Repeat Sales as a Matching Estimator

The most common approaches for constructing house price indices—hedonic price functions and the repeat sales estimator—focus on changes over time in mean prices. Though the hedonic approach is less wasteful of data than the repeat sales estimator, it relies on an accurate specification of the underlying econometric model. I suggest using a matching estimator as an alternative to the hedonic and repeat sales approaches. Like the repeat sales approach, a matching estimator uses pairs of sales from different dates to estimate the mean difference in sales prices over time. The matching approach preserves much larger sample sizes than the repeat sales estimator while requiring less preimposed structure than the hedonic approach. The matching approach makes it easy to characterize changes in the full distribution of house prices.     

Do House Price Levels Anticipate Subsequent Price Changes within Metropolitan Areas?

This research examines the relationship between hedonically controlled housing price levels and subsequent changes in those prices across locations within MSAs. Are areas with a high price relative to an “imputed rent” paying for higher appreciation? In an efficient market (e.g., Gordon Growth Model), as fundamentals (impute rent) differ across locations and change over time, anticipation of these should generate a positive correlation between (residual) price levels and subsequent price changes. We undertake these tests in four different MSAs using a panel of repeat‐sale house price indices that have been scaled to price levels with the hedonic attributes of the house and ZIP code. In three markets we find that identical houses in higher priced ZIP codes subsequently appreciate faster. In one market we find that there is little statistical difference.     

Hedonic Amenity Valuation and Housing Renovations

Hedonic and repeat sales estimators are commonly used to value such important urban amenities as schools, environmental quality and access to transit. Given that property data often omits information on quality differences between same‐aged homes as well as changes in structural attributes over time, researchers must assume that property renovations are uncorrelated with neighborhood amenities. We formally test if this assumption is valid by incorporating detailed data on renovations in Charlotte, North Carolina. We begin by testing how the inclusion of minor and major home improvements influences hedonic and repeat sales indices. Results find limited bias in hedonic indices and that renovated properties are no more likely to be sold than nonrenovated properties. Using the introduction of Charlotte's light rail‐transit system in 2000, we estimate a positive bias of between 1.6% and 19.9% on the capitalized benefits of access to light rail due to omitted information on renovations. Our results show that a number of common data cleaning techniques used to address missing information on structural improvements may worsen this bias.     

GMM Repeat Sales Price Indices

Illiquid assets are widely spread within the economy but their indices are difficult to measure. This paper proposes a Generalized Method of Moment (GMM) repeat sales regression for estimating illiquid asset price indices. This method has estimators that are arithmetic averages of individual asset returns. This method is able to estimate custom-weighted indices, including equal- and value-weighted indices. It can incorporate hedonic variables to improve estimation accuracy, and it can work with a reweighting technique to mitigate a biased sample problem. Simulations based on artificial markets indicate that the method is more accurate than some alternatives in both efficient and sluggish markets, with and without temporal aggregation. As an application, we use this method to estimate a commercial property price index.     

New Evidence on Home Prices from Freddie Mac Repeat Sales

The weighted repeat sales price index methodology recently reported in Case and Shiller [5] [6] is applied to a dataset of over eight million loans bought by the Federal Home Loan Mortgage Corporation over the last twenty years. Regional price indices are reported and compared to indices from other sources. Statistical issues in the creation of the index, both technical and due to sample selectivity of the Freddie Mac dataset, are extensively discussed. It is found that the new index grows at a rate similar to other indices up until 1985, after which time it grows at a significantly higher rate.     

On Choosing Among House Price Index Methodologies

This paper compares housing price indices estimated using three models with several sets of property transaction data. The commonly used hedonic price model suffers from potential specification bias and inefficiency, while the weighted repeat-sales model presents potentially more serious bias and inefficiency problems. A hybrid model combining hedonic and repeat-sales equations avoids most of these sources of bias and inefficiency. This paper evaluates the performance of each type of model using a particularly rich local housing market database. The results, though ambiguous, appear to confirm the problems with the repeat sales model but suggest that systematic differences between repeat-transacting and single-transacting properties lead to bias in the hedonic and hybrid models as well.     

A Varying Parameters Approach to Constructing House Price Indexes

Conventional housing price index models assume interperiodparameter 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 (SUH) technique. The paper also demonstrates a significance test for error correlation and discusses the treatment of unequal numbers of observations among index periods.     

