Abstract

13.1 Export and import price indices (XMPIs) are used for many purposes by government, business, labor, universities, and other kinds of organizations, as well as by members of the general public. Accuracy and reliability are paramount for a statistic as important as XMPIs. Whether XMPIs are used as a deflator of national account values, an indicator of inflation, in escalation of contracts, in assessing developments in the global economy such as exchange rate fluctuations, or in other economic analyses, the process of producing XMPIs needs to be carefully planned and executed.

A. Introduction

13.1 Export and import price indices (XMPIs) are used for many purposes by government, business, labor, universities, and other kinds of organizations, as well as by members of the general public. Accuracy and reliability are paramount for a statistic as important as XMPIs. Whether XMPIs are used as a deflator of national account values, an indicator of inflation, in escalation of contracts, in assessing developments in the global economy such as exchange rate fluctuations, or in other economic analyses, the process of producing XMPIs needs to be carefully planned and executed.

13.2 Individual circumstances vary to such an extent that this Manual cannot be too prescriptive about timetables or critical path analysis of all the steps involved. However, the description in this chapter provides an outline of the kinds of activities that should result from a detailed examination of the logistics of the whole periodic operation of compiling the index.

13.3 The following guidance seeks to present some options in the organization of data collection and estimation. The examples given are based on experience and provide an indication of goals a country may seek. In recognizing these options, this chapter, which talks about organization and management of XMPI processes, covers the relationships between staff, who may be stationed at regional offices in large countries, and XMPI staff at the central office, covering the work carried out in the central office, the flow of information among each part of the organization, and related activities for coordinating collection and processing data. Because of the size, frequency, cost, and complexity of the collection of prices as the basis of the index, in some countries not all these operations and relationships will be appropriate. In some cases, countries may resort to using data already available such as customs data or data from other price programs such as the producer price index (PPI) or consumer price index (CPI).

13.4 The complexity of the organizational structure is necessarily correlated with the scope of the effort, in terms of resources as well as the volume of data collection. In particular, XMPI programs tend to be smaller than other price programs in any given country. Ideally a program would comprise a multifaceted staff with a variety of skills, including economists, statisticians, system analysts/programmers, field staff, and clerical support. In the case of XMPIs, however, resource limitations often may require individuals to perform more than one task.

13.5 Although the mission of XMPIs is singular—to produce a set of price indices—the process for producing these data can be broken out into several discrete activities. These activities can be separated into five major phases: sampling, initiation, repricing, estimation (compilation), and publication. Each phase, however, may require a number of different technical skills as well as a separate but coordinated management structure.

13.6 As explained in Chapter 2, XMPIs may be based on unit value indices from customs data, establishment price surveys, or a hybrid mixture of the two, along with other source data. Organizational issues relating to sampling, initiation, and repricing are primarily the concern of establishment price survey data, though issues in managing data quality and verification remain relevant.

13.7 Sampling is normally the first component of developing XMPIs. This usually entails the selection of companies and products (or product areas) that will be in the market basket. This is also the stage at which a determination is made on how much publication detail the sample can support. During the initiation phase, company cooperation is elicited and, if necessary, a final determination is made regarding the actual items that are to be repriced on a regular basis. The next phase is repricing. This is a recurring process whereby at a regular interval, usually monthly or quarterly, price data are collected from a respondent. Collection methods vary and a program may make use of more than one mode. Current modes include mail, fax, web collection, and personal visits. This component would also include a review, manual and/or automated, of the data in order to ensure its compliance with economy theory. Estimation is the process whereby the detailed price information is aggregated in order to produce a price index. Finally, the data are ready for publication, either as hard copy printouts or, as more and more often is the case, released on the organization website. These stages will be considered in turn after a general consideration of organizational and management issues.

B. Organizational Structure and Resource Management

B.1 Structuring

13.8 In practice, most countries have devoted comparatively little, if any, resources to XMPIs. Whereas some agencies such as the U.S. Bureau of Labor Statistics dedicate more than 130 employees to the production of its export and import price data, the vast majority of countries make do with only a comparative handful of employees. This smaller staff resourcing is usually due to two reasons: first, the higher priority usually given to the production of CPIs and PPIs; and second, the common practice of using readily available administrative data to construct XMPIs based on unit value indices. Consequently, XMPIs may be compiled by a unit devoted solely to XMPIs, or they might be part of a unit responsible for publishing data on the value of exports and imports. However, there are synergies with PPI compilation, especially if the primary data source for price relatives is establishment-based surveys. In such a case, the XMPI unit may well be part of a larger staff who also have responsibility for producing PPIs.

13.9 Like any data collection program, the organizational structure supporting XMPIs can be either vertical or horizontal, with various possibilities in between. A fully vertical structure would be one in which all of the staff on the program work in the same office and work only on XMPIs. A fully horizontal structure would be one in which no one in the program works solely on XMPIs. For example, a unified field data collection staff may be responsible for collecting data for every program in the agency, while a single office of statisticians may similarly be responsible for developing samples for every survey in the agency.

13.10 The key determinants for assessing the organizational structure would be availability of resources, similarity of methodologies, complexity of program, and efficiencies gained by combining or splitting functions. Usually there are advantages in combining resources between programs. In general, the more alike a processing component is between two programs, the better it is to share resources. In the case of XMPIs this usually will lead to the program sharing resources with a PPI program, where many of the concepts and data sources are similar. Consequently, much of the organization and management conventions associated with XMPIs are similar to those found in the construction of PPIs.

B.2 Managing the process

13.11 When the unit responsible for producing XMPIs is small and wholly contained, managerial issues also tend to be small because one supervisor may be responsible for every aspect of the data collection and index estimation process. Even in a small program, however, it is important to have a staff large enough to allow for the development of individual expertise in a selected area, especially in those aspects that demonstrate differences from PPI concepts and methodologies. For example, sources of data available for sampling and weighting tend to be unique in XMPIs. Also, the specialized need to handle pricing in intrafirm trade and exchange rates are unique or especially critical to these series. Finally, and perhaps most important, in addition to having general expertise in statistics, economics, and computer programming, the organization should have as much specialized expertise by industry (or product category) as resources permit. One of the key difficulties in producing accurate and up-to-date price indices is an awareness of product (and other trends) in the underlying economy. Experienced staff who specialize in sectors of the economy are best positioned to spot these trends and help make additions or adjustments in the data in order to keep the indices current and relevant.

13.12 In a larger organization, often the organization has separate functional units in which staff are split by their skills or work assignments. In order to ensure that the individual unit works together, one option is to develop a matrix structure in which different areas of the program are managed by staff from different offices. In some cases the matrix structure might be delineated by processing component; in other examples matrices have been divided into research, development, and production components. For example, in a horizontal structure staff may be categorized by their functional skills: sampling, initiation, data collection, verification, and estimation, and also by whether they are working primarily on XMPIs or PPIs. Matrices also tend to be more flexible and can be more readily rearranged as circumstances warrant.

B.3 Staffing

13.13 The appropriate mix of skills in any given XMPI office may be a function of how the statistical process is organized in a given country, as well as the approach of the nation’s data collection effort (e.g., administrative vs. economic). Nonetheless, certain disciplines and tasks are vital to ensuring that each component of the index process is properly and efficiently carried out, and that the published data are accurate, timely, and relevant. A large organization may have the resources to hire separate staff for each of these disciplines. However, frequently XMPI offices are quite small. Consequently, employees are likely to have multiple responsibilities (e.g., data collection, sampling, and index review); statistical offices may need to employ more adaptable and more educated people, not only because they will have to perform more than one task, but also because they are more likely to have to serve as backups to their colleagues.

13.14 Input from economists is necessary to the process of producing XMPIs. These indices have a multitude of uses, and proper construction of these indices requires economists who are familiar with their purposes and can ensure that the construction of the indices meets the needs of the key functions of the data. In addition to competence with some of the standard sub-disciplines in economics, micro-and macroeconomics as well as international economics (both finance and trade), some staff economists should also be experts in price index number theory itself, a more specialized discipline in economics. Knowledge of specific industries and technical expertise can also be critical in order to properly understand the inputs and outputs as well as the industrial organization of a given sector of the economy. Statistical offices should organize and meet frequently with users committees.

13.15 Statisticians play a key role in the sampling process as well as the index estimation process. Because no establishment-based price program can afford to collect data on the entire set of items in the universe of goods and services being measured, the program requires a method for determining a subsample of both importers and exporters and individual products that should be included in the pricing market basket. This determination process involves balancing a number of factors, such as the number of respondents that the program budget can support, the number of items necessary to sustain an accurate index, the need to trade off respondent burden with the need to include large traders in the market basket, the life of the market basket as well as the need to regularly update the mix of items in the basket, the variation in deterioration rates by industry, and the need to select only items that are traded and repriceable on an ongoing basis. Owing to the complexity of sampling, statisticians should have a good grounding in sampling theory and practice.

