1. Introduction
Statistics New Zealand is progressively redeveloping a suite of business price indexes (BPIs) comprising the Producers Price Index (PPI), the Farm Expenses Price Index (FEPI) and the Capital Goods Price Index (CGPI).
As part of the redevelopment, New Zealand practice for various aspects of BPI compilation has been compared with the practices of five other Organisation for Economic Co-operation and Development (OECD) countries.
This article looks at how BPI data is processed and validated in New Zealand and in the five other countries.
top
2. International practice
For international comparison, Statistics NZ selected five OECD countries representing Europe, North America, Asia and Australasia: the United Kingdom, Australia, Canada, the United States, and Japan. They were selected because of the reputation of their economic statistics and availability of comprehensive documentation in English. The sources used for this article (see the references section) are available to the public and may not reflect the most current developments in those countries.
It is worth noting that these nations have much larger economies than New Zealand, making possible certain sampling procedures that may not be possible in a nation of four million people. It may be a worthwhile endeavour to make a similar comparison in the future with a second tier of smaller OECD nations, such as Ireland.
Statistics NZ tried to make the closest possible match with New Zealand’s BPIs in terms of data coverage. Each nation arranges their indexes slightly differently. For ease of comparison, the indexes under consideration are included below.
The UK Office for National Statistics (ONS) PPI suite includes: Home PPIs (domestic), Export Price Indexes and Import Price Indexes. Capital goods are included in their coverage.
The Australian Bureau of Statistics (ABS) produces a suite of PPIs, an Import Price Index, and an Export Price Index. The PPIs include two services: transport (freight) & storage division, and the property & business services division.
Statistics Canada produces an Industrial Product Price Index (IPPI), a Raw Materials Price Index (RMPI) and four service PPIs (accounting services, informatics professional services, consulting engineering services and traveller accommodation services). Canada produces a Machinery and Equipment Price Index that parallels New Zealand’s CGPI, and a Farm Input Price Index (FIPI) that parallels New Zealand’s FEPI.
The US Bureau of Labor Statistics (BLS) produces a PPI that includes capital goods. The PPI covers almost the entire output of domestic goods-producing sectors, and many service industries. Import and export prices are collected and indexed separately.
The Bank of Japan produces a Corporate Goods Price Index composed of a Domestic Corporate Goods Price Index, an Export Price Index, and an Import Price Index; capital goods are included in its coverage. They produce a separate Corporate Service Price Index.
The New Zealand suite of PPIs comprehensively covers both goods-producing and service industries.
top
3. Data processing and validation
Statistics New Zealand
When surveys are sent back to the office by respondents they are then checked for any price or quality changes. Once groomed, the surveys are entered into the computer processing system.
Any price that has recorded a movement requires a reason to justify the change in price, with those that have moved by more than 5 percent (either positive or negative) undergoing further checks. These checks involve comparing the current price with previous prices and contacting the respondent for further information if needed. Information obtained from respondents also provides useful information that helps to build a pricture of what is driving index movements.
Firms who receive a commodity price survey are split into two groups, key firms and non-key firms. For the key firms, a 100 percent response rate is required for the indexes, while the overall response rate required for all firms is 97 percent. Non-responses are generally imputed to show no change in price.
Quality adjustment is performed mainly using the 'overlap price' method. This is used when prices for both the old item and the replacement item are available in the same period. This method assumes that any price difference between the two products at the overlap period is due to quality differences.
Office for National Statistics (UK)
Contributors return prices by means of a pre-printed form containing the most recent details, which is posted at the beginning of each month.
Monthly movements outside the range of -2.5 percent to +5 percent are considered dubious, and require contact with the contributor. For the more volatile export and import indexes, +/- 7.5 percent is allowed. Indexes which move more than 5 percent (7.5 percent for import or export) must have reasons included. ‘Too stable’ letters are sent to contributors whose prices are recorded as not having moved for a set period, currently 18 months.
The ONS aims for a minimum 82 percent response rate in the all manufacturing output index at the time of first publication (weighted according to sales); and revision in the estimate of the year-to-year all manufacturing output price index should not exceed 0.125 percent between the time of the first publication and the first ‘firm’ estimate published two months later.
Missing prices are filled in by class imputation which involves applying the average weighted price movement of a group of comparable products (or products from the same industry) to the item with the missing price to derive a current price.
The ONS has set procedures to identify production specification changes and assess whether resulting price differences are wholly due to quality change (in which case no price change is shown), partly due to quality change (in which case some, but not all, price change is shown), or purely cosmetic (in which case the full difference is shown as price change).
