Abstract: Analysis of variations in house values among localities requires reliable house value indices. Gatzlaff and Haurin (1994) indicate that traditional hedonic house value index estimates, using only information from a sample of sold homes to estimate value movements for the entire housing stock, may be subject to substantial bias. This article extends previous work by adapting the censored sample procedure to the repeat sales index estimation model. Using data from Dade County, Florida, a house value index constructed from a sample of homes selling more than once, rather than all houses in a locality, is found to be biased. The bias is shown to be highly correlated with changes in economic conditions.

Abstract: This paper employs a new national data set to estimate constant quality dwelling prices for four regions of the country. The data set, collected by the National Association of Realtors, provides sale prices, locations, and characteristics of 5,581 dwellings sold during the years 1986-92 inclusive. The paper provides the first national hedonic analysis based upon transaction prices of sample dwellings. The estimated equation implies that more than half of dwelling price increases during the period resulted from quality improvements in dwellings.

Abstract: Conventional housing price index models assume interperiod parameter stability and typically employ either repeat sales or hedonic methodologies. This paper introduces a method of index construction that combines multiple sales observations with single sale transactions while permitting characteristics prices from hedonic regressions to vary over time. A test for interperiod parameter stability is provided. Each period's data are arranged by location and repeat sales are matched by rows. This construction allows greater use of sample information and acknowledges the unique contribution of repeat sales to the estimation process. It also produces intertemporal error correlations that can be beneficially exploited by the seemingly unrelated regressions (SUR) technique. The paper also demonstrates a significance test for error correlation and discusses the treatment of unequal numbers of observations among index periods.

Abstract: This paper examines implicit price differences of rental housing characteristics across various property types to measure whether determinants of rents are valued in the aggregate or separately. The results show that hedonic price functions are not identical across property types which suggests that ordinary least squares is not the appropriate estimation technique when modeling the implicit prices for an aggregate rental market. Generalized least squares estimation of a random coefficient model removes the restriction of fixed parameters imposed by OLS and allows estimation of implicit prices for rental markets containing multiple property types.

Abstract: The paper tests two alternative specifications for the opportunity cost of time in travel cost models. The standard travel cost survey design is enriched to include a contingent valuation type question about peoples' willingness to accept compensation to forgo a precisely defined recreational experience. It is hypothesized that individually revealed value of time more appropriately reflects the opportunity costs of time associated with a particular aspect of recreation than the wage rate which measures the trade-off between work and leisure, generally. The results seem to indicate a better overall fit for the models with the elicited value of individual consumer's time than for the models with the more traditional hourly earnings (wage rates). The importance of the correct measurement of the opportunity cost time is illustrated by showing that estimated consumer surpluses based on two different value of time measurements differ significantly.

Abstract: Efficient allocation of water requires knowledge of water's value in both consumption and nonconsumptive uses. This study estimates the marginal value of water in lake recreational and aesthetic (RA) use. An hedonic price equation (employing the Box-Cox functional form) indicates lake front location, distance to lake, and scenic view are significant RA characteristics of housing Water front properties command a premium price for the private access they offer. Beyond the water front, the marginal RA price falls rapidly with increasing distance, becoming asymptotic to some minimum. Twenty-two percent of housing price is found to be attributable to the RA component.

Abstract: This paper presents a new method for ranking city quality of life. The author uses data from the 1980 and the 1990 Census of Population and Housing to rank cities. His approach relaxes the standard 'hedonic' method's assumptions that all city local public goods are observed and that the implicit prices of all skills and apartment attributes are equal across cities. The author finds that Los Angeles and San Francisco have higher quality of life than Chicago and Houston in both 1980 and 1990. He finds that quality of life in New York City fell during the 1980s.

Abstract: A hedonic migration model is developed where regional amenities are viewed as influencing household production within the framework of the new demand theory. The inputs to household production are goods, time, and housing. It is shown that economic growth in the economy as a whole will increase the relative attractiveness of regions that are relatively time-saving in the sense that they have a lower time elasticity of household production. Hence, migration will flow into time-saving regions and housing costs in those regions will rise as real GDP grows.

Abstract: Historically, water allocation focused on quantities demanded by consumptive uses. As quantity demand grows, efficient allocation among consumptive and nonconsumptive uses becomes more critical. This hedonic approach provides information regarding recreational and aesthetic (RA) value for a central Texas lake. The model indicates several statistically significant RA characteristics of housing; proximity is the most important. Waterfront properties command a premium but marginal RA price falls rapidly with increasing distance. Marginal RA values are estimated for selected water levels and are found to have a lower marginal price per acre-foot than many agricultural uses.

Abstract: The article examines the relationship between dwelling age and the market value of owner-occupied housing. The article theoretically establishes and empirically verifies that (1) housing depreciation is nonlinear and (2) dwelling age-induced heteroskedasticity is prevalent in hedonic house price equations. The empirical results are obtained with a semilog hedonic house price equation from data on nearly 8,500 transactions of single-family homes in Dallas. Hedonic parameters are estimated with four alternative dwelling age specifications and two iterative generalized least squares estimation procedures that accommodate heteroskedasticity by explicitly modeling the residual variance. Estimated depreciation rates are sensitive to both the dwelling age specification and the estimation procedure. The article establishes the importance of incorporating second-order effects in obtaining accurate point estimates for housing depreciation.

