Linear functional regression: The case of fixed design and functional response

The authors consider the problem of simple linear regression when the exogenous and endogenous variables are functional and the design is fixed. They propose an estimator for the underlying linear operator and prove its consistency under some conditions which ensure that the design is sufficiently informative. They consider the classical calibration (or inverse regression) problem and analyze a consistent estimator. They also give a simulation study. The proposed method is not hard to implement in practice.     

Who's Minding the Kids? Pollucion,Public Schools,and Environmental Justice in Los Angeles

Objective . Although previous environmental justice research has focused on analysis of the disproportionate burden of environmental hazards on minority residents, few studies have examined demographic inequities in health risks among children. This article evaluates the demographic distribution of potentially hazardous facilities and health risks associated with ambient air toxics exposures among public schoolchildren in the Los Angeles Unified School District. Methods . We combine Geographic Information System analysis with multivariate statistics to compare enrollment and demographic information for students who attend district schools with the spatial pattern of land use, locations of toxic emissions and facilities, and calculated indices of estimated lifetime cancer risk and respiratory hazards associated with exposures to toxic air emissions. Results . District schools are more likely to be located in census tracts containing potentially hazardous facilities; however, these tracts actually have slightly lower cancer and respiratory health risks associated with air toxics when compared to other tracts in the district. Demographic comparisons among school sites indicate that minority students, especially Latinos, are more likely to attend schools near hazardous facilities and face higher health risks associated with outdoor air toxics exposure. Conclusions . These patterns of hazard exposure and health risk should be considered both in the process of siting new schools to house the rapidly growing regional student population and in remediation efforts at existing schools.     

Explaining the Surge in Citizenship Applications in the 1990s: Lawful Permanent Residents in Texas

Objective . We explore the increase in citizenship applications in the mid–1990s in order to test popular explanations for them, such as the consequences of IRCA legalization, fear of loss of public benefits, and effects of citizenship outreach programs. Methods . We rely on a nonrandom sample of 526 lawful permanent residents in four Texas cities. About half had applied for citizenship and all were taking affirmative steps via participation in citizenship or English–language classes. Results . Having received amnesty under IRCA predicts rapid application for citizenship upon eligibility but is not associated with greater mastery of the naturalization process or better English skills. Fear of losing eligibility for public benefits and campaigns promoting naturalization motivated about one–quarter of citizenship applicants. Much larger proportions cite their desire to participate fully in American life, to sponsor the immigration of relatives, and to ensure opportunities for their children. The main obstacle they identify is limited English proficiency. Conclusions . Although factors peculiar to the political environment of the 1990s affected many permanent residents, most cited traditional incentives having to do with investment in opportunities for themselves and their families. Our data suggest that the most effective way to facilitate naturalization is to devote more resources to English–language training.     

Globalisation,identity and the state

The government of Botswana had to strike a fine balance between not isolating the liberation movements, not letting them use Botswana as a military base and not appearing to harbour ‘terrorists’. The government realised that overtly supporting the liberation movements was potentially suicidal, for the country could easily be punished by South Africa: trade links could be severed and communication networks paralysed. The settler regimes did try to infiltrate and weaken the liberation movements in Botswana and carried out acts such as kidnapping, intimidation and deportation, to try to prevent the liberation movements from threatening the status quo in southern Africa. Using evidence from the Botswana National Archives, oral interviews, and newspaper reports, the article examines the means the Botswana government adopted to deal with the situation and safeguard the security of its citizens.     

A comparative study of legitimation strategies in hybrid regimes

Despite the growing body of research on ‘hybrid regimes’, few studies address the issue of their domestic legitimacy. Targeting this gap in the literature, this article explores the legitimation strategies of three hybrid regimes around the globe: Russia, Venezuela, and Seychelles. Although these countries differ markedly in almost every aspect that can be thought of, the political systems of all three cases combine formally democratic institutions with authoritarian political dynamics. The qualitative, comparative analysis presented in this article uncovers a number of remarkable similarities between the regimes’ respective legitimization strategies. However, while the strategies for engendering legitimacy are similar across the cases, the content of these strategies is different: the Russian leadership mainly relies on preserving order and nationalism, the Venezuelan regime employs a more populist strategy, and the Seychellois regime uses a more personal and particularistic approach. Our findings not only provide insights into the mechanisms hybrid regimes use to consolidate their authority, but also highlight important differences and similarities between hybrid regimes around the world.     

Estimation and Testing in Elliptical Functional Measurement Error Models

The purpose of this article is to investigate estimation and hypothesis testing by maximum likelihood and method of moments in functional models within the class of elliptical symmetric distributions. The main results encompass consistency and asymptotic normality of the method of moments estimators. Also, the asymptotic covariance matrix of the maximum likelihood estimator is derived, extending some existing results in elliptical distributions. A measure of asymptotic relative efficiency is reported. Wald-type statistics are considered and numerical results obtained by Monte Carlo simulation to investigate the performance of estimators and tests are provided for Student-t and contaminated normal distributions. An application to a real dataset is also included.     

A General Class of Estimators for the Linear Regression Model Affected by Collinearity and Outliers

In this article, a general class of estimators for the linear regression model affected by outliers and collinearity is introduced and studied in some detail. This class of estimators combines the theory of light, maximum entropy, and robust regression techniques. Our theoretical findings are illustrated through a Monte Carlo simulation study.     

Robust Bayesian inference in STAR models with neighbourhood effects

In this paper we propose a robust Bayesian procedure of estimation, testing, validation and selection of spatio-temporal autoregressive models (STAR) with neighbourhood effects applied to the appraisal of dwelling prices. The methodology does not depend on asymptotic results and, unlike previously procedures proposed in the literature, takes into account the uncertainty associated to the estimation of the neighbourhood parameters of the model, giving more realism to the analysis. Moreover, a sequential algorithm to elaborate fast on-line forecast, is provided. The methodology is illustrated by means of a practical case of the real estate market of Zaragoza.     

A Generalized Bayes Rule for Prediction

In the case of prior knowledge about the unknown parameter, the Bayesian predictive density coincides with the Bayes estimator for the true density in the sense of the Kullback-Leibler divergence, but this is no longer true if we consider another loss function. In this paper we present a generalized Bayes rule to obtain Bayes density estimators with respect to any α-divergence, including the Kullback-Leibler divergence and the Hellinger distance. For curved exponential models, we study the asymptotic behaviour of these predictive densities. We show that, whatever prior we use, the generalized Bayes rule improves (in a non-Bayesian sense) the estimative density corresponding to a bias modification of the maximum likelihood estimator. It gives rise to a correspondence between choosing a prior density for the generalized Bayes rule and fixing a bias for the maximum likelihood estimator in the classical setting. A criterion for comparing and selecting prior densities is also given.