13.16 The past few decades have seen a growing role for computer specialists in the production of economic data. Even smaller countries rely more and more on computers for collecting and reviewing the data and calculating XMPIs. And with the increasing need for producing more indices more rapidly, this trend is expected to continue. With many series such as XMPIs collecting price data on thousands of items each month, the use of electronic data processing is central to a program’s ability to produce outputs in a timely manner. The computer programmers should be skilled at evaluating user requirements and determining the proper database design and programming languages necessary to support the program. Particularly in smaller organizations, where a substantial part of the data collection and processing may be handled with comparatively simple software such as spreadsheets, it has become more common to hire technical staff who have very strong programming skills in addition to their subject expertise (usually economics or statistics).

13.17 Often the most difficult roles to fill in a price index program are those on the front lines: the data collectors who usually meet the respondents face to face. Many, if not most, price collection programs are voluntary. Thus, this staff must play many roles, including part economist, part salesperson, in the sense that they must convince establishments of the need to provide data. Literature should be prepared in advance on the usefulness of XMPIs, confidentiality of responses, and need for continuity of price information from a representative sample of establishments. Legislative backing is also useful. The major role for the data collector in XMPI programs is to initiate respondents into the program and often to collect the first set of data from the sampled respondent. This process can be quite complicated, particularly when soliciting a large company, and the data collector must be sufficiently trained to handle a multitude of different issues that may be raised by the respondent. The data collector is also frequently called upon to make split-second decisions during an initiation session, when time may be extremely limited. Note that the “salesperson” part of this job tends to be much more important in programs such as the PPI and XMPIs, where the respondents are usually responsible for supplying data at initiation as well as periodic pricing. In contrast, in consumer price programs, the periodic pricing can normally be done by data collectors from the statistical office.

B.3.1 Outsourcing

13.18 One of the decisions facing any statistical agency carrying out a price collection program is whether to use in-house staff or tender the collection to an external organization. For example, another part of the agency, another government department that specializes in surveys, or a private market research company could perform this function.

13.19 The nature of the price collection and the distribution and profile of statistical staff may help determine whether the collection is suitable for contracting out to another agency or even the private sector. Where price collection is continuous, involves complicated decision making (such as quality adjustment), or is collected from a small number of businesses, it may be advantageous to keep the collection in-house. However, if the collection takes place over just a few days per month from a large number of businesses, is relatively straightforward, and involves only routine or simple decision making (perhaps selecting from a list of codes), then contracting out to another agency can be considered. For example, if the statistical office does not have a dedicated data collection staff, it could contract with other agencies such as commerce, industry, and agriculture to collect XMPI data. Another possibility could be a private research company, if there are market research companies with suitable skills in the country. The statistical office must also take confidentiality requirements into consideration when contracting with another agency to guarantee that there are no breaches in confidentiality. This may involve national statistical laws that address the issue of data collection by contractors and enforcement of penalties for breaking confidentiality requirements.

13.20 Contracting out price collection can lead to lower costs. When price collection is carried out using electronic methods such as computer-assisted telephone interviews or computer-assisted personal interviews, the responsibility for purchasing and maintaining data-capture devices may also be transferred to the contractor. Contracting out may also allow statistical office staff to spend more time analyzing data rather than collecting it. By separating the roles of data collector and data checker, statistical staff can feel more comfortable questioning the validity of price data and the accuracy of collected data can be linked to the performance of the contractor through performance measures, which drive incentives payments (and penalties if targets are not achieved).

13.21 The same considerations may be used when deciding whether the survey division or XMPI staff should conduct the price collection. Usually, some mixed mode of operation will be in place. Staff from the survey division may handle straightforward and routine price collection; more complicated and specialized industries such as chemicals and semiconductors will require price collection by specialists, whether from XMPI staff or consultants of a statistical office.

B.3.2 Training

13.22 Effective training will motivate staff and equip them to deliver a good-quality index. At its simplest, training will give a background understanding of the nature and uses of the index and its compilation. Training and development take many different forms and may include

  • Tutoring by the line manager or supervisor,

  • Attending an induction course or reading a manual, and

  • Accompanying an experienced price collector.

13.23 A written training plan can be useful in identifying training and development needs against the backdrop of the organization’s goals and targets. It can also identify the resources required to deliver these needs and evaluate whether training has been delivered effectively and objectives have been met.

13.24 The statistical office should have a general training program for staff working on the price programs. There are six basic components of such a program:

  • Fundamental (basic) training must provide general information on how to collect data, code data elements, review and edit basic price data, and compile collected data to produce indices. In addition, the training should impart to staff information on the purposes and uses of the collected prices.

  • Price collectors need to be trained specifically in field procedures, including relations with businesses, a selection and definition of a valid price, special rules for certain individual price transactions (including seasonal price transactions), how to complete initiation forms, and, where appropriate, how to use computers. Compilers of the index will need to be trained specifically on the validation, consistency checking, and calculation of centrally collected indices; weighting procedures and how to aggregate prices; and treatment of seasonal price transactions and special procedures relating to some sections of the index.

  • Training, especially for newer staff, may also entail a period of ongoing monitoring of performance.

  • The program should highlight the need for continuous training of staff at all levels. Staff should provide feedback at all levels—from respondents to data collectors and from supervisors to staff. There should be regularly scheduled meetings between staff and supervisors at all levels to assess the program and identify current and potential problems.

  • Statistical offices also need to provide professional training for staff in computer technology, economics, statistics, and even psychology (for dealing effectively with respondents).

  • Regularly scheduled meetings for all or selected staff members can provide a time to discuss the strengths and weakness of the program and plans/changes for the future. This is particularly true when the program undertakes major changes in index methods, such as rebasing with new weights and new sample designs.

B.4 Process improvement

13.25 Developing, maintaining, and updating clearly delineated program goals are crucial to the ongoing success and utility of a well-run program. This process must take into account all stakeholders, both internal and external, and assume realistic estimates of resource availability.

13.26 With the rapid spread of the Internet, the development of new electronic data gathering processes and the demand for new kinds of data (e.g., those measuring intangibles) have made the job of data collectors more difficult. The need for systematic process reviews may be especially critical for XMPI programs to deal with as the rapid globalization of the world’s economy and the attendant shifts in production and consumption have made measurement more difficult.

13.27 XMPI programs should have a well-understood process in place for reviewing and revising goals and should include a process for assessing changes in international trade patterns to ensure outputs, methodology, and data processing methods and procedures are continually reviewed to meet changing needs.

13.28 Staff input is an essential part of continuous quality improvement. Staff may be invited to operational reviews where all team members have the opportunity to raise concerns and, where appropriate, tackle specific issues through individual or group efforts. In order to effect this, staff schedules should include an appropriate amount of time for process improvement.

13.29 A process for improving XMPIs can best take place in an environment where a systematic quality assurance program is in place. This includes not only introducing and monitoring quality controls on the production process itself, but also effective interaction with the user community in order to ensure that their needs are being met—see Section E for further discussion on quality management.

B.5 Processing components

13.30 Although the processing methods and data review used in constructing XMPIs are discussed in other chapters, especially Chapters 6, 7, and 14, there are several organizational and management aspects of each of these processes that should also be touched upon.

13.31 One question that has become increasingly important in the development and maintenance of each of the processing components is how to take best advantage of the efficiencies that can be gained via more effective use of computers. Ideally, an XMPI organization would have its own systems staff to develop and maintain an XMPI production system. In cases in which systems staff are shared with other programs, there should be sufficient flexibility to allow for systems staff to undertake specific XMPI developmental work. If staff are to be shared, then one essential ingredient is that the programs and programming languages should be standardized.

13.32 As a general rule of thumb, the managers of XMPI programs would like to have as much programming under their direct authority as possible. If the best way to achieve this goal is to use simple high-level languages such as EXCEL or SAS (which can be programmed by economists, statisticians, or others on the immediate staff), that may be an appropriate approach. XMPI compilation methods may need to be changed in the light of experience and new developments and it is essential for the XMPI unit to have, or call upon, the expertise to do so.

C. The Sampling Process

13.33 Because many countries have detailed records on all export, and especially import, shipments, very good and detailed data on what companies have been shipping what products across borders are often available. This source of data may, or may not, be collected by the same organization that constructs XMPIs. In either case, however, it is valuable for XMPI offices to make use of these records in order to draw a sample of both respondents and products to initiate and reprice its item selection. Sampling methods were outlined in Chapter 6.

13.34 Whether the data are collected by the same organization or a different one, it is necessary to constantly monitor the quality of the data and to ensure that the data are as up-to-date as possible. While the level of data detail normally available in these records is often quite good, the quality of data being collected for administrative purposes such as duties is often uneven. Thus the management process should include systematically working with the provider office in order to ensure that the data used to construct the sampling frame are high quality. In addition, it is also important that the staff working with developing the sample have access to feed back from those staff who have had direct contact with respondents during the data collection phase.

D. The Initiation Process

13.35 This process can be very labor intensive and normally involves XMPI staff either visiting or conducting a phone interview with individual sampled businesses to establish cooperation, stress the importance of the index, and receive basic information, such as the exact goods and services produced by the business, relative importance of transactions with various clients, and individuals to contact on a recurrent basis (see Chapter 7 for more details). During this initiation visit the respondent and XMPIs staff will normally identify the actual items that will be repriced on a regular basis. In some countries these operations may be conducted by telephone. The range and number of businesses visited and the types of goods and services priced will vary between countries (see Chapter 6).