Abstract: Parametric estimators, such as OLS, attain high efficiency for well-specified models. Nonparametric estimators greatly reduce specification error but at the cost of efficiency. Semiparametric estimators compromise between these dual goals of efficiency and specification error. Semiparametric estimators can assume general forms within classes of functional forms. This paper applies OLS, the kernel nonparametric regression estimator, and the semiparametric estimator of Powell, Stock, and Stoker (1989) to a data set, which should, based on theory and previous empirical work, yield positive coefficients. The semiparametric estimator, on average, displayed the performance most consistent with prior expectations followed by the nonparameter and parametric estimators. In addition, the paper shows how the semiparametric estimator can provide insights into the form of misspecification and suggest data transformations.

Abstract: The cost of shelter is the single most important component of interarea differences in the cost-of-living. This paper constructs hedonic interarea indexes of the cost of shelter using a major new source of detailed microdata, the CPI Housing Survey. Identification of the exact location of housing units permits us to control for measured neighborhood characteristics, and variance components models are used to model the effects of unmeasured neighborhood characteristics. Hierarchical models with interarea slope coefficient variation are applied and model performance is evaluated by comparing out-of-sample predictions. The hierarchical approach allows us to pool information from different cities to reduce the variability of the areas' coefficients. A multilateral index number formula is employed in the index-number construction.

Abstract: Economists commonly estimate the value of characteristics not traded in explicit markets by hedonic pricing. Unfortunately, these nonexplicitly traded characteristics often display a lack of independent variation or multicollinearity. Often some prior information on the value of these characteristics is available from submarkets. This paper utilizes this type of prior information to circumvent multicollinearity problems in hedonic pricing models using an inequality restricted Bayesian estimator. The authors perform a Monte Carlo experiment and cross-validation analysis to demonstrate the superiority of inequality restricted Bayesian over ordinary least squares at many margins in a variety of situations typically faced in hedonic estimation.

Abstract: Using the marginal value of characteristics, the author shows how to construct bounds on the exact hedonic price index. When prices are above marginal costs, then his bounds still apply but the value of characteristics cannot be measured so easily from a hedonic regression. Since the price-cost markups are an omitted variable, they will bias the coefficients obtained. For a special class of utility functions, the author argues that a linear regression will still provide a measure of the marginal value of characteristics but a log-linear regression will overstate these values.

Abstract: Due to the weak behavioral foundations of aggregate demand models, zonal travel cost models have been largely abandoned in favor of models based on individual observations. However, sample selection difficulties in individual-observation models often require the use of distribution-sensitive limited-dependent variables estimators. In this paper, the author uses Monte Carlo simulations to investigate whether the bias from aggregation is worse than possible bias from these narrowly specified estimators. Somewhat surprisingly, the results indicate that zonal models often outperform the individual-observation models, especially when using an aggregate model that incorporates intrazonal variance of the explanatory variables.

Abstract: This paper reports the results of a statistical summary of estimates of the marginal willingness to pay for reducing particulate matter from hedonic property value models developed between 1967 and 1988. Results from ordinary least squares and minimum absolute deviation estimators consider the effects of market conditions and the implementation procedures for hedonic models. The interquartile range for these estimated marginal values (measured as a change in asset prices) lies between zero and $98.52 (in 1982-84 dollars) for a one-unit reduction in total suspended particulates (in micrograms per cubic meter).

Abstract: A house represents not only a bundle of structural characteristics but also a set of location specific characteristics. Adding locational coordinates and site area to other house characteristics makes it possible to estimate a land rent surface as well as the hedonic prices attached to local patterns of land use and other neighborhood characteristics. One can then estimate how the value of such location-specific characteristics are capitalized into land prices. This analysis, illustrated with estimates based on data from two British towns, has a number of wider implications. It generates a more parsimonious method of estimating amenity values. It also reveals likely systematic biases produced by conventional hedonic studies which exclude land and location. Finally, it clarifies the conceptual definition of land and suggests that monocentric models can person,n well despite recent criticism.

Abstract: Loss estimates in wrongful death and personal injury cases remain a controversial issue among forensic economists. One disputed approach is the so-called "hedonic" loss estimates based on estimates of the value of a "statistical life," which tries to separate the value of life from other losses that an injured party suffers. Given the problems with that approach, analysts interested in estimating losses need alternative methods. This paper discusses the benefits and shortcomings of an alternative, utility theory approach based on first-party valuation of losses, including the lost enjoyment of life, associated with decreased health from personal injury.

Abstract: This paper develops and applies a method for estimating workers' marginal willingness to pay for job attributes when workers' job choices are characterized by imperfect information and labor-market search. As an application, this paper analyzes the job durations of white males using data from the National Longitudinal Survey Youth Cohort and the Dictionary of Occupational Titles. Estimates of workers' willingness to pay derived from the job duration model are compared with those derived from an hedonic wage model.