Measuring and Explaining Changes in REIT Liquidity: Moving Beyond the Bid–Ask Spread

This paper investigates changes in REIT liquidity since the REIT boom of 1993. We use trade-by-trade data for REITs traded on the major U.S. exchanges to estimate and compare Kyle's (1985) measure of inverse liquidity for the 1993 and 1996 time periods. For our full sample of equity REITs, there is a significant increase in REIT liquidity in terms of the median price impact of trades. The increasing importance of the self-advised, self-managed organizational structure is found to be a major factor driving increased REIT liquidity. Our results imply a decline in the asymmetric information faced by market-makers. Our investigation of the changes in the size distribution and resulting price impacts of REIT trades over the 1993–1996 period yields evidence of increased importance of informed traders to REIT price dynamics. Our findings of increased liquidity indicate that the increase in adverse-selection costs due to the presence of more informed traders is more than offset by the increase in market thickness as a result of an increase in the number of uninformed (liquidity) traders.     

A Semiparametric Method for Estimating Local House Price Indices

Spatial autoregressive hedonic models utilize house prices lagged in space and time to produce local house price indices, for example, the spatial and temporal autoregressive (STAR) model might be used this way. This paper complements these models with a semiparametric approach, the Local Regression Model (LRM). The greater flexibility of the LRM may allow it to identify space–time asymmetries missed by other models. The LRM is fitted to 49,511 sales from 1972Q1 to 1991Q2 in Fairfax County, Virginia. The local price indices display plausible and significant variations over space and time. The LRM price indices in selected neighborhoods are shown to differ significantly from those in some other neighborhoods. A new method for estimating standard errors addresses an overlooked problem common to all local price indices: how to evaluate the amount of noise in the estimates. Out-of-sample prediction errors demonstrate that LRM adds significant information to the hedonic model.     

Is Selection Bias Inherent in Housing Transactions? An Equilibrium Approach

We develop an equilibrium model for residential housing transactions in an economy with houses that differ in their quality and households that differ in their planned holding horizon. We show that, in equilibrium, a clientele effect persists, with long‐horizon buyers overwhelmingly choosing higher quality properties and short‐horizon buyers settling for lower quality properties. This clientele effect creates a sample selection bias: the properties that are on the market are predominantly of lower quality. Since these are the preferred choice of short‐horizon buyers, they demonstrate a faster turnover. Both the clientele effect and the selection bias are more pronounced with an increase in the variance of house quality and in the variance of the planned holding horizon. Our theoretical model supports empirical evidence on the existence of such bias in home price indices and explains it by the differences in ex ante holding horizons.     

Dwelling Age Heteroskedasticity in Repeat Sales House Price Equations

Several authors have attributed the heteroskedasticity observed in repeat sales house price equations to the length of time between sales. Recently, Goodman and Thibodeau (1995) developed a theoretical model that relates heteroskedasticity in hedonic house price equations to dwelling age. Using data for nearly 2,000 repeat sales in Dallas, Texas, this research examines whether repeat sales heteroskedasticity is related to dwelling age, to the length of time between sales, or to both. An iterative generalized least squares procedure that explicitly models the residual variance is used to obtain robust parameter estimates and to increase the efficiency of the usual repeat sales price indices.     

Forecasting Prices and Excess Returns in the Housing Market

The paper uses quarterly indexes of existing single-family home prices estimated with microdata on properties that sold more than once to estimate excess returns to investment in owner-occupied housing. Housing prices and excess returns are estimated over the period 1970:1 to 1986:3 for Atlanta, Chicago, Dallas, San Francisco. Using time-series cross-section regressions we test for the forecastability of prices and excess returns using a number of independent variables. Price changes in one year tend to continue for more than one year in the same direction. The ratio of construction costs to price, changes in adult population and increases in real per capita income all are positively related to excess returns or price changes over the subsequent year. The results add weight to the argument that the market for single-family homes is inefficient.     

Experimental Evidence on Product Adoption in the Presence of Network Externalities

The benefits accruing to a purchaser of a product due to the existing base of consumers of the same or compatible products are known as network externalities. This paper studies Katz and Shapiro's (1986) model of network externalities in an experimental setting. Two sellers choose prices for competing technologies sold to two groups of four buyers purchasing sequentially in two stages. The results are qualitatively consistent with Katz and Shapiro's equilibrium predictions. In certain sessions over three-quarters of first stage buyers purchase the more expensive technology anticipating that later arriving buyers will also buy this technology. In periods where a strong network has been established for a technology in the first stage, over 80 percent of second stage buyers buy that technology, even though in most cases it is priced higher. The data, however, differ from the point predictions of the model.     

