A Bayesian approach for zero-modified Skellam model with Hamiltonian MCMC

Statistical Methods & Applications - In this paper is presented the zero-modified poisson difference and present possible applications of them in the analysis of paired count data. The...     

Misestimating Betting Behavior: The Role of Negative Asymmetries in Emotional Self Prediction

This paper addresses the role of negative asymmetries in emotional self-prediction by looking at the extent to which individuals misestimate their own betting behavior in sequential gambles. In a series of three experimental studies, we demonstrate that losses lead to higher than planned bets whereas bets are on average carried over after gains. Such asymmetric deviations from the plan emerge (1) when monetary and non-monetary incentives are used, and (2) when participants face fair and unfair gambles. The asymmetry is based on people’s inability to predict how much the negative emotions generated by a bad experience (e.g. the loss) will influence them to put more effort (e.g. bet more) than planned in an attempt to re-establish a homeostatic state in the prospect of a good experience (e.g. winning).     

Ergonomic work analysis as a tool of prevention for the occupational safety and health management system

This paper introduces the Ergonomic Work Analysis as a relevant instrument to identify the risks in occupational environments through the investigation of factors that influence the relationship between the worker and the productive process. It draws a parallel between the several aspects of risk identification in traditional tools of Health and Safety Management and the factors embraced by the Ergonomic Work Analysis, showing that the ergonomic methodology is able to go deeper in the scenarios of possible incident causes. This deepening enables the establishment of a relationship between the work context and the upcoming damage to the physical integrity of the worker. It acts as a complementary instrument in the traditional approach to the risk management. In order to explain the application of this methodology in a preventive way, it is presented a case study of a coal mill inspector in a siderurgic company.     

Bayesian multivariate GARCH models with dynamic correlations and asymmetric error distributions

The main goal in this paper is to develop and apply stochastic simulation techniques for GARCH models with multivariate skewed distributions using the Bayesian approach. Both parameter estimation and model comparison are not trivial tasks and several approximate and computationally intensive methods (Markov chain Monte Carlo) will be used to this end. We consider a flexible class of multivariate distributions which can model both skewness and heavy tails. Also, we do not fix tail behaviour when dealing with fat tail distributions but leave it subject to inference.     

Daytime Sleepiness,Poor Sleep Quality,Eveningness Chronotype,and Common Mental Disorders Among Chilean College Students

Abstract

Objectives: To evaluate whether daytime sleepiness, poor sleep quality, and morningness and eveningness preferences are associated with common mental disorders (CMDs) among college students. Methods: A total of 963 college students completed self-administered questionnaires that collected information about sociodemographic characteristics, sleep quality characteristics, CMDs, and other lifestyle behaviors. Results: The prevalence of CMDs was 24.3% (95% confidence interval [CI] [21.5%, 27.1%]) among all students. Prevalence estimates of both excessive daytime sleepiness and poor sleep quality were higher among females (35.4% and 54.4%) than males (22.0% and 45.8%). Cigarette smoking was statistically significantly and positively associated with having CMDs (p = .034). Excessive daytime sleepiness (odds ratio [OR] = 3.65; 95% CI [2.56, 4.91]) and poor sleep quality (OR = 4.76; 95% CI [3.11, 7.29]) were associated with increased odds of CMDs. Conclusion: Given the adverse health consequences associated with both sleep disorders and CMDs, improving sleep hygiene among college students is imperative to public health.     

Predicting rainy seasons: quantifying the beliefs of prophets

In general, meteorologists find it difficult to make seasonal predictions in the north-east region of Brazil due to the contrasting atmospheric phenomena that take place there. The rain prophets claim to be able to predict the seasonal weather by observing the behavior of nature. Their predictions have a strong degree of subjectivity; this makes science (especially meteorology) disregard these predictions, which could be a relevant source of information for prediction models. In this article, we regard the prophets’ knowledge from a subjectivist point of view: we apply elicitation of expert knowledge techniques to extract their opinions and convert them into probability densities that represent their predictions of forthcoming rainy seasons.     

Dual class shares,board of directors’ effectiveness and firm’s market value: an empirical study

This study aims to identify whether a relationship exists between the controlling shareholders’ voting power and outside directors’ effectiveness in maximizing firms’ financial performance. We analyze a panel data with 3057 observations for the 2000–2012 period using a random effects model, logit and probit regressions, and the two-stage model of Heckman in the Brazilian stock market. Our findings show that firms whose controlling shareholders use dual class shares to leverage their voting power have less independence from the board and worse financial performance and market value. Further, the percentage of outside directors tends to be ineffective in increasing the firm’s value, and in changing the firm’s chief executive officer (CEO) when (1) the controlling shareholder’s voting power is leveraged, or (2) when the CEO assumes a position on the board of directors simultaneously. We interpreted that these results are in line with the arguments in favor of the existence of a new agency cost, which is related to the undue obedience of board members to authority, such as the largest controlling shareholder or the CEO in Brazilian listed firms.     

Robust Bayesian model selection for variable clustering with the Gaussian graphical model

Statistics and Computing - Variable clustering is important for explanatory analysis. However, only few dedicated methods for variable clustering with the Gaussian graphical model have been...     

Transformed generalized linear models

The estimation of data transformation is very useful to yield response variables satisfying closely a normal linear model. Generalized linear models enable the fitting of models to a wide range of data types. These models are based on exponential dispersion models. We propose a new class of transformed generalized linear models to extend the Box and Cox models and the generalized linear models. We use the generalized linear model framework to fit these models and discuss maximum likelihood estimation and inference. We give a simple formula to estimate the parameter that index the transformation of the response variable for a subclass of models. We also give a simple formula to estimate the r$r$th moment of the original dependent variable. We explore the possibility of using these models to time series data to extend the generalized autoregressive moving average models discussed by Benjamin et al. [Generalized autoregressive moving average models. J. Amer. Statist. Assoc. 98, 214–223]. The usefulness of these models is illustrated in a simulation study and in applications to three real data sets.     

Some results for maximum likelihood estimation of adjusted relative risks

Maximum likelihood (ML) estimation of relative risks via log-binomial regression requires a restricted parameter space. Computation via non linear programming is simple to implement and has high convergence rate. We show that the optimization problem is well posed (convex domain and convex objective) and provide a variance formula along with a methodology for obtaining standard errors and prediction intervals which account for estimates on the boundary of the parameter space. We performed simulations under several scenarios already used in the literature in order to assess the performance of ML and of two other common estimation methods.