Abstract: A hedonic price equation of structureless farmland prices in New York State are fitted to 458 land transactions between 1982-1985. No capitalization is found of the state's Agricultural District farmland preservation program, which combines current-use property taxation with several development-inhibiting features. It is hypothesized that landowners avoid joining the program when it would threaten profits from a development sale, and that those who do participate gain little because agriculture is the highest value use of their land.

Abstract: The powerful pattern-recognition properties of Artificial Neural Networks (ANNs) are outlined and shown to discriminate the effect of aircraft noise from other value determinants in a study of residential property values adjacent to Manchester International Airport. The varying effects of noise on different property types and neighbourhoods are identified and examined. The results are contrasted with earlier hedonic regression-based studies, particularly that of Pennington Topham and Ward (1990) which was the source of the data analyzed.

Abstract: A contingent valuation survey was conducted in three cities of the Republic of China (Taiwan) to elicit willingness to pay to avoid a recurrence of the episode of illness most recently experienced by the respondent. A hedonic specification of the willingness to pay function with willingness to pay depending on the attributes of the illness and the respondent's characteristics reveal that willingness to pay for improved health depends on the duration of the illness, the number of symptoms experienced, and income. The elasticity of willingness to pay with respect to each of these variables is, however, quite low. Willingness to pay (WTP) is also affected by the subject's health history and "taste" for health. We use the fitted WTP function to predict willingness to pay of Taiwan households and compare this prediction with benefits transfer extrapolations that multiply WTP for the U.S. by the ratio of Taiwan household income to U.S. household income.

Abstract: Just as a hedonic quantity index holds quality constant for a house or other consumer durable, the concept can be applied to a mortgage. A hedonic mortgage holds quality constant across the characteristics of a loan with a dual hedonic yield. Unlike for houses or consumer durables, the prices in a hedonic mortgage yield are observable directly from derivative securities markets, avoiding the identification problem of distinguishing supply and demand functions. The hedonic mortgage prices the characteristics of the mortgage contract, principally a bond, a default insurance portfolio, and a prepayment insurance portfolio.

Abstract: This study presents an empirical method of modeling the non-negativity of dependent variables using truncated logistic and normal disturbance distributions. The method is applied in estimating a ranch land hedonic price function. Results show that the degree of truncation is significant.

Abstract: In spite of the voluminous literature on property tax capitalization, this paper is the first to derive a discount rate empirically. The paper uses an unique data set from a Mello-Roos community facility district where taxes are expected to be totally capitalized into property values. Using a standard hedonic pricing model, the results show that buyers of homes within the community facility district capitalize taxes into the prices of purchased properties at a discount rate of around four percent.

Abstract: This hedonic price study of the effect of airport noise on property prices uncovers relationships with the number of events that affect a location, and the mean and variance of the loudness of the events. The results suggest that hedonic price models that include cumulative energy noise measures, such as the Noise Exposure Forecast, do not perform as well as models that use the number and loudness of aircraft noise incidents. Furthermore, Box-Cox estimates of the empirical price function reject the usual specifications found in previous literature.

Abstract: This paper investigates whether reliable house price indices can be constructed using a limited set of descriptive variables on a large number of observations. Four primary index methods are compared: (1) median sale price, (2) restricted hedonic, (3) repeated sales, and (4) the assessed-value technique. The paper examines the precision and accuracy of each of the alternative indices.

Abstract: Farmers may value water quality and user safety characteristics of herbicides as they select among products to obtain weed control. Expenditures per application in the U.S. corn and soybean herbicide markets are explained by several safety characteristics in addition to market and weed control characteristics. The explicit inclusion of safety characteristics in the farm decision model indicates that not all safety aspects of pesticides use are external to farmers. Leaching potential and user toxicity are statistically significant but their elasticities are small relative to broadleaf and grass weed control efficacy.

Abstract: This paper compares, via simulation, the performance of the multinomial logit and hedonic models in estimating consumer preferences for product attributes. The authors ascribe preferences over the attributes of houses to a population of consumers and, by having them bid for a set of houses, calculate equilibrium prices. The resulting data are used to estimate the two models. Coauthors are Leland Deck, Nalin Kishor, and Kenneth E. McConnell.

Abstract: Using Monte Carlo simulations, this paper evaluates the predictive performance of ordinary least-squares estimation, ridge regression, two empirical Bayes formulations of Stein-like rules that are based on different nonsample information, and a pretest estimator. The context of the experiment is a standard hedonic model for housing values using American Housing Survey data for six geographically diverse metropolitan statistical areas. The simulations reveal that the Stein-like rules empirically dominate least squares under each of three estimation and prediction loss criteria.

Abstract: Implicit housing price models demonstrate that newer housing units command a premium over similar, older units. Unit condition has long been considered the source of these rent and value differentials. Evidence presented in this article suggests that consumers in many markets may have a pure taste for newer housing. If so, households pay a premium for newness, just as they pay extra for a larger lot, more floor space, and a safer neighborhood. Given two otherwise identical units, the older is less expensive to rent or purchase. Thus, older units most affordably provide a fixed package of housing amenities (a certain floor and lot size, etc.). In particular, policymakers searching for a low-cost method of providing basic housing amenities can turn to older housing. In light of the nation's current housing problems, the discounted price for older units commands attention as a policy instrument.

