Chained,exact and superlative hedonic price changes: estimates from microdata

Scanner data are used to calculate chained, exact (and superlative) hedonic price indexes for television sets. The data source is available for a wide range of goods, the application providing an example of how this method can be more widely applied. The indexes correspond to constant utility, hedonic cost-of-living indexes. The approach improves on the existing direct method, which takes its estimates directly from the coefficients on time dummies in a hedonic regression. It also improves on the matched model method used by statistical agencies. The differences between actual price changes and exact hedonic quality-adjusted price changes are found to be substantial. Base-period and current-period weighted exact hedonic indexes are similar, thus providing good approximations to a superlative index. Estimates from the direct, dummy variable approach were compared to the superlative indexes. The disparities between the results argue for caution in the use of the direct, dummy variable approach to estimating quality-adjusted price changes.     

Faster,smaller, cheaper: an hedonic price analysis of PDAs

We compute quality-adjusted price indexes for personal digital assistants (PDAs) for the period 1999 to 2004. Hedonic regressions indicate that prices are related to processor generation and clock speed, memory capacity, screen size and quality and the presence of a digital camera or wireless capability. A particularly salient feature of PDAs is portability, where we find: (i) purchasers value the energy density of the battery technology (e.g. lithium ion) rather than the battery life in hours; and (ii) the physical characteristics of the PDA (e.g. weight, volume) are nonlinearly related to price, suggesting that valuation of the physical form of PDAs does not bear a simple linear relationship to characteristics, either in absolute terms (‘smaller is better’) or vs. an ergonomic ‘sweet spot’. Rather, portability characteristics are correlated with other desirable attributes, making the relationship between price and portability difficult to disentangle. However, hedonic price indexes are robust across different measures of the portability of PDAs. Hedonic indexes using the dummy variable, characteristics prices, and imputation approaches decline on average between 19 and 26% per year. A matched model price index computed from a subset of observations declines at 19% per year, while a fixed-effects hedonic index declines at 14% per year.     

How Fast are Semiconductor Prices Falling?

The Producer Price Index (PPI) for the U.S. suggests that semiconductor prices have barely been falling in recent years, a dramatic contrast to the rapid declines reported from the mid‐1980s to the early 2000s. This slowdown in the rate of decline is puzzling in light of evidence that the performance of microprocessor units (MPUs) has continued to improve at a rapid pace. Over the course of the 2000s, the MPU prices posted by Intel, the dominant producer of MPUs, became much stickier over the chips' life cycle. As a result of this change, we argue that the matched‐model methodology used in the PPI for MPUs likely started to be biased after the early 2000s and that hedonic indexes can provide a more accurate measure of price change since then. MPU prices fell rapidly through 2004 on every price measure we present, with the PPI declining at an even quicker pace than the hedonic indexes. However, from 2004 to 2009, our preferred hedonic index fell faster than the PPI, and from 2009 to 2013 the gap widened further, with our preferred index falling at an average annual rate of 42 percent, while the PPI declined at only a 6 percent rate. Given that MPUs currently represent about half of U.S. shipments of semiconductors, this difference has important implications for gauging the rate of innovation in the semiconductor sector.     

Technical change, prices and communications technology: Insights from the Local Area Networking industry

We use hedonic regressions to analyse price changes in two categories of Local Area Networking (LAN) equipment: hubs and switches. Constant quality price indexes are constructed from the regressions and contrasted with available indexes constructed for the same type of equipment. We find that prices fell at an average annual rate between 22% and 33% during the 1990s. The results suggest that beside falling prices of inputs (i.e. semiconductors), technical change in the LAN equipment may be responsible for the decrease in the prices of communication equipment during the 1990s.     