13.36 Management of the initiation process may be very important as this is usually the process that is the greatest burden to respondents. Especially when a data collection program is voluntary, it is important to minimize the burden on the reporter. While the original sample universes may differ, frequently the PPI and XMPI market basket of respondents and items will overlap. This is true in part owing to the tendency of companies engaged in foreign trade to be concentrated. Consequently, it may be appropriate to use and manage the same staff to initiate respondents in both programs, Not only might this minimize the duplication of technical knowledge, but it can also serve to minimize burden and enable more efficient scheduling of contacts with an individual reporter.

13.37 Note that in some cases, the data collectors responsible for initiating new respondents into the process may also be responsible for repricing the data on a regular basis.

13.38 Although the precise method of current price collection will vary (see Chapter 7), each price collector may be responsible for the initiation and collection from a certain business or from certain types of businesses. This would enable the collector to specialize in certain subject areas of the index. In other cases, particularly in larger countries, price collectors may specialize by regions. Although price collection is usually done monthly or quarterly, the frequency can change if the prices for certain transactions change at known intervals. Items that are traded only in certain seasons may be collected only in specified months. In other cases respondents may indicate that owing to burden concerns, the data will need to be collected less frequently. Sometimes these prices may be collected directly by XMPI staff in the main office based on external information such as contact with other government offices or through the media. In any case, checks must be in place to ensure all price data are reported. (See Chapter 7, Section B, for information on timing and frequency of price collection.)

13.39 Quality is an important part of price collection; a high-quality price collection enables a statistical agency to have confidence in the index it produces and ensure that observed price changes are genuine and not the result of collector error. Procedures must be developed to ensure that a high standard of collection is maintained for every collection period. These procedures will form the basis of collector training and should be included in any training material developed for price collectors. Guidance should cover price index principles, organizational issues, and validation procedures for both technology and price collection methods.

13.40 Transaction descriptions. During the initiation phase of data collection, accurate price transaction descriptions are critical to ensuring price transaction continuity. Descriptions should be comprehensive to ensure that collectors or reporters can price the same transaction in each collection period. Collectors must record all information that uniquely defines the price transaction selected. So, for example, in price collection for production of clothes, color, size, and fabric composition must be specified to ensure that the same price transaction is priced each month (see Chapter 7 for details).

13.41 Accurate price transaction descriptions will assist the price collector, respondent, and XMPI staff in choosing a replacement for a price transaction that has been terminated and will also help to identify changes in quality. XMPI staff should be encouraged to spend some time, each collection period, going through reported descriptions to ensure that the correct price transactions are being priced. Collectors or respondents should also be encouraged to review their descriptions to ensure that they contain all the relevant information, and it may be useful to ask collectors occasionally to switch collections with another collector as part of a peer review.

13.42 Continuity is one of the most important principles of price collection. Because a price index measures price changes, the same price transaction must be priced every month so that a true picture of price changes is established. It is not possible to be prescriptive because the concept of equivalence will vary among countries, but for practical purposes a detailed description of the price transactions must be kept. Some guidelines may be drawn up by the statistical office’s XMPI Head Office staff to cover different price transactions. All transaction specifications, and especially price-determining characteristics, must be obtained and monitored.

13.43 Feedback. When price collectors are used, they should be encouraged to give feedback to XMPI Head Office staff on their experiences. Collectors are a valuable source of information and often give good early feedback on changes in the different industries. Collectors can often warn of size or product changes before XMPI Head Office staff can derive this information from other sources, such as trade magazines or the business press. Collector feedback can form the basis of a collector newsletter and can support observed price movements and provide supplementary briefing material. Significant changes in price transactions within a business may require an additional visit by XMPI analysts to the business to update the price transaction descriptions.

13.44 Auditing. Because the routine of initiating respondents in the field may be the most critical and labor-intensive component of the entire process, it needs to be carefully planned and managed. Circumstances vary, and it is not appropriate to be too prescriptive. Some of the measures mentioned below may be irrelevant if XMPI analysts in the Head Office collect the prices centrally. However, it is vitally important to check that the information sent in is accurate and complete.

13.45 One way to monitor the work of price collectors is to employ auditors to occasionally accompany collectors during field collection—whether data are collected by phone or personal visits—or to carry out a retrospective check on data that have been collected.

E. The Repricing Process

13.46 The repricing process for XMPI is the single most complex process in constructing price indices as it consists of numerous steps including (1) determining the set of items to be collected in the current period; (2) notifying respondents (or data collectors) of the data they need to supply; (3) receiving the data from respondents; (4) verifying the data; (5) if data are incomplete, missing, or do not appear to be correct, taking remedial action; and (6) preparing the data for estimation. Because of the increasing desire from policymakers for more timely economic data, this process may have to occur in a very short time frame.

13.47 Data can be collected using a number of different methods, such as (1) an online web collection application, (2) e-mail, (3) fax, (4) phoned in, or (5) mailed in. Given advances in computer technology over years, this may be an area where management may want to focus its data processing expertise.

13.48 Although data collection via field staff is often necessary during the initiation phase, especially when a program is voluntary and a certain amount of convincing respondents to participate is needed, field collection via a personal visit is expensive and XMPI programs should try to avoid it during the periodic repricing.

13.49 In any voluntary data collection program, the single biggest issue facing management is nonresponse. In cases in which the organization must rely upon companies to supply the data, it is incumbent upon the program to ensure that there is in place a systematic process for collecting the data and for following up when the information has not been received.

13.50 Offering respondents a variety of modes for collecting data is one aid to garnering respondent cooperation. Reminders using e-mail and other points of contact may also prove to be effective. Because phone contacts are the most labor intensive, it may be more efficient to use clerical staff to make phone calls in cases where a simple checklist or computer-assisted telephone interview process can be developed.

13.51 The key for management is to develop a systematic method for monitoring response rates on a regular basis. Often a sudden change in response rates may indicate a problem somewhere in the data collection process.

13.52 In addition, for any number of reasons (such as volatility of trade, growing complexity of goods, and shorter product life cycle), the data that are collected during repricing may also require some type of follow-up. Consequently, a key to successfully managing this process is to obtain the data as fast and as clean (accurate) as possible, and to ensure there is an effective method for recontacting the respondent and amending the data as appropriate.

13.53 Collectors or respondents should report prices at similar times within each collection period. This is particularly important when pricing volatile price transactions with sharp fluctuations.

E.1 Data entry queries

13.54 Once the price data have been entered in the system, a series of validation checks may be run. In deciding which checks should be carried out, take into account the validation checks carried out in the field, whether by price collectors in the regional office, survey division officials in the main office, or XMPI analysts. When data entry is automated (e.g., collection via the web) then these checks can and should be built directly into the data collection application.

13.55 The range of tests carried out for all collection methods may include the following:

13.56 Missing data. The most common check is for data completeness. Often, a number of price factors besides the price are collected. These may include country of origin or destination, currency of invoicing, and discount structure. When a data element is missing, it should be flagged and reviewed.

13.57 In XMPIs, however, one of the major reasons for missing price data is attributable to the volatility of trade. Particularly in XMPIs, which collect data monthly, respondents will often indicate that there was no trade in the reference month. However, in a PPI, though the respondent may be able to estimate the price of his or her establishment’s product, it is more difficult to do so for an importer. Consequently, it is very important for management to develop a consistent approach to handling data that are temporarily unavailable, because this can represent up to 20 percent or more of a given month’s market basket (see Chapter 8 for the treatment of temporarily missing items).

13.58 Specification change. For any number of reasons, an item may have had a change in its specification. It may be as simple as a change in color or, as in the case of PCs, it may be significant, such as a more powerful microprocessor or larger hard drive. Any time there is a change in the specification, it should be reviewed by a product specialist in order to ensure that the price change from the first period to the second period is appropriately adjusted for any change in the quality of the good.

13.59 Price change. The price entered may be compared with the price for the same defined transaction in the same business in the previous month and queries raised where this is outside preset percentage limits. The latter may vary depending on the price transaction or group of price transactions and may be determined by looking at historical evidence of price variation. If there is no valid price for the previous month, for example, because the produced good was not traded that month, the check can be made against the price two or three months ago. The price may also be compared with other transactions conducted by the same business in the current month. Checks may also be put in place to reveal instances where prices have not been changed for an inordinate amount of time, because this may sometimes indicate instances where the data are not being properly updated.

13.60 Maximum/minimum prices. A query may be raised if the price entered exceeds a maximum or is below a minimum price for a group of goods or services of which the particular product is representative. The range may be derived from the validated maximum and minimum values observed for that price transaction in the previous month expanded by a standard scaling factor. This factor may vary between price transactions.

13.61 If computer-assisted techniques are used, these tests can be easily implemented to take place at the time of collection; otherwise, they will need to be conducted by XMPI Head Office staff as soon as possible after collection and before prices are processed on the main system. If a price given by a respondent fails the computer-assisted test, this should not result in collectors being unable to price the price transaction, but it should prompt them to check and confirm their entries and prompt for an explanatory comment.

13.62 Queries raised may be dealt with either by staff analysts at the XMPI Head Office or by the price collector or respondent contacted for resolution. For example, scrutiny of a form might show that a big price difference has arisen because the transaction priced was a new product replacing one that had been discontinued. In this case, there may be no need to raise a query with the price collector unless there is evidence to suggest that labeling the transaction as a “new product” is incorrect.