Australian Bureau of Statistics
As soon as the price collection forms are received by the ABS they are checked for completeness and the reported data is loaded into the computer. The data is in the form of ‘raw price elements’ such as list prices, various discounts, transport charges, sales tax, etc, from which the transaction prices are calculated for use in the index.
The returned prices are checked for accuracy through comparison with the respondent’s past prices and those reported for the same item by other respondents. Unusual prices are verified with the respondent, and corrected where necessary.
Specifications that require replacement are linked into the sample using an overlap method such that its price relative reflects only price movement and is not affected by the change in specification.
Statistics Canada
Commodity specialists watch developments in the markets closely. They review the behaviour of the reported price changes, both to validate them directly and to ensure they are representative of the product price movement as a whole. Outliers and incorrect or suspicious prices are identified during the initial data processing and then verbal follow-ups are carried out with the respondents to ensure the appropriate information has been obtained.
If no price is returned, either the last reported price quotation will be carried forward or an estimate will be made based on other information. Often, the last reported price would be carried forward in the short term while the commodity officer seeks clarification from the respondent.
Where the commodity is out of season, and no orders normally occur during that period, the last reported price quotation is carried forward until a new price quote is available in the next season.
Quality adjustments are made by using the 'production cost' method. This method involves adjusting the price of the old product by the different amount that it costs to produce the higher or lower quality new product.
Bureau of Labor Statistics (USA)
The schedules returned by the respondents are scanned by an optical character reader, which logs in each form and captures the essential data elements. Analysts then verify the price information and check for changes that might have been missed by the character reader. If the establishment fails to report or reports incomplete information, it is called by a BLS economist who requests the needed information. These automated data-processing systems facilitate the accuracy and timeliness of published PPI data and protect the confidentiality of data supplied by respondents.
Quality adjustments are made by production cost, overlap price and 'hedonic regression' methods. Under the hedonic approach to quality adjustment, a good or service is seen as comprising a bundle of price-determining characteristics. Once the characteristics in the bundle have been identified and measured, the hedonic regression function can be interpreted as breaking down the price of the good or service into the implicit prices and quantities of the characteristics. This allows changes in the quality of products to be quantified and adjusted. Missing prices are filled in by class imputation.
Bank of Japan
Prices are immediately replaced if the products are deemed no longer representative, or terms of transaction change. Quality adjustments are made by production cost and hedonic regression methods.
Summary
Most countries have similar data processing and validation processes, with unusual or large price changes requiring reasons for movement or further clarification. The U.S. Bureau of Labour Statistics is the only statistics office discussed in this article that uses scanning and optical character reading. Carrying forward previous prices is a commonly used imputation method used when no current price is received.
top
4. References
Statistics New Zealand (Dec 1999). "Producers Price Index: Concepts, Sources and Methods", business-activity-stats-1999
Statistics New Zealand. "Information about the Producers Price Index (PPI)", http://www2.stats.govt.nz/domino/external/omni/omni.nsf/outputs/Producers+price+index+(PPI)
Statistics New Zealand. "Information about the Commodity Price Survey", http://www2.stats.govt.nz/domino/external/omni/omni.nsf/outputs/Commodity+Price+Survey
Statistics New Zealand. "Information about the Capital Goods Price Index", http://www2.stats.govt.nz/domino/external/omni/omni.nsf/outputs/Capital+Goods+Price+Index
Statistics New Zealand. "Information about the Farm Expenses Price Index", http://www2.stats.govt.nz/domino/external/omni/OMNI.NSF/Outputs/Farm+Expenses+Price+Index
Richardson I, Office for National Statistics (UK) (2000). "Producer Price Indices: Principles and Procedures".
McLennan W, Australian Bureau of Statistics (Feb 1997). "Analytical Framework for Price Indices".
McLennan W, Australian Bureau of Statistics (Mar 1999). "Producer Price Index Developments".
United States Bureau of Labor Statistics (Oct 2001). "Rebasing of Selected Producer Price Indices", http://www.bls.gov/ppi/ppibase.htm
United States Bureau of Labor Statistics (Nov 2004). "PPI Frequently Asked Questions", http://www.bls.gov/ppi/ppifaq.htm
United States Bureau of Labor Statistics (Mar 2004). "PPI General Overview", http://www.bls.gov/ppi/ppiover.htm
United States Bureau of Labor Statistics (Sep 2003). "BLS Handbook of Methods", http://www.bls.gov/opub/hom/homtoc.htm
Ministry of Internal Affairs and Communication (Oct 2004). "Guide to Official Statistics in Japan", http://www.stat.go.jp/english/index/official/index.htm
Back to Price Index News: January 2008