Abstract: In this paper we present a generalized functional form estimator, recently developed by Jeffrey Wooldridge; and then we compare it empirically to the popular Box-Cox (BC) estimator using three data sets. We begin by briefly reviewing the drawbacks of the BC estimator. We then introduce the nonlinear least squares (NLS) alternative of Wooldridge which retains the desirable qualities of the BC estimator without the associated theoretical problems. We continue by applying both the BC and the NLS models to data from three classic hedonic regression studies and then compare the estimation results--point estimates, inferences, and fitted values. The estimations include a wage rate equation, and two computer hedonic regression equations, one using data from a classic study by Gregory Chow and the other using an IBM data set, that formed the basis of the new official BLS computer price index.

Abstract: Some econometric issues associated with the characteristics approach to simplify complex market structures where many differentiated products interact to a smaller number of homogeneous attributes are considered. These include the choice of functional form for the hedonic price equation, the data requirement for the identification of market demand and supply of characteristic s, and the practical method for selecting characteristics to represent differentiated products. The implicit market for U.S. automobile dem and is analyzed to illustrate the authors' approach.

Abstract: This paper uses the three markets (peak, pre, and post season) for weekly rentals of vacation properties along The Outer Banks of North Carolina and the hedonic model to test whether coastal amenities influence the marginal rate of substitution for short term displacement on the timing of recreation trips to the beach. Proximity to the ocean was found to be a significant determinant of temporal substitution between the peak and pre peak seasons with ocean front properties having 1.9 to 4.7 percent smaller discounts for pre season rentals relative to other properties.

Abstract: Unrestricted nonlinear models typically outperform their simple linear counterparts in the hedonic pricing and mass assessment fields. Economic theory, however, suggests prior information that most naturally applies to the simple linear model. This article examines the consequences of translating this prior information across specifications. The results show that the addition of the prior information improved the ex-sample prediction accuracy over all sample sizes examined. The prior information effectively augments the sample size, thus extending the domain of these models.

Abstract: This study examines the effects of different combinations and qualities of selected site characteristics on the value of agricultural land in six substate regions in the state of Washington. The analysis follows the general hedonic regression form but incorporates nonnegativity constraints on the models. This, coupled with an adaptation of H. Bierens's (1990) conditional moment test, yields consistent results showing (1) land value is a function of site characteristics, (2) land markets in the state of Washington are highly regional, (3) parsimonious empirical models can provide adequate representations of expected land values, and (4) nonnegative truncation is a valuable procedure in hedonic models.

Abstract: Current real estate statistical valuation involves the estimation of parameters within a posited specification. Such parametric estimation requires judgment concerning model (1) variables; and (2) functional form. In contrast, nonparametric regression estimation requires attention to (1) but permits greatly reduced attention to (2). Parametric estimators functionally model the parameters and variables affecting E(y|x) while nonparametric estimators directly model pdf(y,x) and hence E(y|x). This article applies the kernel nonparametric regression estimator to two different data sets and specifications. The article shows the nonparametric estimator outperforms the standard parametric estimator (OLS) across variable transformations and across data subsets differing in quality. In addition, the article reviews properties of nonparametric estimators, presents the history of nonparametric estimators in real estate, and discusses a representation of the kernel estimator as a nonparametric grid method.

Abstract: Unrestricted nonlinear models typically outperform their simple linear counterparts in the hedonic pricing and mass assessment fields. Economic theory, however, suggests prior information that most naturally applies to the simple linear model. This article examines the consequences of translating this prior information across specifications. The results show that the addition of the prior information improved the ex-sample prediction accuracy over all sample sizes examined. The prior information effectively augments the sample size, thus extending the domain of these models.

Abstract: Although communities worldwide have shown an increasing concern for the environment, hedonic regression shows little change over time in the relationship of airport noise to the property values of detached dwellings. The effects of noise on the value of multiple-unit residential condominiums and on the value of vacant land are found to be higher than for detached houses and are statistically significant.

Abstract: Alternative traditional and spatial autoregressive hedonic urban housing price models are offered corresponding to different conceptualizations of the housing price determination process. Some methodological issues relevant to their estimation are addressed that draw upon recent development from spatial econometrics. These include the selection of the appropriate estimation strategy; the application of diagnostic tests for the detection of spatial dependence and heterogeneity; and the use of robust methods in the presence of heteroskedasticity.

Abstract: Observations drawn from multiple markets are essential to the construction of indices of housing costs and to measures of demand for housing attributes. It is not evident when multiple markets exist or whether such markets exist for some attributes but not for others. They test for multiple markets by using Bayesian methods to assess the transferability (random exchangeability) of entire hedonic price expressions from one site and time to another, the transferability of hedonic price functions are particular attributes, and the degrees of similarity and hedonic price functions must have in order to be transferable. In the authors' illustrations, price functions for structural housing attributes are generally transferable, prices for neighborhood attributes are not. Therefore, in their illustrations, the desired price indices and demand functions should be estimable for neighborhood attributes, but not for structural ones.

