Estimation and diagnostic for skew-normal partially linear models

Partially linear models (PLMs) are an important tool in modelling economic and biometric data and are considered as a flexible generalization of the linear model by including a nonparametric component of some covariate into the linear predictor. Usually, the error component is assumed to follow a normal distribution. However, the theory and application (through simulation or experimentation) often generate a great amount of data sets that are skewed. The objective of this paper is to extend the PLMs allowing the errors to follow a skew-normal distribution [A. Azzalini, A class of distributions which includes the normal ones, Scand. J. Statist. 12 (1985), pp. 171–178], increasing the flexibility of the model. In particular, we develop the expectation-maximization (EM) algorithm for linear regression models and diagnostic analysis via local influence as well as generalized leverage, following [H. Zhu and S. Lee, Local influence for incomplete-data models, J. R. Stat. Soc. Ser. B 63 (2001), pp. 111–126]. A simulation study is also conducted to evaluate the efficiency of the EM algorithm. Finally, a suitable transformation is applied in a data set on ragweed pollen concentration in order to fit PLMs under asymmetric distributions. An illustrative comparison is performed between normal and skew-normal errors.     

The Brazilian public pension system: Policy changes, political effects

This article discusses the reciprocal relationship between public pension policy and age-based politics in Brazil, a nation with a public pension system that has the potential for influencing policy developments in other developing nations faced with the problem of how to extend social security coverage to the entire population. Our goal is to extend a line of analysis used in previous studies of industrial nations to the case of Brazil. Pension policy changes made during the 1960s and 1970s had a number of unintended consequences. One was the role these policy changes played with respect to the emergence of rural unions and age-based interest groups: both are becoming increasingly important actors with respect to pension policy. We discuss the implications of the Brazilian case for policy options and outcomes in other newly democratic nations, particularly those in Latin America.     

On influence diagnostic in univariate elliptical linear regression models

We discuss in this paper the assessment of local influence in univariate elliptical linear regression models. This class includes all symmetric continuous distributions, such as normal, Student-t, Pearson VII, exponential power and logistic, among others. We derive the appropriate matrices for assessing the local influence on the parameter estimates and on predictions by considering as influence measures the likelihood displacement and a distance based on the Pearson residual. Two examples with real data are given for illustration.     

Supporting the allocation of software development work in distributed teams with multi-criteria decision analysis

In the fast moving software industry, projects have been increasingly developed by distributed teams, which are located in geographically remote offices and collaborate using information communication technologies. In such environments, project distribution presents specific challenges, as work in distributed teams increases project technical complexity, communication lines multiply and stakeholders’ interests may be divergent. Despite the importance and complexity of this type of problem, it seems that there is a lack of reports, in the literature, of systems that could support these decisions. This paper presents a real-world case study, where we developed a multi-criteria model for supporting the distributed team work allocation decision for a major global software company. It was developed with a group of software development project managers, using decision conferencing and multi-attribute value analysis. The model deals not only with software engineering attributes, but also “soft” and strategic issues, like team satisfaction and training opportunities. We also discuss some issues and challenges faced during this modelling process.     

Bias correction and improved residuals for non-exponential family nonlinear models

In this paper we derive general formulae for the biases to order n ^?1 of the parameter estimates in a general class of nonlinear regression models, where n is the sample size. The formulae are related to those of Cordeiro and McCullagh (1991) and Paula (1992) and may be viewed as extensions of their results, Correction factors are derived for the score and deviance component residuals in these models. The practical use of such corrections is illustrated for the log-gamma model.     

A flexible semiparametric regression model for bimodal,asymmetric and censored data

In this paper, we propose a new semiparametric heteroscedastic regression model allowing for positive and negative skewness and bimodal shapes using the B-spline basis for nonlinear effects. The proposed distribution is based on the generalized additive models for location, scale and shape framework in order to model any or all parameters of the distribution using parametric linear and/or nonparametric smooth functions of explanatory variables. We motivate the new model by means of Monte Carlo simulations, thus ignoring the skewness and bimodality of the random errors in semiparametric regression models, which may introduce biases on the parameter estimates and/or on the estimation of the associated variability measures. An iterative estimation process and some diagnostic methods are investigated. Applications to two real data sets are presented and the method is compared to the usual regression methods.     

New regression model with four regression structures and computational aspects

A new general class of exponentiated sinh Cauchy regression models for location, scale, and shape parameters is introduced and studied. It may be applied to censored data and used more effectively in survival analysis when compared with the usual models. For censored data, we employ a frequentist analysis for the parameters of the proposed model. Further, for different parameter settings, sample sizes, and censoring percentages, various simulations are performed. The extended regression model is very useful for the analysis of real data and could give more adequate fits than other special regression models.     

Mapping vulnerability to climate change-related hazards: children at risk in a US–Mexico border metropolis

There are significant human impacts associated with climate change. This paper introduces a model for identifying small area risks associated with children’s vulnerability to climate change-related hazard exposures, which is transferable to other regions and adaptable to varied population and exposure scenarios. The cross-national El Paso-Ciudad Juárez (US-Mexico) metropolis serves as the study area for model implementation, which involves mapping social vulnerability, hazard exposure, and cumulative climate change-related risks. This study addresses two limitations of extant fine-scale climate change vulnerability mapping studies. First, rather than focusing on one exposure variable, it assesses the combined risks of multiple exposures (extreme heat, peak ozone, and floods) and, thus, offers a model for mapping neighborhood-level cumulative climate change exposure risks. Second, it provides a model for small area spatial analyses of climate change vulnerability within low-/middle-income countries and in contexts where climate change risks (and appropriate responses) are cross-national in scope.