Using Latent Root Regression to Identify Nonpredictive Collinearity in Statistical Appraisal Models

The objective of this study is to examine the potential benefits of using latent root regression techniques to improve the stability of appraisal coefficients (hedonic prices) over time. Another related objective is to more clearly identify the nature and implications of collinearity present in most appraisal models. The results indicate that the majority of the collinearity present in the data is of a predictive nature, hence latent root techniques will likely show little or no improvement over OLS models.     

Price Adjustment Policies in Procurement Contracting: An Analysis of Bidding Behavior

The fluctuations in fuel prices over the past decade led a number of government agencies to introduce price adjustment clauses in procurement contracting. Those clauses were primarily designed to reduce contractors’ uncertainty without considering the impact of such initiatives on bidding and the budget. We analyze a newly constructed, detailed panel of observations on bids for construction contracts and compare bidding behavior across periods and projects, and across items within projects. Estimates from a difference‐in‐differences approach, indicate that bidding becomes more aggressive and less dispersed after the implementation of this policy. The difference is more pronounced when we consider itemized bids than overall project bids. Alternative techniques of regression discontinuity and nonparametric estimation are applied and yield consistent results.     

Assessment Inequity in a Declining Housing Market: The Case of Detroit

We examine the degree to which assessment practices in the City of Detroit have created substantial inequities in property tax payments across residential properties. Two key contributions of this article include: (1) inequities created by assessment practices are examined in a collapsed real estate market, and (2) quantile regression techniques are used to determine how assessment practices have altered assessment distributions within and across property value groups. Results show that current practices have created a wide range of property tax payments across properties with similar value (horizontal inequity), and similar tax payments for properties of differing values (vertical inequity).     

A Theoretical Basis for Hedonic Regression: A Research Primer

The hedonic regression, estimation of an hedonic price function, is shown to be an approximation of a multifaceted consumption possibilities frontier in characteristics space. Consequently, a linear functional form is inappropriate, included characteristics must be restricted to those which pertain to the good itself, and the estimated intercept and qualitative characteristic coefficients are easily interpretable.     

An Empirical Analysis of Hedonic Regression and Grid-Adjustment Techniques in Real Estate Appraisal

Multiple regression analysis has become increasingly popular when appraising residential properties for tax purposes. Alternatively, most fee appraisers and real estate brokers use the traditional sales comparison approach. This study combines the two techniques and uses multiple regression to generate the adjustment coefficients used in the grid adjustment method. The study compares the combined grid-regression method with ordinary regression and defines the market conditions under which each method is likely to be more effective. The grid-regression method is found to be more accurate for relatively homogeneous housing markets, and the multiplicative percentage adjustment method (MPAM) the preferred approach.     

基于多元线性回归的装饰工程快速估价模型

针对目前装饰工程陕速估价方法的不足，以及装饰工程造价组成的特点，建立一种基于多元线性回归的快速估价新模型。以住宅类建筑为例，建立其多元线性回归模型，结合SPSS软件对样本分析，结果表明，其线性回归模型显著，同时，内墙、外墙、楼地面和窗的回归系数也非常显著。通过计算回归值与实际值的误差，发现误差比较理想，该模型具有很好的实用价值。     

基于绿色供应链的报废汽车企业绩效评价研究

本文基于绿色供应链理念,以A企业为代表的报废汽车回收公司为例,建立岭回归-BP神经网络企业绩效综合评价模型。首先采用岭回归分析法对指标进行筛选,再通过BP神经网络模型对筛选的指标进行仿真训练,并将实际结果与仿真结果进行对比评价,最终就企业存在的问题分别从3个层面提出相关建议。     

The Incidence of Property Taxes on Single-Family Housing*

The incidence of local property taxes, specifically the degree of capitalizing of property tax differentials in market prices, remains an unresolved question. The studies by Oates (1969) and McMillan and Carlson (1977) , which come to contradictory conclusions typify the diversity of opinion on the question. Many of the previous studies suffer from research design problems including, the use of census data for market values and property tax levels on real property; failure to control for differences in public services quality among the cities samples; and use of assessed value as a proxy for market price. A theoretical model in developed to explain the capitalization effect of property tax differentials within an urban area. Because the model is exactly identified, a single reduced from equation relating market value to a set of physical characteristics of the property and the level of property taxes can be estimated using ordinary least-squares techniques. The function is estimated using data drawn from 107 residential property sales made during 1976. Estimated parameters for the other equations then are determined indirectly. Actual market price and property tax data for each parcel ware used. It is found that property tax differentials on otherwise comparable properties are associated with significant market value differentials. Because the assessed value ranges from 7 to 20 percent of market value, the property tax procedure in the area studied appears to have randomly generated large capital gains for some and capital losses for others. Because of the limited data base, the statistical results are only indicative; the model, howevfer, should have wide applicability in a variety of questions concerning the incidence of property taxes.     