ASSESSING THE QUALITY ERROR IN OUTPUT MEASURES: THE CASE OF REFRIGERATORS*

This paper computes new indexes of output for refrigerators, using hedonic methods to adjust for quality change. The hedonic technique is applied in a new way (it is used to make quality adjustments to prices before they are used in the index), and the results are compared with those from methods used in previous hedonic investigations. There are three major findings. (1) Overall (1960–1972), our hedonic deflated output series rise more rapidly than conventional measures, because the price indexes used for deflation rise more slowly. (2) The output measures fluctuate more than do output measures produced by conventional methods, because adding hedonic quality adjustments to WPI indexes moves them up in some years and down in others, and the resulting adjustments to the output series were positively correlated with changes in output. (3) Applying methods used in previous studies produces larger adjustments to the published indexes, suggesting that some of the differences noted in previous studies between hedonic indexes and official published indexes are related to computational methods, not to quality adjustment.     

特征价格模型的发展应用研究

特征价格模型因为其完美的理论思想而成为国际上普遍使用的分析异质品价格和特征关系的主要方法.本文通过对国外核心期刊上一百五十二篇特征价格法相关文献的检阅,梳理了国内外特征价格模型及指数编制的研究现状,对特征价格模型的功能进行了总结性定位,认为特征价格模型的功能主要在于:异质品价格指数的编制,异质品价格预测、价值评估或产品定价,异质品价格影响因素分析,非市场因素的经济效应的检验及对传统经济学模型的改进五方面.文章最后以住宅为例,归纳总结了特征价格法在研究应用中存在的主要问题:一是市场细分;二是特征变量选择和量化;三是模型形式选择;四是模型估计方法的研究;五是指数编制中的问题.这些研究对象为未来特征价格的研究提供了可行参考.     

Alternative Land-Price Indexes for Commercial Properties in Tokyo

The System of National Accounts (SNA) requires separate estimates for the land and structure components of a commercial property. Using transactions data for the sales of office buildings in Tokyo, a hedonic regression model (the “builder’s model”) was estimated and this model generated an overall property price index as well as subindexes for the land and structure components of the office buildings. The builder’s model was also estimated using appraisal data on office building real estate investment trusts (REITs) for Tokyo. These hedonic regression models also generated estimates for net depreciation rates, which can be compared. Finally, the Japanese government constructs annual official land prices for commercial properties based on appraised values. The paper compares these official land prices with the land prices generated by the hedonic regression models based on transactions data and on REIT data. The results reveal that commercial property indexes based on appraisal and assessment prices lag behind the indexes based on transaction prices.     

The product life cycle and sample representativity bias in price indexes

Official price indexes are usually calculated using matched samples of products. If products exhibit systematic price trends at different points in their life cycle then matched sample methods may introduce bias if the life cycle movement in the sample does not adequately reflect that in the population. This article explores the extent of these life cycle pricing effects and then examines the bias it can introduce in measured inflation. A large US supermarket scanner data set for six cities and six products over 12 years is used. Using hedonic methods we find that the life cycle component of price change is important across a range of products and cities. To explore the bias introduced by these movements, we use simulations that construct indexes with different sample update frequency. For indexes that are never completely resampled, we find an annual absolute bias of 0.88 and 0.59 percentage points depending upon whether we use the actual prices or prices imputed from our hedonic model. This compares with absolute biases of 0.34 and 0.10 percentage points for the corresponding cases for samples, which are re-selected annually. Thus our results provide strong support for more frequently updating index samples.     

Approaches to performance measurement in hedonic analysis: Price indexes for laptop computers in the 1990's

This paper estimates price indexes for laptop personal computers using hedonic methods and data taken from PC Magazine technical reviews. We use benchmark test results to construct a measure of system performance that encapsulates factors that have previously gone unmeasured, such as the interactions between hardware components. The resulting hedonic function is parsimonious yet has good explanatory power. A second approach to performance measurement is developed using a set of technical proxies that are shown to closely approximate the benchmark test scores, and are thus nearly perfectly equivalent in terms of resulting price index estimates. While not as parsimonious as a single performance measure, these proxies have the advantage of not requiring direct performance testing, and could thus be applied to larger data sets. Laptops were found to have declined in quality-adjusted price at an average rate of 40% per year for the period 1990-1998.     