An Empirical Examination of Traditional Neighborhood Development

This study analyzes the impact of the new urbanism on single-family home prices. Specifically, we explore the price differential that homebuyers pay for houses in new urbanist developments relative to houses in conventional suburban developments. Using data on over 5,000 single-family home sales from 1994 to 1997 in three different neighborhoods, hedonic regression results reveal that consumers pay more for homes in new urbanist communities than those in conventional suburban developments. Further analyses indicate that the price premium is not attributable to differences in improvement age and other housing characteristics.     

A Methodology for Constructing Vacant Land Price Indices

Existing estimates of movements in vacant land prices are limited to a few metropolitan areas and infrequent time intervals. This paper develops a new methodology for estimating vacant land price trends for subareas within states and metropolitan areas. It utilizes data from a sales ratio study, a large database available in most states. The methodology uses assessed value to control for "hedonic characteristics" associated with the property and its location. A model is developed to correct assessed value for measurement errors. Statistical results for forty-one Connecticut towns indicate that the model provides a reasonable compromise between data availability and accuracy of price trend estimates.     

High Leverage and Willingness to Pay: Evidence from the Residential Housing Market

I document a strong correlation between paying the full listing price on homes and borrowing 100% loan‐to‐value. Homebuyers who do both overpay by 2.8% to 3.9% ($4,800 to $6,700) and are 22.7% more likely to have their properties foreclosed within one year. The correlation is not mechanical: there is a discontinuity in the average leverage around the full listing price. The correlation is stronger in areas with a high fraction of financially constrained and unsophisticated residents, and in areas of high past price growth (potentially indicative of buyer optimism).     

The Motivation for Institutional Real Estate Sales and Implications for Asset Class Returns

Since real estate assets are sold infrequently, analyses that use samples of exclusively sold properties to estimate pricing models may be seriously in error. This paper uses data on samples of sold and unsold properties and an appropriate statistical methodology to evaluate the extent of this bias. The results clearly show that it is important to control for sales motivations and that pricing equations that ignore this source of bias may be misleading.     

A Metropolitan Transaction-Based Commercial Price Index: A Time-Varying Parameter Approach

This study examines the usefulness of time-varying parameter techniques for constructing reliable transaction-based commercial price indices for metropolitan areas. Time-varying parameter techniques allow the implicit prices of differing quality characteristics to vary intertemporally, overcoming the potential bias imposed by holding implicit prices fixed and simply interpreting time dummy variables as in a conventional hedonic approach. This paper empirically investigates three time-varying parameter methods (Chained, Laspeyres, and Paasche) and considers the potential for sample selection bias. Precision measures are constructed to examine the reliability of the respective indices.     

Inventory of differential items selling from two shops under a single management with periodically increasing demand over a finite time-horizon

Inventories of differential items including the defective ones purchased/produced in a lot and sold from two shops (primary and secondary shops) under a single management are considered here over a finite time-horizon. A primary shop receives the differential units in a lot but sells only the non-defective ones whose demand periodically increases with time and decreases during the shortage period in such a way that it comes back to the initial value at the beginning of the next cycle. Hence in this shop, shortages are allowed and fully backlogged. Moreover, at the beginning of the next cycle, the retailer purchases purely non-defective units at a higher price to meet up the shortage amount along with the usual lot of differential units for regular sale. The defective units identified at the time of selling at the primary shop are continuously transferred to the adjacent secondary shop from which the defective ones are sold at a reduced price after some rework. Normally, the price of a defective item is fixed depending upon the quantum of its defect and people go for these items if they are cheap. Hence, demand for these units is dependent on the selling price, which is again inversely proportional to the rate of defectiveness. There may be five scenarios for dealing with defective units depending upon the coincidence of the time periods at two shops. For all scenarios, problems have been mathematically formulated and solved by the use of both parametric study and a gradient-based non-linear optimisation method. The models are illustrated with the help of numerical examples.     

Mass Layoffs and CEO Turnover

We investigate the relationship between layoff announcements and CEO turnover over a 31-year period. We find that layoffs significantly increase CEO turnover in the following year, and, in some time periods, CEO changes are strongly positively associated with layoff announcements two years earlier. We proceed to show how this relationship has changed over time, and offer several possible explanations. Finally, we find strong evidence that layoffs that are associated with negative stock price reactions are much more likely to lead to CEO turnover than those associated with positive stock price reactions, especially in the earlier years in our sample.