Why Do REIT Returns Poorly Reflect Property Returns? Unrealizable Appreciation Gains due to Trading Constraints as the Solution to the Short‐Term Disparity

This study addresses the short‐term disparity between REIT returns and direct property returns, and argues that this phenomenon is due to the trading constraints in the direct property market imposed on REITs (the dealer rule). This renders REITs unable to time markets in order to realize short‐term property appreciation profits, making REITs primarily a property income investment rather than a full property investment, and explains the observed disparity. Empirically, I find that REIT returns consistently reflect property income returns, but not property appreciation returns. This makes this study the first in the literature to find a consistent link between REIT returns and any portion of direct property returns at short time horizons, in the context of a linear factor model. I then set up a natural laboratory to test the trading‐constraints explanation by examining the appreciation dependence of different types of REITs, which should be differently affected by the trading constraints. I find that returns to UPREITs, which are less affected by the constraints, have a stronger appreciation dependence than returns to regular REITs. I also perform a size test and find that large REITs, which are less affected by the constraints, have a stronger appreciation dependence than small REITs. When testing the effects of UPREIT and size characteristics simultaneously, I find a consistent UPREIT effect. I further find that Real Estate Operating Companies (REOCs), which are not subject to trading constraints, show short‐term property appreciation dependence. These findings offer strong support for the trading‐restrictions explanation.     

Cheap Tuesdays and the demand for cinema

Many movie markets are characterised by extensive uniform pricing practices, hampering the ability to estimate price elasticities of demand. Australia presents a rare exception, with most cinemas offering cheap Tuesday ticket prices. We exploit this feature to estimate a random coefficients discrete choice model of demand for the Sydney region in 2007. We harness an extensive set of film, cinema, and time-dependent characteristics to build a rich demand system. Our results are consistent with a market expansion effect from the practice of discounted Tuesday tickets, and suggest that cinemas could profit from price dispersion by discounts based on observable characteristics.     

An Empirical Examination of the Stability of Housing Price Equations Over Time

This study investigates the extent to which the coefficients of housing price equations are stable over time. Using annual data from 1959 to 1979 for a large neighbourhood in Vancouver, British Columbia, a series of twenty-four housing price equations is estimated. The estimated coefficients exhibit substantial instability over the period. Further, prediction errors are generally minimized for a given year when the coefficients estimated for that year are used to predict. The results strongly suggest that such equations should be recalibrated each year.     

How Do Firms Finance Nonprimary Market Investments? Evidence from REITs

This study explores the impact of investment characteristics, mainly investment location relative to the firm's primary market, on financing choices by real estate investment trusts (REITs). Using a large sample of commercial property acquisitions, we show that REITs are 4–8% less likely to use secured (mortgage) debt when acquiring properties in their primary markets than elsewhere. The documented evidence supports a demand‐side story for the relation between investment characteristics and financing. Moreover, the evidence is consistent with the hypothesis that REITs avoid mortgage financing in their primary markets to preserve operational flexibility in those markets.     

The Performance of Commercial Mortgages

This study examines the return characteristics of a large, well-diversified commercial mortgage portfolio. Mortgage-specific cash-flow histories are constructed for 2,480 loans originated over the period 1974 through 1990, and a contingent-claims approach to pricing risky debt is used to estimate inter-temporal market values. Quarterly holding-period returns are compared across selected mortgage groups and to alternate asset classes. Our findings suggest that both mortgage returns and volatility of return are comparable to those of other forms of fixed-income assets over the study period. Implied property price volatility is found to average 17%, a result significantly higher than reported in earlier studies. While mortgage returns are found to vary by property type and region of origin, cross correlation of returns is found to be high, illustrating the systematic effect of interest rates on the performance of commercial mortgages over the period 1974 through 1990. However, an increase in credit risk in the latter years of the study suggests that diversification may be a worthwhile objective for holders of these assets. We do not find evidence to suggest that abnormal returns were earned on commercial mortgage portfolios over the study period.     