Estimating Quality‐adjusted Price Changes: Method and Application to VCRs

This paper uses scanner data to generate estimates of quality‐adjusted price changes for video‐recorders. We use hedonic regressions to derive estimates of the changing worth of each quality component. These are then applied to weighted changes in the mix of quality attributes of products to derive estimates of quality‐adjusted price (QAP) changes. The data source used is electronic‐point‐of‐sale (EPOS) scanner data that are available for a wide range of goods. This study provides an example of how such methods can be more widely applied. The estimates of QAP changes correspond to constant‐utility, (hedonic) cost‐of‐living indexes defined in economic theory as the ratio of expenditure functions at constant utility allowing for changing prices and characteristics of goods. This method is proposed as an improvement on the existing direct method , which takes its estimates directly from the coefficients associated with 'time dummies' in a hedonic regression. We finally undertake a matching process, akin to that used by statistical offices, and compare the results. Direct comparisons with RPI estimates and these hedonic approaches are not easy since the approaches use quite different data sets. Our replication of a procedure akin to that used for the RPI on the scanner data set provides insights into sources of potential bias.     

Path dependence of the general price level: A value theoretic analysis

The paper examines path dependence of price indexes, a problem that has become acute after international adoption of chain indexes for price and volume changes in the SNA93. Path dependence is an old issue of index numbers, and has been in the way of using chain indexes ever since their invention. The paper accepts chaining at its start, and tries to develop a sound deflation procedure from there. In this analysis path dependence is less an issue of appropriate formalization of a given concept, the traditional approach in index number theory, but rather a problem of developing an interpretation to a given and now worldwide recommended statistical practice. The key issue is found in the fact that money is not only the standard means of payment, concerning central banks, but also the standard of value in an economy, a feature that bears directly on the compilation of price indexes and national accounts. As a result, a chained weighted index is shown to be path independent, if it is interpreted as a change not of prices, but of the unit of account in which prices are expressed.     

The treatment of ‘quality’ in the cost of living index

This paper develops the implications of cost of living index theory for measuring the impact of changes in the availability and prices of goods on a household's welfare. It considers both the ‘goods approach’, which treats each variety as a separate entity, and two characteristics approaches: ‘L-characteristics’ and ‘H-characteristics’. L-characteristics are Lancaster's ‘linear and additive’ specification; H-characteristics are Houthakker's ‘heterogeneous’ specification in which the household consumes only a single variety of each product. The paper concludes by discussing the implications of the theory for actual index number construction and relating it to the literature on ‘quality’ and ‘hedonic indexes’.     

WEIGHTED COUNTRY PRODUCT DUMMY VARIABLE REGRESSIONS AND INDEX NUMBER FORMULAE

The article considers a very simple type of hedonic regression model where the only characteristic of a commodity is the commodity itself. This regression model is known as the country product dummy method for calculating country price parities in the context of making international comparisons. The paper considers only the two country or two period case and introduces value or quantity weights into the regression. The resulting measures of overall price change between the two countries or time periods are compared to traditional bilateral index number formulae. It is shown how the Geary Khamis, Walsh and Törnqvist price indexes can be obtained as special cases of this framework.     

The short-run and long-run benefits of environmental improvement

The social value of a nonmarginal improvement to amentities is not related to hedonic prices in a simple way. Furthermore, hedonic price data do not completely reveal preferences. In order to evaluate short-run benefits of an improvement, the rate of change of the hedonic price function must be normalized by a ratio of population densities. To calculate long-run benefits of the improvement one must calculate the responsiveness of population densities to the nonmarginal improvement. A technique to do so is suggested.     