13.63 One noticeable difference between collecting data for a PPI versus collecting data for an XMPI is the role of transfer prices (transactions between related parties). Often, transfer prices are valued at cost instead of an arm’s-length market price. Sometimes transfer prices may remain unchanged for what appears to be an inordinate length of time, while in other instances they may fluctuate wildly and for no apparent reason. Consequently, XMPI programs should track these data and take special measures in handling them (see Chapter 19).

E.2 Quality control

13.64 As in the initiation process, regular quality checking of the ongoing repricing data is critical to the ability to publish accurate price indices. Although the concepts associated with the quality control of repricing data are similar to those pertaining to the earlier initiation process, the specific type of audits and controls may differ. For example, whereas the initiation process usually involves a staff member from the collection organization in the documenting and verifying of the initial data, the reporting of the ongoing repricing data would normally be done by an employee of the importer or exporter. Regardless of how these data are reported, the information must be subject to a rigorous review. This would include such steps as

  • Ensuring that the price reports are sent in when they are due. If not, it is necessary to find out the reason and take appropriate action;

  • Confirming that the reports contain what they are supposed to contain—that is, that required fields have not been left blank, that numeric fields contain numbers, and that nonnumeric fields do not;

  • Reviewing and editing each return. Substitutions may have to be made centrally or those made by the collectors may have to be approved. Unusual (or simply large) price changes may need to be queried. Transactions priced in multiple units or varying weights may have to be converted to price per standard unit. Missing prices must be dealt with according to standard rules relating to the cause; and

  • Identifying and correcting errors introduced when keying the numbers into the computer or transcribing them onto worksheets.

13.65 As stated above, logical checks conducted in the field by an automated process can reduce the amount of checks and errors handled by XMPI Head Office staff.

13.66 Some of these tasks can be done by computer, others, manually. Therefore, no general suggestion can be made about the sequence of the work or about its division into different parts. Procedures should be in place to check that all documents, messages, or files are returned from the field so that price collectors can be contacted about missing returns. Initial checks should then be carried out to ensure that data are complete and correct. If any prices fail these checks, a query should be raised with the price collector for clarification. Because some of the checking may require reference back to the price collectors (or to their supervisors or respondents when direct-mail questionnaires are used), the timetable for producing the index must allow for this communication to take place.

13.67 Following the price data checks, a series of validation checks may be run. In deciding which checks should be carried out, account should be taken of the validation checks carried out in the field. For example, computers will increase the potential for validation at the time of price collection and reduce the need for detailed scrutiny at the XMPI Head Office. In addition, it would not be productive or cost-effective to repeat all the tests already carried out, except as a secondary audit or random check.

13.68 Reports (on paper or computer) should be generated routinely for most representative price transactions. Reports help the analyst pick out particular prices that are different from those reported for similar firms elsewhere or that lie outside certain specified limits. A computer printout can list all cases that either fall well outside the range of prices obtained earlier for that representative price transaction or show a marked percentage change from last time for the same price transaction in the same business. The limits used will vary from price transaction to price transaction and can be amended. The analyst can study the printout, first ascertaining whether there has been a keying error, then examining whether the explanation furnished by the collector adequately explains the divergent price behavior, and finally determining whether a query should be sent back to the supervisor or collector. The timetable should allow for this step, and anomalous observations should be discarded where an acceptable explanation or correction cannot be obtained in time. (Also see Chapter 10, Section D, on editing data.)

13.69 The quote report consists of a range of information on a price transaction that the index dispersion report has highlighted as warranting further investigation. Information listed may include current price, recent previous prices, and base price, together with similar quotes from other reporting businesses. The report can be used to identify the quotes that require further investigation and also to investigate rejected prices.

13.70 Algorithms can be created that identify and invalidate price movements that differ significantly from the norm for a price transaction. For some seasonal price transactions for which price movements are erratic, it may be more appropriate to construct an algorithm to look at price level rather than price change.

13.71 Although algorithms can be an efficient way to highlight problematical data, a word of caution should be expressed about using them. Analysts will want to assure themselves that their use does not result in systematic bias in the index. This issue may also need to be addressed in any editing routines (as presented in Chapter 10, Section D), although it is less likely to be problematical in the context of manual editing.

F. The Estimation Process

13.72 The estimation process is the component where all of the data come together to produce program outputs. Although the index calculation process is usually highly automated, the index review process can be quite labor intensive, albeit with a number of automated summary outputs that facilitate a quick review. One approach to take during the index review process is to have it looked at both by someone who is knowledgeable about the specific product area covered by the index and also by someone who is looking more broadly to ensure consistency across indices. The latter review, for example, may be appropriate if there is a widespread shock to the economy such as a dramatic devaluation or revaluation of the home country’s currency.

13.73 Usually the calculation of price indices is handled by a computer program, either one customized by the agency or one that is off-the-shelf. In the latter case, such software can range from a simple spreadsheet program, such as Excel, to a powerful statistical program such as SAS (which originally stood for Statistical Analysis Software).

13.74 Because the algorithm used in the construction of the index can be fairly complex, it is vital that statisticians and economists play a major role in developing the formula and also in verifying that the formula has been properly converted into the appropriate calculation module.

13.75 Although data collection agencies may have different rules for when to publish and when not to publish data (owing to confidentiality or index quality constraints), it is important that indices be reviewed every time they are calculated in order to ensure they meet some standards for publication. These rules can be as complex as use of variance estimates or as simple as verifying the index is constructed using a minimum number of respondents and items. Part of management’s responsibility is to ensure that that these rules are consistently applied and that they dovetail with publication rules in similar programs. It is important, however, to keep in mind that these rules need to be flexible enough to allow for the fact that commodity areas may manifest very different pricing traits. For example, price trends in fuels tend to be very uniform, whereas price trends for individual miscellaneous electronic components can vary dramatically. Another approach is to look for similar data, such as PPIs or CPIs, that can be used to verify price trends.

G. The Publication and Documentation Process

G.1 Publication

13.76 In recent years the publication process appears to have drawn closer attention for two reasons: first, with the rise of the Internet, there is greater concern regarding the security of data; and two, published economic data appear to be playing a larger role in the movement of prices in the stock market. Consequently, management should now give greater scrutiny to the publication process, the subject of Chapter 14. This has proven to be an area where good documentation has become especially important. There is usually a set amount of time between the time the indices are finalized and the time they are published. Frequently, there are a number of steps during the interim, including writing any appropriate text and possibly transmitting the data to a publication database.

13.77 In addition to tightening up documentation, agencies have also had to expend significant resources to ensure the security of their external and internal websites. Rules and procedures covering the electronic handling of sensitive data are usually established by the agency producing the data. However, the individual office that produces the data may have responsibility for making these procedures operational. Although XMPIs have traditionally not received the attention given to other price indices, an organization cannot afford to make the mistake of prematurely releasing any of its data.

13.78 Depending on the structure of the organization, successively higher levels of management and any other affected office as appropriate may need to be made aware of any impending news release. Often an agency may have a separate publication office responsible for coordinating agency outputs. If so, it is also good practice to work closely with this office in order to ascertain the types of questions that they may receive from users of the data.

13.79 Because of the similarity of XMPIs and PPIs, an organization may choose to release these data simultaneously. In such instances, it may be ideal to have the same staff produce the release and be prepared to answer questions from the media and other users.

13.80 Compilers of the index also may wish to visit the field occasionally and participate in or observe the price collection. This will provide them with a better appreciation of the practical problems associated with price collection, a better feel for data and index quality, and the skills required to help with price collection in the event of an emergency. In XMPIs, this may be of great importance, especially when collecting price transaction data in more complicated economic branches.

G.2 Documentation

13.81 The larger an organization, the more critical is good documentation. Staff, especially junior staff, should not have to rely on their memory when faced with a question of how to handle a specific issue.

13.82 Smaller organizations, too, need good documentation. Because a smaller organization may not have a large enough staff to have sufficient overlap of staff as new employees start and old ones leave, there may be a lack of what is called institutional memory, used to orally pass on data collection practices.

13.83 Offices with large systematized computer programming staff usually produce adequate system documentation. However, in small programs where any automated data processing may be handled by a statistician or economist, special care must be taken to ensure good documentation, because the training in those disciplines is less likely to include the appropriate type of documentation skills.

13.84 Good documentation should also include production schedules. Each aspect of the processing environment should have its own production schedule that needs to be integrated with each of the other schedules. This is true even though the production schedules may be on very different cycles. Much of the ongoing data collection and index calculation schedules are usually monthly (or quarterly), but the production or initiation of a sample of respondents may take a year or more. A process should be documented and in place that facilitates the overall development of an integrated schedule. Often unforeseen circumstances, such as weather or computer downtime, may force a change in the schedule. By having one process for scheduling changes, it ensures that the overall impact of any change can be effectively synchronized.

13.85 Manuals and other documents such as desk instructions may serve for initial training and later on should enable the collectors and compilers to remind themselves of all the relevant XMPI rules and procedures. Documents should be well organized and well indexed so that answers to problems can quickly be found.