The Measurement of Firm Information About Product Demand

The role of firm information about product and financial markets is the subject of considerable research. Typically empirical research measures information through price dispersion. However, the dispersion represents an imperfect measure of information. Several studies utilize stochastic frontier estimation techniques to measure worker information about the labor market. This paper determines whether the frontier information measure can be applied to the measurement of firm information about product markets. Several intuitive hypotheses are tested concerning the relationship between firm characteristics and information investments. The results are consistent with expectations and provide support for using stochastic frontier techniques to measure firm information.     

Biased Prediction of Housing Values

This paper introduces the use of non-sample, prior information to the problem of predicting prices of heterogeneous products. Using data from the 1983 American Housing Survey, the predictive performance of three Stein-like empirical Bayes estimation rules are compared to the least squares estimator and the traditional biased estimation technique, ridge regression. The biased estimators improve upon the least squares mean square error of prediction risk under certain design-related conditions. We provide evidence of this for the housing market in this paper.     

可编程控制器发展综述

论述了可编程控制器(PLC)的产生和发展过程,概述了其特点、应用领域及今后的发展趋势。鉴于PLC具有通用性强、使用方便,功能性强、使用面广,可靠性高、抗干扰能力强,编程方法简单、易掌握,体积小,功耗低等特点,并且PLC控制技术将成为今后工业自动化的手段之一,建议将PLC内容纳入大学本科非电专业教学计划,以利于学生了解和掌握电机控制的先进技术。     

Taxation of Residential Property in New York City: The Sources of Differential Treatment

Intrajurisdictional variations in the effective residential property tax are analyzed for New York City. Significant variation is observed by type of structure, by borough, by income quartiles, and over time. Cross-sectional regression equations indicate that effective rates tend to vary inversely with income and positively with the proportion of poverty households and building size. Market values, on the other hand, tend to vary inversely with poverty households and building age, and positively with income and building size. Over time, effective tax rates show a strong inverse relationship with the rate of inflation.     

Personal Residential Real Estate Investment in Australia: Investor Characteristics and Investment Parameters

To date our understanding of the factors affecting the housing supply stem from the private provision of new units through real estate development. This article investigates a different aspect of housing supply, the private provision of rental housing through investment in existing properties. Using logistic regression and a series of micro data sets of Australian households, we examine the investment decision of residential rental property investors over the period 1990–2004. The sample period incorporates a full real estate cycle. Our results indicate that wealth-related factors are the dominant factors driving these investments. Life-cycle factors such as marriage and children play a less important role. Most of the determinants of income property investment do not vary with the property cycle. Marriage is an exception. It became more important as house prices rose.     

稠油开采节能技术的降稠方式分析

针对稠油流动性差、黏度大、开采难度大的问题,胜利油田根据不同条件的油藏选择了多种降黏开采方式,逐步建立并形成了具有自己特色的稠油油藏水驱开采技术、热采技术以及地面节能配套工艺技术。并对此三种开采方式的特点、性能及不同油藏条件下稠油开采方式的选择和开发效果进行了详细介绍。     

Multicollinearity: How common factors cause Type 1 errors in multivariate regression

Research Summary : In multivariate regression analyses of correlated variables, we sometimes observe pairs of estimated beta coefficients large in absolute magnitude and opposite in sign. T‐statistics are also large, suggesting meaningful findings. I found 64 recently published Strategic Management Journal articles with results exhibiting these characteristics. In this article, I demonstrate that such results may be Type 1 errors (false positives): If regressors are correlated via an unobservable common factor, estimated beta coefficients will misleadingly tend toward infinite magnitudes in opposite directions, even if the variables’ real effects are small and of the same sign. Diagnostics such as Variance Inflation Factors (VIF) will misleadingly validate Type 1 errors as legitimate results. After establishing general results via mathematical analysis and simulation, I provide guidelines for detection and mitigation. Managerial Summary : This article demonstrates mathematically how regression analyses with correlated independent variables may generate beta coefficients of opposite sign to the variables’ true effects. To assess the likelihood of this possibility, I propose that: if (a) absolute correlation of two independent variables is about ±0.3 or more (smaller correlations may be problematic for large data sets), (b) the two variables have beta coefficients of opposite sign, if correlated positively, and of the same sign, if correlated negatively, and (c) the bivariate correlation of one independent variable with the dependent variable is of the opposite sign from the beta coefficient, then the beta might be a false positive. To facilitate such analysis, authors should provide complete correlation tables, including dependent variables, interaction terms, and quadratic terms.