Hedonic prices and cost/benefit analysis

Hedonic prices have been used to evaluate the willingness to pay for attributes. We reformulate the notion of hedonic price from a composite price on housing to a unit price on traded quantities, in conformity with long run competitive equilibrium theory. This formulation was suggested (but not developed) by Rosen (J. Polit. Econ.82, No. 1 (1974), 34–35). By first characterizing an efficient allocation of consumers to space, we show that hedonic unit prices can be understood as a bid-rent function which supports the efficient allocation. This is despite the fact that the lots over which consumers bid are themselves endogenous. We show that unit hedonic prices reveal preferences in a manner different from composite hedonic expenditures.     

Asset pricing theory and the valuation of Canadian paintings

Abstract.  The valuation of Canadian paintings is analysed empirically. Using a sample of auction prices for major Canadian painters for the period 1968–2001, we run hedonic regressions to analyse the influence of various factors, including painter identity, on auction prices, as well as to construct a market price index. This index is used in a second‐stage analysis in which we analyse the properties of Canadian art viewed as an investment asset. We apply standard asset pricing theory, as incorporated in the capital asset pricing model (CAPM), to the analysis of price movements in the market for Canadian paintings.     

Price convergence in the EMU? Evidence from micro data

The establishment of the European Monetary Union (EMU) was widely expected to cause price convergence among member states. In an investigation of this claim, the present study avoids problems of comparability and representativeness by using an extremely detailed and comprehensive scanner database on washing machine prices and sales volumes for 17 European countries. A hedonic regression yields country-specific time series for quality-adjusted price differentials. Statistically and economically significant deviations from the Law of One Price emerge. Log t tests firmly reject price convergence among EMU countries. Small convergence clusters can be identified but they are unrelated to EMU membership.     

Hedonic price measurement: the CCC approach

An accurate measurement of general price inflation is an essential prerequisite for sound economic analysis and prudent policy-making. Regrettably, numerous hedonic regression studies (predominately focusing on computers) have suggested that due to product quality changes, national statistical agencies are not computing unbiased price-trend estimates. This paper argues that the time-honored hedonic estimation procedure—the adjacent year regression (AYR) method—is generally neither unbiased nor robust. Consequently, the continuously changing coefficient (CCC) approach is introduced. Utilizing various hedonic techniques, several quality-adjusted price-trends for laser printers (1992–2005) were estimated and compared with the one officially released by the statistical agency.     

An Index Approach to Measuring Product Differentiation: A Hedonic Analysis of Airfares

The main objective of this paper is to introduce an Allen-type index of differentiation based on cost functions. With this index, we create an economic measure of product differentiation that quantifies differences between products. Applied research has some generally accepted economic measures, for example, the Herfindahl–Hirschman Index for market concentration, or the Gini coefficient for inequality. Product differentiation, however, does not yet have an established measure. Our objective is to fill that gap and introduce a measure that can be used in market-related applied research such as market power, antitrust, price indexes, or market strategy. To operationalize the index, we introduce the concept of a core product and use cost functions to measure the degree of differentiation from the core product. To demonstrate the use of the index, we study the effect of product differentiation on price formation in the airline industry using an enhanced hedonic model. The model is empirically tested on 103,980 observations of quarterly US domestic airfare data between 2002 and 2016 and shows that product differentiation has a significant effect on both price and mark-up.     

AN EVALUATION OF THE USE OF HEDONIC REGRESSIONS FOR BASIC COMPONENTS OF CONSUMER PRICE INDICES

The importance of adjusting for quality changes in the measurement of consumer prices, and the role hedonic regressions can play in achieving this, is well recognised. However, the use of such regressions can take different forms, including (i) adjustments by statistical offices for non-comparable substitutions via the matched models method , (ii) direct estimates from the coefficients on dummy variables for time, and (iii) exact hedonic and superlative indices corresponding to a constant utility formulation from an economic theoretic approach. The literature on these approaches generally deals with each in isolation; the purpose of this paper is to outline and evaluate them in order to draw conclusions as to their practical suitability for the compilation of quality-adjusted consumer prices indexes. The case is argued for a move towards the last of these approaches, which developments in electronic data retrieval (scanner data) now make feasible. The paper concludes with the results of some empirical work comparing the results of the direct method with those from the exact, superlative, approach.