Abstract: The application of the hedonic pricing technique to estimating consumer values of avoiding or incurring the risk of loss from natural hazards has recently appeared in the literature. The probabilistic nature of the hazards evaluated in these studies raise new questions regarding the interpretation of the hedonic prices estimated. The authors present a hedonic price model that accounts for information level and uncertainty when valuing nonmarket goods. A simple set of rules are derived for analyzing hedonic prices for probabilistic nonmarket goods.

Abstract: This paper uses a semiparametric empirical technique (maximum score) to estimate the determinants of the decision of low-income renters to move out of their dwelling. The maximum score estimates prove to be far more precise than probit estimates. The estimates are used to show that low-income residents highly value remaining in their dwelling. In addition, these estimates are used to illustrate an alterative method to measure willingness to pay for neighborhood amenities, which the authors argue to be superior to hedonic-based willingness-to-pay measures.

Abstract: Although it is intuitively obvious that neighborhood quality and accessibility should affect housing prices, the empirical evidence is weak: Most hedonic estimations show few significant coefficients on the neighborhood and accessibility variables. The lack of empirical support for the capitalization of neighborhood and accessibility effects may stem from the multicentric nature of the city as well as measurement problems with regard to neighborhood quality. In this paper, an alternative approach is taken: Omit all neighborhood and accessibility measures from the set of explanatory variables and instead model the resulting autocorrelation in the error term. Data from Baltimore are used in an empirical example; the results show that this approach provides a very plausible pattern of housing price variation.

Abstract: This study is the first to lend empirical support to the common belief that traffic intensity affects property values. Using a standard hedonic pricing model, this paper investigates the price effects on housing of traffic within a neighborhood. Results using data on single-family housing transactions for two different locations in a medium-sized city show a substantial negative price effect of traffic externalities. The magnitude of the effect is shown to be location specific.

Abstract: The valuation of water quality has proved difficult for economists using hedonic methods. This study, by employing a sample of lakes and considering only land values, is able to overcome many methodological and empirical problems inherent in previous studies. One objective measure of water quality, secchi disc reading, is found to be significant for various alternative specifications of the hedonic model. As explained, however, the results suggest that economic value may be attached to a perceived, rather than actual, measure of water quality. This raises fundamental questions as to how economists and natural scientists can work together to formulate public policy regarding water quality.

Abstract: The conventional model of the housing market does not take into account the search process for a suitable housing unit. Based on a dynamic search theory, this paper develops and estimates a truncated regression model of the rental housing market with stochastic and unobserved truncation points. The author's model provides a joint estimation of the hedonic rice and the reservation rent equations. The results turn out to be superior to the ordinary least squares estimates of either the traditional housing demand function or the hedonic price equation.

Abstract: This paper reconsiders whether implicit discount rates, generally cited as a market barrier to conservation, are really too high, and demonstrates that probabilistic choice studies of consumer durable purchases and hedonic housing price regression studies measure similar but non identical discount factors. Four hedonic regression studies are reviewed which attempt to ascertain whether and to what extent the housing market capitalizes energy conservation investments. A theoretical model is presented which links the probabilistic choice and hedonic regression methods and shows how using results from both studies allows measurement of individual discount rates without bias. The paper identifies several factors which cause the degree of capitalization to differ from unity, resulting in consumer decisions which are rational from the individual perspective, but which can lead to low levels of social conservation.

Abstract: Houses are routinely sold at prices below, but rarely sold at prices above, their list price. List prices appear to be price ceilings that preclude the possibility of sales at higher prices. This paper presents a theory of sellers' behavior that explains why there are list prices in housing markets and why list prices are distinct from sellers' reservation prices. The theory forms the basis of an econometric model that has been estimated using data from the Baltimore, Maryland, area. The estimated model predicts sale and reservation prices conditional on list prices. The predictions of sale prices are considerably more accurate than those obtained from a standard hedonic price regression. The estimated model also explains why sellers may not be willing to reduce their list prices even after their houses have remained unsold for long periods of time.

Abstract: This paper is the first to apply the theory of deterministic chaos to a microeconomic problem. Previous applications of chaos theory to time-series data, while successful in uncovering nonlinearities, have not provided guidelines for resolving uncovered misspecification problems. In contrast, the authors show that a modified test statistic from chaos theory is an extremely valuable tool in microeconomic model specification because it shows when excluded information is correlated with included information. This test, applied to hedonic estimation of marginal housing prices, is able to distinguish among alternative regression specifications and assists in discovering a parsimonious specification devoid of nonlinear effects.

Abstract: Hedonic measurement of housing quality is normally based on a wide range of data including information on structural, neighborhood, and geographic attributes of the housing stock. Readily accessible tax assessment database across many U.S. communities typically contain limited data, on housing structural attributes. It is always very expensive to augment such variables with additional data on housing neighborhood and location. Consequently, hedonic estimation of quality based on these limited data perennially suffers specification bias. Because few hedonic variables are capable of proxying the statistical influence of omitted ones, there is really no need for more expensive data that some analysts insist are necessary for proper use of hedonic index to make housing quality judgments. This makes tax records a valuable source of information for hedonic estimation.

