Empiric Bayes Estimation of Hypergeometric Probability.
Estimación bayesiana de una función de fiabilidad con conocimiento a priori gamma expendido.
Se plantea el problema de estimar una función de fiabilidad en el contexto bayesiano no paramétrico, pero utilizando técnicas paramétricas de estimación en procesos estocásticos. Se define el proceso gamma extendido, cuyas trayectorias son tasas de azar crecientes cuando se eligen convenientemente los parámetros del proceso. Se obtienen estimadores basados en este proceso, se estudian sus propiedades asintóticas bayesianas, y se termina con un ejemplo de aplicación mediante simulación.
Estimación bayesiana múltiple de un parámetro.
The problem to be analyzed in this paper deals with the finding of n values x1, x2, ..., xn ∈ R which minimize the function:E [míni=1,...,n c (ξ - xi)]where ξ is a one-dimensional random variable with known distribution function φ and c is a measurable and positive function.First, conditions on c in order to ensure the existence of a solution to this problem are determined. Next, necessary conditions to be satisfied by the point (x1, x2, ..., xn) in which the function attains the minimum are looked...
Estimación paramétrica bayesiana no paramétrica de funciones de supervivencia con observaciones parcialmente censuradas.
The problem of nonparametric estimation of a survival function based on a partially censored on the right sample is established in a Bayesian context, using parametric Bayesian techniques. Estimates are obtained considering neutral to the right processes, they are particularized to some of them, and their asymptotic properties are studied from a Bayesian point of view. Finally, an application to a Dirichlet process is simulated.
Estimates of reliability for the normal distribution
The minimum variance unbiased, the maximum likelihood, the Bayes, and the naive estimates of the reliability function of a normal distribution are studied. Their asymptotic normality is proved and asymptotic expansions for both the expectation and the mean squared error are derived. The estimates are then compared using the concept of deficiency. In the end an extensive Monte Carlo study of the estimates in small samples is given.
Estimating normal density and normal distribution function: is Kolmogorov's estimator admissible?
The statistical estimation problem of the normal distribution function and of the density at a point is considered. The traditional unbiased estimators are shown to have Bayes nature and admissibility of related generalized Bayes procedures is proved. Also inadmissibility of the unbiased density estimator is demonstrated.
Estimating the shape parameter of the Topp-Leone distribution based on Type I censored samples
The shape parameter of the Topp-Leone distribution is estimated from classical and Bayesian points of view based on Type I censored samples. The maximum likelihood and the approximate maximum likelihood estimates are derived. The Bayes estimate and the associated credible interval are approximated by using Lindley's approximation and Markov Chain Monte Carlo using the importance sampling technique. Monte Carlo simulations are performed to compare the performances of the proposed methods. Real and...
Estimation of the parameters of Gumbel and Burr distributions in terms of kth record values
The minimum variance linear unbiased estimators (MVLUE), the best linear invariant estimators (BLIE) and the maximum likelihood estimators (MLE) based on m selected kth record values are presented for the parameters of the Gumbel and Burr distributions.
Estimation of the scale parameter of gamma model in the presence of outlier observations.
Estimation of the variance components in the linear regression model
Estimation with delayed observations
Evolutionary computation based on Bayesian classifiers
Evolutionary computation is a discipline that has been emerging for at least 40 or 50 years. All methods within this discipline are characterized by maintaining a set of possible solutions (individuals) to make them successively evolve to fitter solutions generation after generation. Examples of evolutionary computation paradigms are the broadly known Genetic Algorithms (GAs) and Estimation of Distribution Algorithms (EDAs). This paper contributes to the further development of this discipline by...
Evolutionary learning of rich neural networks in the Bayesian model selection framework
In this paper we focus on the problem of using a genetic algorithm for model selection within a Bayesian framework. We propose to reduce the model selection problem to a search problem solved using evolutionary computation to explore a posterior distribution over the model space. As a case study, we introduce ELeaRNT (Evolutionary Learning of Rich Neural Network Topologies), a genetic algorithm which evolves a particular class of models, namely, Rich Neural Networks (RNN), in order to find an optimal...
Extensions de l'analyse de la variance : l'analyse bayésienne des comparaisons