1990, as part of the five yearly cycle;
• there was a need to review the existing sample given that changes in the economy had occurred since the previous re-design;
• improvements in the coverage of the business directory had been made since 1990 and as the sample was drawn from the business directory, then these improvements needed to be taken into account;
• the implementation of the Australian and New Zealand Standard Industrial Classification (ANZSIC) which replaced the previous New Zealand Standard Industrial Classification (NZSIC).

The September 2003 redesign of the RTS introduced a number of methodology and design enhancements (see above).

Change to Seasonal Adjustment Process

From August 1998, the seasonally adjusted and trend estimates have been produced using X12-ARIMA. This is an upgrade of the X11-ARIMA package previously used. X12-ARIMA was implemented to ensure that the high quality of the seasonal adjustment process is maintained. The change resulted in some additional revisions to previously released figures, due to the slightly different treatment of outliers in the newer package. The series for the six broad regions (plus North Island and South Island subtotals) were first seasonally adjusted for the November 1998 month. Prior to this, only storetype and total sales were seasonally adjusted.

Usage and Limitations of the Data ..The objective of the Retail Trade survey is to provide timely, short term, key indicator statistics on the retail sector of the economy. This provides a useful short term indicator for economic analysts and policy makers.

Retail sales are used in forecasting consumer demand, economic growth, inflation, interest rates, imports, the balance of payments and the exchange rate and are used in formulating government policy and Reserve Bank monetary policy. Retail sales are also used in comparison with business and regional sales by external users.

The main limitations of the Retail Trade data are the unavailability of a commodity breakdown, and sample error and confidentiality concerns with detailed data release. Sales are classified by industry and specific sales by commodity are not available. Sample errors and confidentiality may limit the availability of the data at detailed levels of ANZSIC and by region below Regional Council Areas.

Related Data Sources ..Indicators that impact on retail activity include:

• spending on credit
• number of tourists
• building activity
• imports of consumer goods

Other data that provides similar information:

• Household Expenditure Survey
• Consumers Price Index.

Sampling 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.

Non-sampling errors Non-Sampling Errors in the survey data may result from errors in the sample frame, respondent error or mistakes made during processing survey results and non-responses. Statistics New Zealand adopts procedures to detect and minimise these types of errors but they may still occur and they are not quantifiable.

Data for the RTS is subject to revision if significant errors are detected in subsequent months.

Caveats on Release ..Data below design level

Data may be released below the design level, i.e. below industry level, but each value released must be made up of at least 30 observations. This ruling is concerned with data quality and is not related to confidentiality considerations.

This caveat is to be attached to any release of Retail Trade Survey data below design level, e.g. below publication industry.

These statistics are released with a caveat because of limitations in the data, they are of a lower standard than official statistics the Department releases. This is because the Retail Trade Survey sample is selected and weighted at the publication industry level and the release of this data is below that design level. This data is indicative only, and may be subject to revisions in the future.

---

Customised Output

Customised information such as sub-regional, sub-storetype and storetype by region estimates are available to clients. Breakdowns are available as follows: March 1990 month to April 1995 month, breakdowns consistent with the old survey totals prior to revision; April 1995 month onwards, breakdowns consistent with the new survey. Customised breakdowns are derived by utilising the "Supercross" processing tool.

---

Catalogue & Reference Numbers

---

---

Other Comments

---

Classification(s) used

---

Glossary of Terms

Term	Description
Business Directory / Business Frame	The business directory was a register of all businesses operating in New Zealand. Prior to the December 1996 month the survey was selected from the Business Directory (BD). The Business Frame superseded the BD in December 1996. The statistical units on the BF are Enterprises, kind of activity units (kaus) and geographic units (geos). These replace enterprises, accounting units and activity units, respectively, on the BD. The underlying concepts are unchanged.
Constant Price Estimates	A constant price estimate, is one in which the portion of the sales movement caused by a price change, has been removed.
Enterprise	An enterprise is a single business entity operating in NZ, either as a legally constituted body, or as a self-employed individual.
Geographic Unit (GEO)	A geographic unit is a separate operating unit engaged in New Zealand in one, or predominantly one kind of economic activity, from a single physical location or base.
Industry	An industry consists of similar geographic units (GEOs) based on their predominant activity in terms of sales. The industry classification used is the ANZIND96 Inter-Industry level.
Sample Error	A sample error is the measure of the variability that occurs because a sample rather than the entire population is surveyed.
Seasonal Adjustment	Seasonal adjustment aims to eliminate the impact of regular seasonal events. They may be due to climatic effects or calendar effects.
Trend Estimates	Trend series have had both the seasonal and irregular components removed. An example of an irregular event would be the change in expenditure caused by the introduction of GST. Trend estimates reveal the underlying direction of movement in a series and are likely to indicate turning points more accurately than seasonally adjusted estimates.

---

Contact Details

Customer Service E-mail Contact:	info@stats.govt.nz
Survey Enquiries E-mail Contact:	info@stats.govt.nz

Liability

Statistics New Zealand gives no warranty that the information or data supplied contains no errors. However, all care and diligence has been used in processing, analysing and extracting the information. Statistics New Zealand shall not be liable for any loss or damage suffered by the customer consequent upon the use directly, or indirectly, of the information supplied in this product.