Abstract: Constructs a measure of well being that combines physical quality of life and economic liberty indexes for 122 countries for 1980. Constructs some aggregate indexes of the quality of life, demonstrating how relative rankings of well being will vary depending on the aggregation method and the weights. Analyzes twenty indicators of quality of life to capture a multidimensional view of the physical quality of life. Uses kernel density estimates and cluster analysis to examine the distribution of the individual quality of life indicators across countries and to determine which are most similar in their cross country distributions. Constructs a number of summary indexes of economic liberty based on principal component and hedonic weighting techniques. Combines the quality of life indexes with the economic liberty indexes in an overall measure of well being. Coauthors are Gerald W. Scully, Joseph G. Hirschberg, and Kathy J. Hayes. Slottje is Professor of Economics at Southern Methodist University. No index.

Abstract: In this paper we examine the problem of consistently estimating capitalization rates and hedonic housing prices. We specify a hedonic pricing model for housing that combines owner-occupied and rental unit samples in a manner yielding hedonic prices not subject of selections bias and capitalization rates which vary with the age and family income of the residents. We use the 1982 Annual Housing Survey (AHS) for metropolitan Philadelphia to obtain parameter estimates for this model. Our findings indicate that selectivity bias is present in price functions utilizing only owner-occupied or rental unit samples. Our results further indicate that the mean annual capitalization rate for owner-occupied units is approximately 10 percent. However, the capitalization rate is non-monotonically related to both age of the head and family income. 0

Abstract: Coastal land-use controls that limit new residential development on land adjacent to water have three principle efficiency effects: gain in aesthetics and clean water, loss of residential proximity to the coast, and loss of amenities at inland locations. Using hedonic price analysis of housing with data from a county on the Chesapeake Bay where controls were introduced, the authors estimate the opportunity cost of the second efficiency effect--displaced residential development. They predict the number of houses displaced due to controls and multiply that by the implicit value of coastal access amenities from the hedonic to estimate the loss.

Abstract: Specification testing can be an effective method for addressing the considerable econometric problems present in hedonic models. In this article, the authors suggest the use of three different Hausman-type specification tests--tests for the hedonic price equation, each preference equation, and a system of equations--as a way of isolating the sources of misspecification in a hedonic model. Using a national data sample as an example, they illustrate the use of these tests to guide model specification in a simultaneous setting.

Abstract: Theoretical models for estimating individuals' values for sure improvements in environmental quality are well developed. These models can be classified as being based on averting behavior, hedonic prices, or weak complementarity. Some of these models have also been applied to the task of valuing changes in risk based on expected utility theory. This article provides a systematic development of these models for changes in either the probability or the magnitude of an uncertain event and shows that the derived expressions for individual preferences is continuous, convex, and twice differentiable.

Abstract: Nine papers, originating at an open workshop held in Chicago in November 1988, examine the theory and practice of measuring consumer demand for environmental quality. Contributions focus on environmental demand theory; household production functions and environmental benefit estimation; hedonic methods; constructed markets; environmental health effects; the aesthetic benefits of environmental improvement; recreation; the application of welfare evaluation techniques to materials damages; and conceptualizing total economic value and its nonuse components. Braden and Kolstad are at the University of Illinois. Bibliography; author and subject indexes.

Abstract: When the value of access to a natural resource is measured by different methods, double counting sometimes occurs. This paper shows that, when travel cost models and hedonic models are used to measure the value of access, the hedonic estimate includes the travel cost estimate. This result extends to damages from pollution. Both travel cost models and hedonic models can be exploited to measure the damages from pollution in a natural resource, but the hedonic model provides a broader measure that incorporates the travel cost estimate.

Abstract: This paper reviews the conceptual basis for valuing environmental amenities and discusses travel cost recreation demand and hedonic property value models as strategies that rely on observed choice to measure use values for environmental resources. The growing importance of measuring nonuse values is noted because people experience satisfaction from environmental resources without actually using them. Nonuse values do not require a choice, so measuring them requires analyzing other behavioral indicators: conversation and the adaptations people make as they learn. Recent advances are described in using surveys as conversational sources of information about people's values within a contingent valuation framework.

Abstract: The J test (a non-nested test) is used to determine which set of neighborhood variable best explains the variation in housing prices. The results indicate that characteristics of neighbors (race and socio-economic descriptors) are more important than the quality of public services.

Abstract: Econometric analysis often addresses model misspecification due to the improper pooling of observations. One major problem in testing for improper pooling is the requirement that alternative stratifications be obtained from others through sets of restrictions (i.e., that they be nested stratifications), thus eliminating a large class of alternative non-nested stratifications. We propose that non-nested tests can be used to compare non-nested stratifications. We formally define the econometric problem, and show the applicability of the J, JA, Cox and non-nested F tests. We then use the four tests to compare spatial stratifications in a model of a house price determination.

Abstract: This chapter gives an overview of the techniques used to value the non market benefits of water related public goods and of the major empirical studies in this area. Travel cost, hedonic pricing, and contingent valuation are described, special emphasis is placed on the problems and limitations of implementing these methods to value changes in the quality and quantity of water-related amenities. Major empirical efforts to value national and regional water quality improvements, water-based recreation, ecosystem preservation, instream flows, groundwater protection and water supply reliability are discussed.

