Determining the season of death from the family composition of insects infesting carrion

Determining the season of death by means of the composition of the families of insects infesting carrion is rarely attempted in forensic studies and has never been statistically modelled. For this reason, a baseline-category logit model is proposed for predicting the season of death as a function of whether the area where the carcass was exposed is sunlit or shaded and of the relative abundance of particular families of carrion insects (Calliphoridae, Fanniidae, Sarcophagidae, and Formicidae). The field study was conducted using rodent carcasses (20-252 g) in an urban forest in southeastern Brazil. Four carcasses (2 in a sunlit and 2 in a shaded area) were placed simultaneously at the study site, twice during each season from August 2003 through June 2004. The feasibility of the model, measured in terms of overall accuracy, is 64 +/- 14%. It is likely the proposed model will assist forensic teams in predicting the season of death in tropical ecosystems, without the need of identifying the species of specimens or the remains of carrion insects.

A valuation of patients` willingness-to-pay for insulin delivery in diabetes

Objectives: The aim of this study was to determine the insulin-delivery system and the attributes of insulin therapy that best meet patients` preferences, and to estimate patients` willingness-to-pay (WTP) for them. Methods: This was a cross-sectional discrete choice experiment (DCE) study involving 378 Canadian patients with type 1 or type 2 diabetes. Patients were asked to choose between two hypothetical insulin treatment options made up of different combinations of the attribute levels. Regression coefficients derived using conditional logit models were used to calculate patients` WTP. Stratification of the sample was performed to evaluate WTP by predefined subgroups. Results: A total of 274 patients successfully completed the survey. Overall, patients were willing to pay the most for better blood glucose control followed by weight gain. Surprisingly, route of insulin administration was the least important attribute overall. Segmented models indicated that insulin naive diabetics were willing to pay significantly more for both oral and inhaled short-acting insulin compared with insulin users. Surprisingly, type 1 diabetics were willing to pay $C11.53 for subcutaneous short-acting insulin, while type 2 diabetics were willing to pay $C47.23 to avoid subcutaneous short-acting insulin (p < .05). These findings support the hypothesis of a psychological barrier to initiating insulin therapy, but once that this barrier has been overcome, they accommodate and accept injectable therapy as a treatment option. Conclusions: By understanding and addressing patients` preferences for insulin therapy, diabetes educators can use this information to find an optimal treatment approach for each individual patient, which may ultimately lead to improved control, through improved compliance, and better diabetes outcomes.

Fiscal policy and reelection in Brazilian municipalities

This paper uses a new panel of more than 2,000 Brazilian municipalities over 13 years to analyze the influence of public expenditures on the probability of mayors` reelection. We examine Brazilian municipal elections from 1988 to 2000 using a logit fixed-effects model. The results suggest that mayors who spend more during their terms of office increase the probability of their own reelection or of a successor of the same political party. In particular, higher capital spending over the years preceding elections and current expenditures in election years are beneficial to Brazilian incumbent mayors.

Power series generalized nonlinear models

We introduce in this paper a new class of discrete generalized nonlinear models to extend the binomial, Poisson and negative binomial models to cope with count data. This class of models includes some important models such as log-nonlinear models, logit, probit and negative binomial nonlinear models, generalized Poisson and generalized negative binomial regression models, among other models, which enables the fitting of a wide range of models to count data. We derive an iterative process for fitting these models by maximum likelihood and discuss inference on the parameters. The usefulness of the new class of models is illustrated with an application to a real data set. (C) 2008 Elsevier B.V. All rights reserved.

Bayesian Estimation of the Logistic Positive Exponent IRT Model

A Bayesian inference approach using Markov Chain Monte Carlo (MCMC) is developed for the logistic positive exponent (LPE) model proposed by Samejima and for a new skewed Logistic Item Response Theory (IRT) model, named Reflection LPE model. Both models lead to asymmetric item characteristic curves (ICC) and can be appropriate because a symmetric ICC treats both correct and incorrect answers symmetrically, which results in a logical contradiction in ordering examinees on the ability scale. A data set corresponding to a mathematical test applied in Peruvian public schools is analyzed, where comparisons with other parametric IRT models also are conducted. Several model comparison criteria are discussed and implemented. The main conclusion is that the LPE and RLPE IRT models are easy to implement and seem to provide the best fit to the data set considered.

Framework for Skew-Probit Links in Binary Regression

We review several asymmetrical links for binary regression models and present a unified approach for two skew-probit links proposed in the literature. Moreover, under skew-probit link, conditions for the existence of the ML estimators and the posterior distribution under improper priors are established. The framework proposed here considers two sets of latent variables which are helpful to implement the Bayesian MCMC approach. A simulation study to criteria for models comparison is conducted and two applications are made. Using different Bayesian criteria we show that, for these data sets, the skew-probit links are better than alternative links proposed in the literature.

Comparison for three Classification Techniques

In this paper we show the results of a comparison simulation study for three classification techniques: Multinomial Logistic Regression (MLR), No Metric Discriminant Analysis (NDA) and Linear Discriminant Analysis (LDA). The measure used to compare the performance of the three techniques was the Error Classification Rate (ECR). We found that MLR and LDA techniques have similar performance and that they are better than DNA when the population multivariate distribution is Normal or Logit-Normal. For the case of log-normal and Sinh(-1)-normal multivariate distributions we found that MLR had the better performance.