13.86 All concerned should check the documentation and update it regularly; the pile of paper containing amendments should never grow large and should be replaced by a new consolidated version. One way of achieving this, for hard copies, is to have a loose-leaf manual so that individual pages can be replaced whenever necessary.

13.87 However, the use of a centralized electronic storage of documentation is increasing. This facilitates a systematic and controlled method for maintaining documentation. A variety of available software can help the statistical office. The benefits of using standard electronic software for documentation are threefold:

  • More efficient production of documentation, because software helps with initial compilation and reduces the need to print and circulate paper copies;

  • Better informed staff, because they have immediate electronic access to the latest documentation, including desk instructions with search facility by subject and author; and

  • Better quality control, because authors can readily amend and date-stamp updates, and access is restricted to “read only” nonauthors.

13.88 In a more sophisticated technological environment, documentation can be centrally maintained, with updates automatically promulgated to PCs or other electronic devices, thus obviating the need for manual updating.

13.89 Documentation includes not only price collectors’ and compilers’ manuals but also details of the many routines used in collection and compilation including features of product markets that have given rise to a particular method for use when there are missing values or a need for quality adjustments—such metadata are outlined in Chapter 9. It further includes metadata for users that should be posted on the statistical authority’s website. There should be a short user-friendly account for lay users along with frequently asked questions (and answers) and a more detailed technical manual along with technical articles on issues such as rebasing and, of course, data.

H. Quality Assurance

13.90 Though this chapter touched on some specific quality control techniques in the earlier data collection sections, there are a number of more general quality management areas and approaches one may also want to investigate. Statistical offices are faced with the continuous challenge of providing a wide range of outputs and services to meet user, that is, customer, needs. Thus, a key element of quality is customer focus and the effective dissemination of relevant, accurate, and timely statistics. In addition, a quality program should include effective customer education on the use of such statistics. In these terms, success can be measured by the achievement of a high level of satisfaction among well-informed users. The IMF has developed the Dissemination Standards Bulletin Board1 that provides dissemination standards and a data quality reference site.

13.91 For the quality management of XMPIs, it can be argued that the priority area is quality control of the production process itself. For most statistical offices, this will be an area that represents a high risk, given the complexity of the process and the financial implications of an error in the index. If the principles of organizing and managing the collection of data, and subsequent processing of information to produce XMPIs, are to be adopted, then it is vital that a quality management system is in place. This will ensure the data obtained, the processes involved in achieving the specified outputs, and the formulation of policies and strategies that drive them are managed in an effective, consistent manner. The data systems should, wherever possible, be open to verification and mechanisms put in place to ensure outputs meet requirements—in other words, customer satisfaction.

13.92 A number of examples and case studies of quality systems in practice illustrate how different models may be applied. Some models may be more suitable than others, depending on the exact mode of XMPI operations in different countries:

13.93 Total Quality Management, or TQM, is most closely identified with a management philosophy rather than a highly specified and structured system. The characteristics associated with TQM and an effective quality culture in an organization includes benchmarking, a process of comparing with, and learning from, others about what you do and how well you do it, with the aim of creating improvements. The Australian Bureau of Statistics has been particularly active in this area and undertook an exercise in 1998–2000 in partnership with the United Kingdom. Benchmarking projects have also been undertaken in New Zealand, the United States, and Scandinavian countries.

13.94 The European Foundation for Quality Management Excellence Model is a self-assessment diagnostic tool that is becoming widely used by government organizations across Europe to improve quality and performance. It may be described as a tool that drives the philosophy of TQM. It focuses on general business areas and assesses performance against five criteria covering what the business area does (the enablers: leadership, people, policy/strategy, partnership/resources, process) and four criteria covering what the business area achieves (the results: people results, customer results, society results, key performance results). Evidence based on feedback from focus groups, questionnaires, and personal interviews is used to score performance and a resulting action plan for improvement is introduced, which is then included in the business plan.

13.95 ISO 9000 is the International Standards Organization (ISO) international quality standard for management systems. The quality system is a commonsense, well-documented business management system that is applicable to all business sectors and that helps to ensure consistency and improvement of working practices, including the products and services produced. The ISO standards have been fully revised to match current philosophies of quality management and to provide the structures needed to ensure continuous improvement is maintained.

13.96 An independent advisory board is a common approach to addressing quality issues. Depending on membership, a board (or boards) can serve a multitude of purposes. Some boards may consist of technical experts who can provide advice on specific techniques used in the construction of price indices, whereas others may serve as more of a forum for users who want to ensure that the indices meet their needs. Boards can also serve as a method for helping to publicize new outputs to the community at large.

  • Abraham, Katherine G., John S. Greenlees, and Brent R. Moulton, 1998, “Working to Improve the Consumer Price Index,” Journal of Economic Perspectives, Vol. 12 (Winter), pp. 2736.

    • Search Google Scholar
    • Export Citation
  • Aczél, J., 1987, A Short Course on Functional Equations: Based Upon Recent Applications to the Social and Behavioral Sciences (Dordrecht, Netherlands: Reidel).

    • Search Google Scholar
    • Export Citation
  • Aizcorbe, Ana, Carol Corrado, and Mark Doms, 2001, “Constructing Price and Quantity Indexes for High Technology Goods” (Washington: Industrial Output Section, Division of Research and Statistics, Board of Governors of the Federal Reserve System, July). Also available asWhen Do Matched-Model and Hedonic Techniques Yield Similar Measures?Federal Reserve Bank of San Francisco Working Paper No. 2003-14. Available via the Internet: http://www.frbsf.org/publications/economics/papers/index.php?2005.

    • Search Google Scholar
    • Export Citation
  • Allen, Robert D., and W. Erwin Diewert, 1981, “Direct Versus Implicit Superlative Index Number Formulae,” Review of Economics and Statistics, Vol. 63 (August), pp. 43035.

    • Search Google Scholar
    • Export Citation
  • Alterman, William, 1991, “Price Trends in U.S. Trade: New Data, New Insights,” in International Economic Transactions, NBER Studies in Income and Wealth Vol. 55, ed. by Peter Hooper and J. David Richardson (Chicago: University of Chicago Press).

    • Search Google Scholar
    • Export Citation
  • Alterman, W.F., W. Erwin Diewert, and Robert C. Feenstra, eds., 1999, International Trade Price Indexes and Seasonal Commodities (Washington: Bureau of Labor Statistics).

    • Search Google Scholar
    • Export Citation
  • Alterman, William, David S. Johnson, and John Goth, 1987, “BLS Publishes Average Exchange Rate and Foreign Currency Price Indexes,” Monthly Labor Review (December), pp. 4749.

    • Search Google Scholar
    • Export Citation
  • Anderson, Richard G., Barry E. Jones, and Travis Nesmith, 1997, “Building New Monetary Services Indexes: Concepts, Data and Methods,” Federal Reserve Bank of St. Louis Review, Vol. 79 (January/February), pp. 5383.

    • Search Google Scholar
    • Export Citation
  • Angermann, Oswald, 1980, “External Terms of Trade of the Federal Republic of Germany Using Different Methods of Deflation,” Review of Income and Wealth, Vol. 26 (December), pp. 36785.

    • Search Google Scholar
    • Export Citation
  • Archibald, Robert B., 1977, “On the Theory of Industrial Price Measurement: Output Price Indexes,” Annals of Economic and Social Measurement, Vol. 6, No. 1, pp. 5772.

    • Search Google Scholar
    • Export Citation
  • Arguea, N.M., C. Hsiao, and G.A. Taylor, 1994, “Estimating Consumer Preferences Using Market Data—An Application to U.S. Automobile Demand,” Journal of Applied Econometrics, Vol. 9 (January–March), pp. 118.

    • Search Google Scholar
    • Export Citation
  • Armknecht, Paul A., Walter F. Lane, and Kenneth J. Stewart, 1997, “New Products and the U.S. Consumer Price Index,” in The Economics of New Goods, NBER Studies in Income and Wealth Vol. 58, ed. by Timothy F. Bresnahan and Robert J. Gordon (Chicago: University of Chicago Press), pp. 37591.

    • Search Google Scholar
    • Export Citation
  • Armknecht, Paul A., and Fenella Maitland-Smith, 1999, “Price Imputation and Other Techniques for Dealing with Missing Observations, Seasonality and Quality Change in Price Indices,” IMF Working Paper 99/78 (Washington: International Monetary Fund).

    • Search Google Scholar
    • Export Citation
  • Armknecht, Paul A., and Fenella Maitland-Smith, 2002, “Spurious Inflation: The Legacy of Laspeyres and Others,” Quarterly Review of Economics and Finance, Vol. 42 (Autumn) pp. 52942.

    • Search Google Scholar
    • Export Citation
  • Australian Bureau of Statistics, 1995, “Producer and International Trade Price Indexes,” Catalogue No. 6419.0 (Canberra). Available via the Internet: www.abs.gov.au.

    • Search Google Scholar
    • Export Citation
  • Australian Bureau of Statistics, 2001, “Stages of Production Producer Price Indexes,” Australia, Catalogue No. 6426.0 (Canberra). Available via the Internet: www.abs. gov.au.