Abstract: A model of neighborhood turnover drawn from Bond and Coulson (1989) is proposed. The type of turnover process that is obtained is shown to depend mainly on the hedonic bid functions for housing and neighborhood quality. A demand system of four hedonic attributes is estimated. The main results are that the traditional model of filtering by age of unit does not occur and that filtering by housing size does. Tipping due to changes in median neighborhood income is also quite possible. Tipping through changes in racial composition appears less likely.

Abstract: This paper considers the effect of floodplain management programs on the market for vacant residential land. The authors model the land developers' profit from housing production to illustrate the expected effects of parcel characteristics on land value. The hedonic method is utilized to analyze data on vacant floodplain land parcels from nine communities that vary by type of flooding, regulatory programs, and geographic location. The authors' results show that zoning floodplains for lower density development, implementing building regulations requiring elevation above the level of the flood, and providing clear local leadership of programs each contribute to lowering floodplain land values.

Abstract: The value of a parcel of land as a factor of production is a result of the characteristics the land embodies. This paper develops a model of land markets that considers these characteristics and is based on the behavior of the demanders and suppliers of the services of land. This model provides a basis for estimates of hedonic equations for land and the demands for the characteristics of land. The techniques necessary to use hedonic estimates to measure willingness-to-pay for improvements in land are shown to depend on the nature of the improvement.

Abstract: Explicit estimates of compensating or equivalent variation have replaced measures of consumer surplus in many applied settings. This paper compares two widely used methods of making such estimates: so called "hedonic price" or implicit markets approaches and discrete choice methods based upon stochastic utility functions. Both techniques are applied to identical data sets in an extensive monte carlo simulation. The results are compared in terms of their accuracy in estimating consumer "willingness to pay" for marginal and nonmarginal changes in consumption.

Abstract: This study examines how errors in measuring marginal attribute pric es vary with the form of the hedonic price function. In simulations, consumers with known utility functions bid for houses with given attributes. Various forms of the hedonic function are estimated using equilibrium housing prices. Errors in estimating marginal attribute prices are calculated by comparing each consumer's equilibrium marginal bid vector with the gradient of the hedonic function. When all attributes are observed, linear and quadratic Box-Cox forms produce lowest mean percentage errors; however, when some attributes are unobserved or are replaced by proxies, linear and linear Box-Cox functions perform best.

Abstract: Implicit markets capture compensation for intraurban and interregional differe nces in amenities and yield differences in housing prices and wages. These pecuniary differences become preference-based weights in a qual ity-of-life index. Hedonic equations are estimated using microdata fr om the 1980 Census and assembled county-based amenity data on climati c, environmental, and urban conditions. Ranking of 253 urban counties reveals substantial variation within, as well as among, the 185 urba n areas. The quality-of-life differences across counties within one S MSA is almost one-half of the difference between the top- and bottom- ranked counties in the nation.

Abstract: This article develops ex ante measures of the benefits of large amenity improvements. A commonly-used bene fit measure, the willingness to pay of housing consumers for the amenity improvement at their original location, is shown to underestimate benefits because it overlooks adjustments by housing consumers and landlords. The article also derives an upper bound to benefits: the pr operty value increases predicted by an original hedonic function. The article argues that this upper bound will often be the best feasible approximation to the true efficiency benefits of amenity improvements.

Abstract: S. Scotchmer has shown that, even if the population is homogeneous, hedonic prices do not correctly measure long-run benefit s of a large public project. This paper examines the direction of err ors and shows that the use of cross-sectional land rent differentials leads to overestimation of the benefits. The short-run benefits with fixed lot size are also considered.

Abstract: In this paper, the characteristics model of Kelvin Lancaster is reconsidered. It is shown by example that equili brium prices need not be linearly decomposable. It does follow that e quilibrium prices must be a convex function of characteristics, howev er. Further, it is shown that this fact holds independent of the form of firm competition (e.g., perfect or monopolistic). Finally, the pr edictions of the theory are discussed in the context of two empirical examples.

Abstract: In any hedonic system in which consumers purchase a characteristic embodied in a good, consumers with strong tastes for the characteristic are matched with producers with low costs of producing it. This paper demonstrates that, as a result of this matching process, the "exogenous" variables in the supply e quation cannot be used as instruments in the demand equation and vice versa. The authors show that despite the absence of the usual instru ments, the system is identified under reasonable orthogonality assump tions. They develop an efficient estimator for the identified system and suggest some specification tests.

Abstract: The marketing of unique durable goods such as housing presents a good example for the application of search theory. An optimal stopping rule strategy is employed to model sellers' behavior. The primary hypothesis is that the greater the atypicality of a house, the greater the expected variance of offers. Because a maximizing seller will wish to entertain more offers the greater is the variance, the marketing time of atypical houses will be relatively longer than that of standard houses. Using a sample of resale houses, the empirical study uses a failure time model to confirm the hypothesis. Extensions are mentioned, including discussions of the role of the list price and the limitations of the standard hedonic regression approach when applied to housing.

