Edilberto Cepeda-Cuervo

This paper proposes new parameterizations of the beta and beta binomial distributions as functions of the mean and variance parameters. From these new parameterizations, new beta and beta binomial linear regression models are formulated by assuming that appropriate real functions of the mean and variance follow linear regression structures. These models were fitted to real datasets by applying Bayesian methods, using the OpenBUGS software. The new beta regression models were fitted to the Dyslexia Reading Accuracy dataset and the new beta binomial regression models were applied to the School Absenteeism Dataset. In both cases, the results obtained by fitting these models were compared with those obtained by fitting the usual mean and dispersion beta regression models and the mean and dispersion beta binomial regression models, respectively.

This paper proposes new parameterizations of the beta and beta binomial distributions as functions of the mean and variance parameters. From these new parameterizations, new beta and beta binomial linear regression models are formulated by assuming that appropriate real functions of the mean and variance follow linear regression structures. These models were fitted to real datasets by applying Bayesian methods, using the OpenBUGS software. The new beta regression models were fitted to the Dyslexia Reading Accuracy dataset and the new beta binomial regression models were applied to the School Absenteeism Dataset. In both cases, the results obtained by fitting these models were compared with those obtained by fitting the usual mean and dispersion beta regression models and the mean and dispersion beta binomial regression models, respectively.

In this paper we propose Bayesian methods to fit econometric regression models, including those where the variability is assumed to follow a regression structure. We formulate the main functions of the statistical R-package BSPADATA, developed according to the proposed methods to obtain posteriori parameter inferences. After that, we include results of simulated studies to illustrate the use of this package and the performance of the proposed methods. Finally, we provide studies to illustrate the applications of the models and compare our results with that obtained by maximum likelihood.

In this paper, we propose Bayesian skew‐normal regression models where the location, scale and shape parameters follow (linear or nonlinear) regression structures, and the variable of interest follows the Azzalini skew‐normal distribution. A Bayesian method is developed to fit the proposed models, using working variables to build the kernel transition functions. To illustrate the performance of the proposed Bayesian method and application of the model to analyze statistical data, we present results of simulated studies and of the application to studies of forced displacement in Colombia.

In this paper we propose Bayesian non-standardized t regression models with unknown degrees of freedom, where both location and scale parameters follow regression structures, and a Bayesian method to fit the proposed models and obtain posterior parameter inferences when the degrees of freedom are assumed to be continuous or discrete. Assuming uniform (discrete and continuous), exponential, Jeffreys and Poisson prior distributions, we develop a R-Bayesian t-regression package to obtain the posterior parameter estimates, applying a discrete and a continuous random walks in discrete and bounded real intervals, respectively. We also compare our proposal according to the usual maximum likelihood criteria, through simulations and an application to a financial dataset. In these simulations and the application, we find that our proposal has the best performance when we use the AIC, BIC and DIC criterions.

Details hetero_general is a function made in order to fit Spatial General Model with a normal heteroscedatic disturbance term through MCMC methods as Metropolis-Hastings algorithm, under two proposals for trasition kernel to get samples of spatial lag parameters, rho and lambda, and aided by working variables approach to get samples of conditional posterior distribution of gamma vector.

Background Variability in chronic kidney disease (CKD) progression is a well-known phenomenon that underlines the importance of characterizing the said outcome in specific populations. Our objectives were to evaluate changes in the estimated glomerular filtration rate (eGFR) over time and determine the frequency of dialysis admission and factors associated with this outcome, to estimate the rate of program’s loss-to-follow-up and the probability of transition between CKD stages over time. Methods e study type was an observational analytic retrospective cohort in patients treated in a CKD prevention program in Bogota, Colombia, between January 1, 2009, and December 31, 2013, with follow-up until December 31, 2018. Adult participants of 18 years of age or older with diagnosed CKD stages G3 or G4 were enrolled into a prevention program. For each patient, the rate of progression of CKD in ml/min/1.73 m2/year was estimated using the ordinary least-squares method. Dialysis initiation and program’s loss-to-follow-up rates were calculated. Heat maps were used to present probabilities of transitioning between various CKD stages over time. Survival model with competing risks was used to evaluate factors associated with dialysis initiation. Results A total of 2752 patients met inclusion criteria and contributed with 14133 patient-years of follow-up and 200 dialysis initiation events, which represents a rate of 1.4 events per 100 patient-years (95% CI 1.2 to 1.6). e median change of the eGFR for the entire cohort was− 0.47 ml/min/1.73 m2 per year, and in the diabetic population, it was− 1.55 ml/min/1.73 m2 per year. e program’s loss-to-follow-up …

In this paper, we propose new RESIDUALS for GAMMA REGRESSION models, assuming that both mean and shape parameters follow regression structures. The models are summarized and fitted by applying both classic and Bayesian methods as proposed by Cepeda-Cuervo (2001). The RESIDUALS are proposed from properties of the biparametric exponential family of distributions. Simulated and real data sets are analyzed to determine the performance and behavior of the proposed RESIDUALS.