    • Search Google Scholar
    • Export Citation
  • Baldwin, Andrew, 1990, “Seasonal Baskets in Consumer Price Indexes,” Journal of Official Statistics, Vol. 6 (September), pp. 25173.

    • Search Google Scholar
    • Export Citation
  • Baldwin, Andrew, 2002, “The Redesign of the Farm Product Price Index: Questions and Answers” (Ottawa: Industry Measures and Analysis Division, Statistics Canada, May).

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 1980a, Seasonal Products in Agriculture and Horticulture and Methods for Computing Price Indices, Statistical Studies No. 24 (The Hague: Netherlands Central Bureau of Statistics).

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 1980b, “Seasonal Commodities and the Construction of Annual and Monthly Price Indexes,” Statistical Papers, Vol. 21 (June), pp. 11016.

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 1980c, “A Method for Constructing Price Indices for Seasonal Commodities,” Journal of the Royal Statistical Society, Series A, Vol. 143, No. 1 pp. 6875.

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 1981, “A Simple Method for Constructing Price Indices for Seasonal Commodities,” Statistical Papers, Vol. 22 (March), pp. 7278.

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 1983, “Does There Exist a Relation Between Inflation and Relative Price-Change Variability? The Effect of the Aggregation Level,” Economics Letters, Vol. 13, (No. 2–3), pp. 17380.

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 1985, “A Simple Characterization of Fisher’s Price Index,” Statistical Papers, Vol. 26 (December), pp. 5963.

  • Balk, Bert M., 1989, “Changing Consumer Preferences and the Cost-of-Living Index: Theory and Nonparametric Expressions,” Journal of Economics, Vol. 50 (June), pp. 15769.

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 1994, “On the First Step in the Calculation of a Consumer Price Index,” paper prepared for the International Conference on Price Indices, First Meeting hosted by Statistics Canada, Ottawa, October 31–November 4.

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 1995, “Axiomatic Price Index Theory: A Survey,” International Statistical Review, Vol. 63, pp. 6993.

  • Balk, Bert M., 1996a, “A Comparison of Ten Methods for Multilateral International Price and Volume Comparison,” Journal of Official Statistics, Vol. 12 (June), pp. 199222.

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 1996b, “Consistency-in-Aggregation and Stuvel Indices,” Review of Income and Wealth, Vol. 42 (September), pp. 35363.

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 1998a, Industrial Price, Quantity, and Productivity Indices: The Micro-Economic Theory and an Application (Boston: Kluwer Academic).

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 1998b, “On the Use of Unit Value Indices as Consumer Price Subindices,” paper prepared for the International Conference on Price Indices, Fourth Meeting hosted by the Bureau of Labor Statistics, Washington, April 22–24.

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 2000a, “Divisia Price and Quantity Indexes 75 Years After” (unpublished; Voorburg, Netherlands: Department of Statistical Methods, Statistics Netherlands).

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 2000b, “On Curing the CPI’s Substitution and New Goods Bias,” Research Paper 0005 (Voorburg, Netherlands: Department of Statistical Methods, Statistics Netherlands). Presented at the Fifth Meeting of the International Working Group on Price Indices, 25–27 August 1999, Reykjavik; at the Joint ECE/ILO Meeting on Consumer Price Indices, 3–5 November 1999, Geneva; and at the Fourth Conference on Methodological Issues in Official Statistics, 12–13 October 2000, Stockholm.

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 2001, “Aggregation Methods in International Comparisons: What Have We Learned?” Report Series Research in Management ERS-2001-41-MKT, Erasmus Research Institute of Management (Rotterdam: Erasmus University). Available via the Internet: www.rsm.nl/portal/pls/portal/xopus_public.download_document?p_ guid=298255C5FD4A09A2E0401BAC4D010CA9.

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., 2004, “Decompositions of Fisher Indexes,” Economics Letters, Vol. 82 (January), pp. 10713.

  • Balk, Bert M., 2005, “Price Indexes for Elementary Aggregates: The Sampling Approach,” Journal of Official Statistics, Vol. 21 (December), pp. 67599.

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., and W. Erwin Diewert, 2001, “A Characterization of the Törnqvist Price Index,” Economics Letters, Vol. 72 (September), pp. 27981.

    • Search Google Scholar
    • Export Citation
  • Balk, Bert M., and H.M.P. Kersten, 1986, “On the Precision of Consumer Price Indices Caused by the Sampling Variability of Budget Surveys,” Journal of Economic and Social Measurement, Vol. 14, pp. 1935.

    • Search Google Scholar
    • Export Citation
  • Bartik, Timothy J., 1988, “Measuring the Benefits of Amenity Improvements in Hedonic Price Models,” Land Economics, Vol. 64 (May), pp. 17283.

    • Search Google Scholar
    • Export Citation
  • Barnett, William, 1978, “The User Cost of Money,” Economics Letters, Vol. 1, No. 22, pp. 14549.

  • Barnett, William, 1980, “Economic Monetary Aggregates: An Application of Index Number and Aggregation Theory,” Journal of Econometrics, Vol. 14 (September), pp. 1148.

    • Search Google Scholar
    • Export Citation
  • Bean, L.H., and O.C. Stine, 1924, “Four Types of Index Numbers of Farm Prices,” Journal of the American Statistical Association, Vol. 19 (March), pp. 3035.

    • Search Google Scholar
    • Export Citation
  • Becker, Gary S., 1965, “A Theory of the Allocation of Time,” Economic Journal, Vol. 75 (September), pp. 493517.

  • Bénabou, Roland, and Robert Gertner, 1993, “Search with Learning from Prices: Does Increased Inflationary Uncertainty Lead to Higher Markups?Review of Economic Studies, Vol. 60 (January), pp. 6994.

    • Search Google Scholar
    • Export Citation
  • Berndt, Ernst R., 1983, “Quality Adjusted Prices, Hedonics, and Modern Empirical Demand Theory,” in Price Level Measurement: Proceedings from a Conference Sponsored by Statistics Canada, ed. by W. Erwin Diewert and C. Montmarquette (Ottawa: Statistics Canada), pp. 81763.

    • Search Google Scholar
    • Export Citation
  • Berndt, Ernst R., 1991, The Practice of Econometrics: Classic and Contemporary (Reading Massachusetts: Addison–Wesley).

  • Berndt, Ernst R., Linda T. Bui, David H. Lucking-Reiley, and Glen L. Urban, 1997, “The Roles of Marketing, Product Quality, and Price Competition in the Growth and Composition of the U.S. Antiulcer Drug Industry,” in The Economics of New Goods, NBER Studies in Income and Wealth Vol. 58, ed. by Timothy F. Bresnahan and Robert J. Gordon (Chicago: University of Chicago Press), pp. 27732.

    • Search Google Scholar
    • Export Citation
  • Berndt, Ernst R., Zvi Griliches, and Neal J. Rappaport, 1995, “Econometric Estimates of Price Indexes for Personal Computers in the 1990’s,” Journal of Econometrics, Vol. 68 (July), pp. 24368.

    • Search Google Scholar
    • Export Citation
  • Berndt, Ernst R., Zvi Griliches, and Joshua G. Rosett, 1993, “Auditing the Producer Price Index: Micro Evidence from Prescription Pharmaceutical Preparations,” Journal of Business and Economic Statistics, Vol. 11 (July), pp. 25164.

    • Search Google Scholar
    • Export Citation
  • Berndt, Ernst R., Margaret K. Kyle, and Davina C. Ling, 2003, “The Long Shadow of Patent Expiration: Generic Entry and RX-to-OTC Switches,” in Scanner Data and Price Indexes, NBER Studies in Income and Wealth Vol. 64, ed. by Robert C. Feenstra and Matthew D. Shapiro (Chicago: University of Chicago Press), pp. 22973.

    • Search Google Scholar
    • Export Citation
  • Berry, Steven, James Levinsohn, and Ariel Pakes, 1995, “Automobile Prices in Market Equilibrium,” Econometrica, Vol. 63 (July), pp. 84190. Also published as NBER Working Paper No. 4264, July 1996 (Cambridge, Massachusetts: National Bureau of Economic Research). Available via the Internet: www.nber.org/papers/w4264.

    • Search Google Scholar
    • Export Citation
  • Blackorby, Charles, Daniel Primont, and R. Robert Russell, 1978, Duality, Separability, and Functional Structure: Theory and Economic Applications (New York: Elsevier North-Holland).

    • Search Google Scholar
    • Export Citation
  • Bodé, Ben, and Jan van Dalen, 2001, “Quality-Corrected Price Indexes of New Passenger Cars in the Netherlands, 1990–1999,” paper prepared for the International Conference on Price Indices, Sixth Meeting, hosted by the Australian Bureau of Statistics, Canberra, April 2–6.

    • Search Google Scholar
    • Export Citation
  • Bortkiewicz, L.v., 1923, “Zweck und Struktur einer Preisindexzahl,” Nordisk Statistisk Tidskrift, Vol. 2, pp. 369408.

  • Boskin, Michael J.S., chair, 1996, “Toward a More Accurate Measure of the Cost of Living,” Final Report to the Senate Finance Committee, Advisory Commission to Study the Consumer Price Index, Washington, December 4.