Abstract: This paper addresses the econometric issues of variable selection, measurement error, functional form, and error distribution in the context of estimating hedonic prices for urban ai r quality. The empirical magnitudes of the hedonic prices vary substa ntially, depending on how each issue is addressed. It is recommended that future empirical work investigate the sensitivity of hedonic pri ce estimates to these issues and concentrate on building more detaile d and accurate data sets. Coauthors are James C. Murdoch, Mark A. Tha yer, and Don Waldman.

Abstract: Spatial autocorrelation occurs when population members are related through their geographic location. This paper presents a maximum likelihood procedure for simultaneously estimating the parameters of the correlation function and the regression coefficients. A test for the presence of spatial autocorrelation is also provided. Estimation of an hedonic regression illustrates the technique.

Abstract: Much of the current literature on water rights is concerned with the efficiency of water allocations where there are legal and institutional constraints on water rights trades. This paper develops a quantitative basis for assessing the efficiency of a water rights market and applies the procedure to 1970 data collected from Weld County, Colorado. The first step is to estimate a hedonic price function for farm parcels in which the parcel price depends on quantities of land, water, and other attributes. Conclusions may then be drawn about the efficiency of a regional water rights market from the functional form of the estimated equation.

Abstract: Concern over the theoretical framework underlying the hedonic travel cost (HTC) model's implicit prices (as well as the process of estimating these prices) and the definitions of the quanti ties of site characteristics "consumed" by recreationists motivated this analysis. This evaluation of the HTC model considers the implic ation of the definitions of price and quantity measures for both the estimated demands for the characteristics of recreation sites and for the benefit measures based on them. The authors' results contrast wi th all the published applications of the HTC model. They indicate tha t application of the model should not be regarded as a routine implem entation of a hedonic price function.

Abstract: Accurate measurement of the effect of growth control on house prices requires that the research design cont rol for factors other than the growth control program that could affect house pr ices. This paper draws on a hedonic view of housing markets to examine and compa re the merits of several forms of quasiexperimental and statistical controls. Th e methodological critique is tested empirically, using data from Davis, Californ ia (a growth control city) and three comparison cities. The resulting estimates of the growth control effect vary widely among the methods, and in particular, b etween a theoretically inferior method that is widely used and the preferred met hod. It is concluded that preferred methods are able to reduce important sources of bias.

Abstract: Beginning with an axiom of separability in willingness to pay for space and amenities, we develop a general technique to evaluate the benefits of nonmarginal improvements to amenities in the short run and the long run. If cross section observations are made on both hedonic prices p(a) and lot sizes s(a, y) (where y is the resident's income), there is sufficient information in hedonic price data to reveal preferences. This is because the hedonic price function p(a) has two marginal properties. dp(a)/da = m sub a`a, s(a, y),u/s(a, y) where m sub a is the marginal rate of substitution between money and a particular attribute. In addition, p(a)=-m sub s`a, s(a, y);u, where -m sub s is the marginal rate of substitution between money and lot-size on type-a land.

Abstract: A common objective in econometric analyses of hedonic markets is to obtain estimates of parameters describing consumer preferences for one or more of the attributes which constitute the traded good. However, because the marginal price of each attribute is never observed and because both the attribute levels and their marginal prices are choice variables (since the budget set is nonlinear), a satisfactory technique to obtain this objective has remained elusive. In this paper, a new two-step procedure is proposed to estimate these preference parameters. In the first step, non-parametric kernel regression is used to estimate the marginal prices for observed attributes; in the second, nonlinear two-stage least squares is used to estimate the preference parameters. The resultant estimator is shown to be consistent and asymptotically normal (converging at the rate root-n) with an estimable covariance matrix.

Abstract: Hedonic prices are prices of land which depend on amenities: p:A >R, where A is a set of attribute vectors. We show that if cross section observations are made on both land prices p(a) and lot sizes s(a,y) (where y is the resident's income), there is sufficient information in hedonic price data completely to reveal preferences. This is because the hedonic price function p(a) has two marginal properties. We show that dp(a)/da = ma`a,s(a,y),u/s(a,y) where ma is the marginal rate of substitution between money and a particular attribute. In addition, p(a)=-ms`a,s(a,y);u, where -ms is the marginal rate of substitution between money and lot-size on type-a land. We can identify indifference curves by integrating these two differential equations.

Abstract: The widespread presence of hazardous waste disposal sites is widely recognized as one of the most pressing environmental problems of this decade. Hundreds of such sites have been identified throughout the United States, and billions of dollars have been budgeted for cleanup. Yet virtually no studies have investigated the quantitative benefits resulting from cleanup. There are several methodological options for calculating these benefits. This paper estimates the benefits of cleaning up hazardous waste sites using a methodology based on housing price differences. Specifically, we employ statistical techniques to determine households' implicit willingness to pay to locate further from hazardous waste sites. The empirical results are based on housing transactions for single family detached residences in the Boston metropolitan area. The benefits of cleaning up a site depend on the population density near the site, the prices of the homes near the site, and the characteristics of the site itself. To illustrate the application of our statistical results, we estimate the willingness to pay for the cleanup of three sites in the Boston area; in 1980 dollars, these benefit estimates range from $3.6 million to $17.4 million.