Search

As the marginal suspect and propensity to commit crime are unobserved across racial categories, it is difficult to quantify racial bias with law enforcement outcomes data. We test for racial bias in driving-under-the-influence of alcohol enforcement. The assessment outcome variable, blood alcohol content (BAC), provides information about motorist's choices and allows for a more refined test for racial bias compared with other law enforcement outcome data. We find no evidence of racial bias in the relevant range where our model applies. However, we do find differences in find rates at the lowest levels of BAC, where there should be no impairment. (JEL J7, K42), I. INTRODUCTION The Civil Rights Act of 1964 created a legal cause of action in Federal Courts in claims of discrimination on the basis of age, race, or gender under [...]

When there is uncertainty concerning the appropriate statistical model and corresponding estimators and inference methods, we use the Cressie--Read measure of divergence to define a semiparametric estimator, [??]([??]), that combines plausible estimation problems. This estimation procedure identifies, conditional on the data, an optimal combination of competing estimators for the unknown parameters associated with the alternative plausible structural model specifications. The optimization is handled internally and avoids the tuning parameters usually necessary in problems of this type. To illustrate finite sample performance, an extensive sampling experiment is conducted to demonstrate the adaptive nature of the estimator for an array of data sampling specifications. JEL Classification: C10; C24 Keywords: Semiparametric estimation and inference; Empirical likelihood; Convex combination of estimators; Asymptotic and finite sample risk

Asymptotically, semi parametric estimators of the parameters in linear structural models have the same sampling properties. In finite samples the sampling properties of these estimators vary and large biases may result for sample sizes often found in practice. With a goal of improving asymptotic risk performance and finite sample efficiency properties, we investigate the idea of combining correlated structural equation estimators with different finite and asymptotic sampling characteristics. Based on a quadratic loss measure, we present evidence that the finite sample performance of the resulting combination estimator can be notably superior to that of a leading traditional moment based estimator. Keywords: Combined estimators: Quadratic loss; Semiparametric estimation; Data dependent shrinkage; Instrumental variables

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.jeconom.2004.08.006 Byline: Ron C. Mittelhammer (a), George G. Judge (b) Keywords: Combined estimators; Quadratic loss; Semiparametric estimation; Data dependent shrinkage; Instrumental variables Abstract: Asymptotically, semi parametric estimators of the parameters in linear structural models have the same sampling properties. In finite samples the sampling properties of these estimators vary and large biases may result for sample sizes often found in practice. With a goal of improving asymptotic risk performance and finite sample efficiency properties, we investigate the idea of combining correlated structural equation estimators with different finite and asymptotic sampling characteristics. Based on a quadratic loss measure, we present evidence that the finite sample performance of the resulting combination estimator can be notably superior to that of a leading traditional moment based estimator. Author Affiliation: (a) School of Economic Sciences and Department of statistics, Washington State University, P.O. Box 646210, Pullman, WA 99164-3144,USA (b) Department of Agricultural and Resource Economics, 207 Giannini Hall, University of California, Berkeley, CA 94720, USA Article History: Received 12 February 2004

A Bayesian bootstrap multivariate regression (BBMR) procedure is presented that allows robust Bayesian analysis of multivariate regression models. BBMR does not require a parametric specification for the likelihood function and instead uses a bootstrapped likelihood based on the sampling distribution of location and scale estimators. A mixing algorithm for implementing the procedure automatically incorporates the scale invariant ignorance prior on the covariance matrix. BBMR can be implemented as a generic algorithm in standard statistical software independently of the actual choice of prior distribution. Monte Carlo evidence is provided showing accuracy and robustness of the approach in representing posterior distributions. Keywords: Bayesian inference; Bootstrapping; Robust likelihood; Multivariate regression; Simultaneous equation mappings

The economic consequences of assigning individual transferable quotas (ITQ) in fisheries management to harvesters and its effects on processors are analyzed. Previous literature has implied that assigning fishing rights is equivalent to property rights and that this was done to prevent the occurrence of overcapitalization among harvesters. It was argued that without perfectly malleable capital, a conventional ITQ policy will cause the disenfranchisement of the processing sector by relegating some of its quasi-rents to the harvesting sector during a transition period and in the long-run.

Applications of Bayesian statistical techniques are examined. The applications include a combination of the techniques with inferential philosophy within a linear model, the selection of an autoregressive process for determining prices in futures markets and a linear model of agricultural supply with variable parameters. It is shown that the Bayesian method offers consistent applications involving prior and data-based information.

The effects of site characteristics on agricultural land values are examined. Conventional theory states that expected net return is the most important determinant of land values, but both its monetary and psychic components are nor readily available for use in testing. Instead, the hedonic regression approach is proposed, wherein a combination of variables such as gross income, soil productivity, parcel size, irrigation and other site characteristics is used as a proxy for net returns. This approach combines Bieren's conditional moment test and nonnegativity constraints and is applied to six areas in Washington state. The results indicate that land values are indeed determined by site characteristics and that the sample land markets are highly regioinal. In addition, both nonnegative truncation and parsimonious model specifications are valuable tools.

Research shows that consumers who are likely to buy a specific product are those who indicate their willingness to pay a premium greater than or equal to a positive lower bound. Data were obtained from surveys regarding 'eco-labeled' or environmentally safe produce.

A new study investigates whether ex-vessel price determination in the Alaska king crab industry may be considered to be a bilateral monopoly.