    • Search Google Scholar
    • Export Citation
  • Boskin, Michael J.S., chair, Ellen R. Dulberger, Robert J. Gordon, Zvi Griliches, and Dale W. Jorgenson, 1998, “Consumer Prices, the Consumer Price Index, and the Cost of Living,” Journal of Economic Perspectives, Vol. 12 (Winter), pp. 326.

    • Search Google Scholar
    • Export Citation
  • Bowley, Arthur L., 1899, “Wages, Nominal and Real,” in Dictionary of Political Economy, Vol. 3, ed. by R.H. Inglis Palgrave (London: Macmillan), pp. 64051.

    • Search Google Scholar
    • Export Citation
  • Bowley, Arthur L., 1901, Elements of Statistics (London: P.S. King & Son).

  • Bowley, Arthur L., 1919, “The Measurement of Changes in the Cost of Living,” Journal of the Royal Statistical Society, Vol. 82, pp. 34372.

    • Search Google Scholar
    • Export Citation
  • Bowley, Arthur L., 1921, “An Index of the Physical Volume of Production,” Economic Journal, Vol. 31 (June), pp. 196205.

  • Bowley, Arthur L., 1922, “The Definition of National Income,” Economic Journal, Vol. 32 (June), pp. 111.

  • Bradley, Ralph, 2005, “Pitfalls of Using Unit Values as a Price Measure or Price Index,” Journal of Economic and Social Measurement, Vol. 30, No. 1, pp. 3961.

    • Search Google Scholar
    • Export Citation
  • Bradley, Ralph, Bill Cook, Sylvia G. Leaver, and Brent R. Moulton, 1997, “An Overview of Research on Potential Uses of Scanner Data in the U.S. CPI,” paper prepared for the International Conference on Price Indices, Third Meeting, hosted by Statistics Netherlands, Voorburg, April 16–18.

    • Search Google Scholar
    • Export Citation
  • Bresnahan, Timothy F., 1997, “Comment” on Jerry R. Hausman’sValuation of New Goods under Perfect and Imperfect Conditions,” in The Economics of New Goods, NBER Studies in Income and Wealth Vol. 58, ed. by Timothy F. Bresnahan and Robert J. Gordon (Chicago: University of Chicago Press).

    • Search Google Scholar
    • Export Citation
  • Bucknall, Robert, Markus Sova, and John Wood, 2005Estimating Standard Errors of Movements in Producer Price Indices,” in Proceedings of the GSS Methodology Conference 2005 (London: Office for National Statistics). Available at www.statistics.gov.uk/events/gss2005/agenda.asp.

    • Search Google Scholar
    • Export Citation
  • Bureau of the Census, 2002, “U.S. Goods Trade: Imports and Exports by Related Parties; 2001,” United States Department of Commerce News, Economics and Statistics Information, Bureau of the Census, May 7. Available via the Internet: www.census.gov/foreign-trade/Press-Release/2001pr/aip/rp01.pdf.

    • Search Google Scholar
    • Export Citation
  • Burns, Arthur F., 1930, “The Measurement of the Physical Volume of Production,” Quarterly Journal of Economics, Vol. 44 (February), pp. 24262.

    • Search Google Scholar
    • Export Citation
  • Carli, Gian-Rinaldo, 1804, “Del valore e della proporzione de’ metalli monetati,” in Scrittori classici italiani di economia politica, Vol. 13, by Domenico di Gennaro Cantalupo, Giovanni Rinaldo Carli, Pietro Verri (Milan: G.G. Destefanis), pp. 297366. Originally published in 1764.

    • Search Google Scholar
    • Export Citation
  • Carruthers, A.G., D.J. Sellwood, and P.W. Ward, 1980, “Recent Developments in the Retail Prices Index,” The Statistician, Vol. 29 (March), pp. 132.

    • Search Google Scholar
    • Export Citation
  • Cas, Alexandra, and Thomas K. Rymes, 1991, On Concepts and Measures of Multifactor Productivity in Canada 1961–1980 (London: Cambridge University Press).

    • Search Google Scholar
    • Export Citation
  • Cassel, Eric, and Robert Mendelsohn, 1985, “On the Choice of Functional Forms for Hedonic Price Equations: Comment,” Journal of Urban Economics, Vol. 18 (September), pp. 13542.

    • Search Google Scholar
    • Export Citation
  • Caves, Douglas W., Laurits R. Christensen, and W. Erwin Diewert, 1982a, “Multilateral Comparisons of Output, Input and Productivity Using Superlative Index Numbers,” Economic Journal, Vol. 92 (March), pp. 7386.

    • Search Google Scholar
    • Export Citation
  • Caves, Douglas W., Laurits R. Christensen, and W. Erwin Diewert, 1982b, “The Economic Theory of Index Numbers and the Measurement of Input, Output, and Productivity,” Econometrica, Vol. 50, (November), pp. 13931414.

    • Search Google Scholar
    • Export Citation
  • Cecchetti, Stephen G., 1997, “Measuring Short-Run Inflation for Central Bankers,” Federal Reserve Bank of St. Louis Review, Vol. 79 (May/June), pp. 14355.

    • Search Google Scholar
    • Export Citation
  • Christensen, Laurits R., Dale W. Jorgenson, and L.J. Lau, 1971, “Conjugate Duality and the Transcendental Logarithmic Production Function,” Econometrica, Vol. 39 (July), pp. 25556.

    • Search Google Scholar
    • Export Citation
  • Clements, Kenneth W., and H.Y. Izan, 1981, “A Note on Estimating Divisia Index Numbers,” International Economic Review, Vol. 22 (October), pp. 74547.

    • Search Google Scholar
    • Export Citation
  • Clements, Kenneth W., and H.Y. Izan, 1987, “The Measurement of Inflation: A Stochastic Approach,” Journal of Business and Economic Statistics, Vol. 5 (July), pp. 33950.

    • Search Google Scholar
    • Export Citation
  • Cobb, Charles W., and Paul H. Douglas, 1928, “A Theory of Production,” American Economic Review, Vol. 18 (March), pp. 13965.

  • Cochran, William G., 1977, Sampling Techniques (New York: Wiley; 3rd ed.).

  • Cockburn, Iain M., and Aslam H. Anis, 1998, “Hedonic Analysis and Arthritic Drugs,” NBER Working Paper No. 6574 (Cambridge, Massachusetts: National Bureau of Economic Research). Available via the Internet: www.nber.org/papers/w6574.

    • Search Google Scholar
    • Export Citation
  • Coggeshall, F., 1886, “The Arithmetic, Geometric, and Harmonic Means,” Quarterly Journal of Economics, Vol. 1 (October), pp. 8386.

    • Search Google Scholar
    • Export Citation
  • Commission of the European Communities (Eurostat), International Monetary Fund, Organisation for Economic Cooperation and Development, United Nations, and World Bank, 1993, System of National Accounts 1993 (New York: United Nations).

    • Search Google Scholar
    • Export Citation
  • Commission of the European Communities, International Monetary Fund, Organization for Economic Cooperation and Development, United Nations, and World Bank, 2008, System of National Accounts 2008, Volume 1 (New York: United Nations). Available via the Internet: http://unstats.un.org/unsd/sna1993/draftingphase/ChapterList.asp.

    • Search Google Scholar
    • Export Citation
  • Cope, Ian, and David Freeman, 1998, “Improving the Quality of the Producer Price Index,” Economic Trends, No. 541, pp. 6374.

  • Copithorne, L., 1976, “La théorie des prix des transfert internes des grandes sociétés,” L’actualité économique, Vol. 52, pp. 32452.

    • Search Google Scholar
    • Export Citation
  • Court, Andrew T., 1939, “Hedonic Prices with Automobile Examples,” in The Dynamics of Automobile Demand (New York: General Motors Corporation), pp. 99117.

    • Search Google Scholar
    • Export Citation
  • Court, L.M., and H.G. Lewis, 1942–43, “Production Cost Indices,” Review of Economic Studies, Vol. 10 (Winter), pp. 2842.

  • Cropper, Maureen L., Leland B. Deck, and Kenneth E. McConnell, 1988, “On the Choice of Functional Form for Hedonic Price Functions,” Review of Economics and Statistics, Vol. 70 (Nov), pp. 66875.

    • Search Google Scholar
    • Export Citation
  • Crump, Norman, 1924, “The Interrelation and Distribution of Prices and Their Incidence upon Price Stabilization,” Journal of the Royal Statistical Society, Vol. 87 (March), pp. 167219.

    • Search Google Scholar
    • Export Citation
  • Curry, Bruce, Peter Morgan, and Mick Silver, 2001, “Hedonic Regressions: Misspecification and Neural Networks,” Applied Economics, Vol. 33 (April), pp. 65971.

    • Search Google Scholar
    • Export Citation
  • Czinkota, Michael R., and Ilkka Ronkainen, 1997, “International Business and Trade in the Next Decade: Report from a Delphi Study,” Journal of International Business Studies, Vol. 28 (December), pp. 82744.

    • Search Google Scholar
    • Export Citation
  • Dalén, Jörgen, 1992, “Computing Elementary Aggregates in the Swedish Consumer Price Index,” Journal of Official Statistics, Vol. 8 (June), pp. 12947.

    • Search Google Scholar
    • Export Citation
  • Dalén, Jörgen, 1994, “Sensitivity Analyses for Harmonising European Consumer Price Indices,” paper presented at the International Conference on Price Indices, First Meeting, hosted by Statistics Canada, Ottawa, October 31–November 4.

    • Search Google Scholar
    • Export Citation
  • Dalén, Jörgen, 1997, “Experiments with Swedish Scanner Data,” paper presented at the International Conference on Price Indices, Third Meeting, hosted by Statistics Netherlands, Voorburg, April 16–18.

    • Search Google Scholar
    • Export Citation
  • Dalén, Jörgen, 1998, “On the Statistical Objective of a Laspeyres’ Price Index,” paper prepared for the International Conference on Price Indices, Fourth Meeting, hosted by the Bureau of Labor Statistics, Washington, April 22–24.

    • Search Google Scholar
    • Export Citation
  • Dalén, Jörgen, 2001, “Statistical Targets for Price Indexes in Dynamic Universes,” paper presented at the International Conference on Price Indices, Sixth Meeting, hosted by the Australian Bureau of Statistics, Canberra, April 2–6.

    • Search Google Scholar
    • Export Citation
  • Davies, George R., 1924, “The Problem of a Standard Index Number Formula,” Journal of the American Statistical Association, Vol. 19, pp. 18088.

    • Search Google Scholar
    • Export Citation
  • Davies, George R., 1932, “Index Numbers in Mathematical Economics,” Journal of the American Statistical Association, Vol. 27, pp. 5864.

    • Search Google Scholar
    • Export Citation
  • de Haan, Jan, 2001, “Generalised Fisher Price Indexes and the Use of Scanner Data in the CPI,” paper presented at the International Conference on Price Indices, Sixth Meeting, hosted by the Australian Bureau of Statistics, Canberra, April 2–6.

    • Search Google Scholar
    • Export Citation
  • de Haan, 2003, “Direct and Indirect Time Dummy Approaches to Hedonic Price Measurement,” paper presented at the International Conference on Price Indices, Seventh Meeting, hosted by INSEE, Paris, May 27–29.

    • Search Google Scholar
    • Export Citation
  • de Haan, 2004, “Estimating Quality-Adjusted Unit Value Indexes: Evidence from Scanner Data,” paper presented at the Seventh EMG Workshop, Sydney, December 12–14. Also presented at the SSHRC International Conference on Index Number Theory and the Measurement of Prices and Productivity, Vancouver, June 30–July 3.

    • Search Google Scholar
    • Export Citation
  • de Haan, 2007, “Hedonic Price Indexes: A Comparison of Imputation, Time Dummy, and Other Approaches,” paper presented at the International Conference on Price Indices, Tenth Meeting, hosted by Statistics Canada, Ottawa, October 9–12. Available at: www.ottawagroup2007.ca/ogo_r003_e.htm.

    • Search Google Scholar
    • Export Citation
  • de Haan, and Eddy Opperdoes, 1997, “Estimation of the Coffee Price Index Using Scanner Data: The Choice of the Micro Index,” paper presented at the International Conference on Price Indices, Third Meeting, hosted by Statistics Netherlands, Voorburg, April 16–18.

    • Search Google Scholar
    • Export Citation
  • de Haan, and Eddy Opperdoes, and C.M. Schut, 1999, “Item Selection in the Consumer Price Index: Cut-Off Versus Probability Sampling,” Survey Methodology, Vol. 25 (June), pp. 3144.

    • Search Google Scholar
    • Export Citation
  • Debreu, Gérard, 1952, “A Social Equilibrium Existence Theorem,” Proceedings of the National Academy of Sciences, Vol. 38 (October 15), pp. 88693.

    • Search Google Scholar
    • Export Citation
  • Debreu, Gérard, 1959, Theory of Value: An Axiomatic Analysis of Economic Equilibrium (New York: Wiley).

  • Decoster, Renaud, 2003a, “Import and Export Price Indices: A Comparison of Import Unit Value Indices and Import Specific Price Indices for Four EU Member States,” Second Report, Study Performed for Eurostat Unit C-4: Methodology, Nomenclature and Statistics of External and Intra-Community Trade (Paris: PLANISTAT Europe).

    • Search Google Scholar
    • Export Citation
  • Decoster, Renaud, 2003b, Import and Export Price Indices: Final Report, Study Performed for Eurostat Unit 0074 C-4: Methodology, Nomenclature and Statistics of External and Intra-Community Trade (Paris: PLANISTAT Europe).

    • Search Google Scholar
    • Export Citation
  • Denny, M., 1974, “The Relationship Between Functional Forms for the Production System,” Canadian Journal of Economics, Vol. 7 (February), pp. 2131.

    • Search Google Scholar
    • Export Citation
  • Diewert, W. Erwin, 1973, “Functional Forms for Profit and Transformation Functions,” Journal of Economic Theory, Vol. 6 (June), pp. 284316.

    • Search Google Scholar
    • Export Citation
  • Diewert, W. Erwin, 1974a, “Applications of Duality Theory,” in Frontiers of Quantitative Economics, Vol. II, ed. by M.D. Intrilligator and D.A. Kendrick (Amsterdam: North-Holland), pp. 10671. Available via the Internet: www.econ.ubc.ca/diewert/theory.pdf.

    • Search Google Scholar
    • Export Citation
  • Diewert, W. Erwin, 1974b, “Functional Forms for Revenue and Factor Requirements Functions,” International Economic Review, Vol. 15 (February), pp. 11930.

    • Search Google Scholar
    • Export Citation
  • Diewert, W. Erwin, 1974c, “Intertemporal Consumer Theory and the Demand for Durables,” Econometrica, Vol. 42 (May), pp. 497516.

  • Diewert, W. Erwin, 1976, “Exact and Superlative Index Numbers,” Journal of Econometrics, Vol. 4 (May), pp. 1145.

  • Diewert, W. Erwin, 1978, “Superlative Index Numbers and Consistency in Aggregation,” Econometrica, Vol. 46 (July), pp. 883900.

  • Diewert, W. Erwin, 1980, “Aggregation Problems in the Measurement of Capital,” in The Measurement of Capital, NBER Studies in Income and Wealth Vol. 45, ed. by Dan Usher (Chicago: University of Chicago Press), pp. 433528.

    • Search Google Scholar
    • Export Citation
  • Diewert, W. Erwin, 1983a, “The Theory of the Output Price Index and the Measurement of Real Output Change,” in Price Level Measurement: Proceedings from a Conference Sponsored by Statistics Canada, ed. by W.E. Diewert and C. Montmarquette (Ottawa: Statistics Canada) pp. 10491113.

    • Search Google Scholar
    • Export Citation
  • Diewert, W. Erwin, 1983b, “The Treatment of Seasonality in a Cost of Living Index,” in Price Level Measurement: Proceedings from a Conference Sponsored by Statistics Canada, ed. by W. Erwin Diewert and C. Montmarquette (Ottawa: Statistics Canada), pp. 101945.

    • Search Google Scholar
    • Export Citation
  • Diewert, W. Erwin, 1985, “Transfer Pricing and Economic Efficiency,” in Multinationals and Transfer Pricing, Croom Helm Series in International Business, ed. by A.M. Rugman and L. Eden (London: Croom Helm), pp. 4781.

    • Search Google Scholar
    • Export Citation
  • Diewert, W. Erwin, 1990, “The Theory of the Cost-of-Living Index and the Measurement of Welfare Change,” in Price Level Measurement, Contributions to Economic Analysis 196, ed. by W. Erwin Diewert (Amsterdam: North-Holland), pp. 79147.

    • Search Google Scholar
    • Export Citation
  • Diewert, W. Erwin, 1992a, “Fisher Ideal Output, Input and Productivity Indexes Revisited,” Journal of Productivity Analysis, Vol. 3 (September), pp. 21148.

    • Search Google Scholar
    • Export Citation
  • Diewert, W. Erwin, 1992b, “Exact and Superlative Welfare Change Indicators,” Economic Inquiry, Vol. 30 (October), pp. 56582.

  • Diewert, W. Erwin, 1993a, “The Early History of Price Index Research,” in Essays in Index Number Theory, Vol. 1, ed. by W. Erwin Diewert and A.O. Nakamura (Amsterdam: North-Holland), pp. 3365.

    • Search Google Scholar
    • Export Citation
  • Diewert, W. Erwin, 1993b, “Duality Approaches to Microeconomic Theory,” in Essays in Index Number Theory, Vol. 1, ed. by W. Erwin Diewert and A.O. Nakamura (Amsterdam: North-Holland), pp. 10575.

    • Search Google Scholar
    • Export Citation
  • Diewert, W. Erwin, 1993c, “Symmetric Means and Choice Under Uncertainty,” in Essays in Index Number Theory, Vol. 1, ed. by W. Erwin Diewert and A.O. Nakamura (Amsterdam: North-Holland), pp. 355433.

    • Search Google Scholar
    • Export Citation
  • Diewert, W. Erwin, 1993d, “Overview of Volume 1,” in Essays in Index Number Theory, Vol. 1, ed. by W. Erwin Diewert and A.O.