الصفحة 1
الصفحة 1
Information criteria and statistical modeling
One of the main objectives of this book is to provide comprehensive explanations of the concepts and derivations of the AIC and related criteria, including Schwarz’s Bayesian information criterion (BIC), together with a wide range of practical examples of model selection and evaluation criteria. A secondary objective is to provide a theoretical basis for the analysis and extension of information criteria via a statistical functional approach. A generalized information criterion (GIC) and a bootstrap information criterion are presented, which provide unified tools for modeling and model evaluation for a diverse range of models, including various types of nonlinear models and model estimation procedures such as robust estimation, the maximum penalized likelihood method and a Bayesian approach.
Finite Mixture and Markov Switching Models
The prominence of finite mixture modelling is greater than ever. Many important statistical topics like clustering data, outlier treatment, or dealing with unobserved heterogeneity involve finite mixture models in some way or other. The area of potential applications goes beyond simple data analysis and extends to regression analysis and to non-linear time series analysis using Markov switching models.It is the first time that the Bayesian perspective of finite mixture modelling is systematically presented in book form. It is argued that the Bayesian approach provides much insight in this context and is easily implemented in practice. Although the main focus is on Bayesian inference, the author reviews several frequentist techniques, especially selecting the number of components of a finite mixture model, and discusses some of their shortcomings compared to the Bayesian approach. The aim of this book is to impart the finite mixture and Markov switching approach to statistical modelling to a wide-ranging community. This includes not only statisticians, but also biologists, economists, engineers, financial agents, market researcher, medical researchers or any other frequent user of statistical models. This book should help newcomers to the field to understand how finite mixture and Markov switching models are formulated, what structures they imply on the data, what they could be used for, and how they are estimated.
Financial risk management with bayesian estimation of GARCH models : Theory and applications
This book presents methodologies for the Bayesian estimation of GARCH models and their application to financial risk management. The study of these models from a Bayesian viewpoint is relatively recent and can be considered very promising due to the advantages of the Bayesian approach, in particular the possibility of obtaining small-sample results and integrating these results in a formal decision model. The first two chapters introduce the work and give an overview of the Bayesian paradigm for inference. The next three chapters describe the estimation of the GARCH model with Normal innovations and the linear regression models with conditionally Normal and Student-t-GJR errors. The sixth chapter shows how agents facing different risk perspectives can select their optimal Value at Risk Bayesian point estimate and documents that the differences between individuals can be substantial in terms of regulatory capital.
Le choix bayésien: Principes et pratique
Covers the so-called Bayesian approach to statistical inference and in particular its decision-making aspects. The bases of this axiomatics (choice of the a priori, optimal decisions, tests and regions of confidence) are discussed in detail, as well as more recent openings of Bayesian analysis such as the choice of models, the use of numerical methods. Stochastic approximation (MCMC), the theory of noninformative laws (Berger-Bernardo axioms) and the relation to the classical theory of admissibility. Each chapter is completed by an extensive series of exercises of increasing difficulty and by bibliographical notes on the themes addressed. This book can be used in a Master's program in Applied Mathematics, Biometrics, Econometrics or any other program that uses quantitative information processing techniques. It only requires a basic course in probability theory and mathematical statistics as a preliminary.
Bayesian reliability
Bayesian Reliability presents modern methods and techniques for analyzing reliability data from a Bayesian perspective. The adoption and application of Bayesian methods in virtually all branches of science and engineering have significantly increased over the past few decades. This increase is largely due to advances in simulation-based computational tools for implementing Bayesian methods. The authors extensively use such tools throughout this book, focusing on assessing the reliability of components and systems with particular attention to hierarchical models and models incorporating explanatory variables. Such models include failure time regression models, accelerated testing models, and degradation models. The authors pay special attention to Bayesian goodness-of-fit testing, model validation, reliability test design, and assurance test planning. Throughout the book, the authors use Markov chain Monte Carlo (MCMC) algorithms for implementing Bayesian analyses--algorithms that make the Bayesian approach to reliability computationally feasible and conceptually straightforward.
Artificial neural networks : Formal Models and Their Applications – ICANN 2005 ; 15th International Conference, Warsaw, Poland, September 11-15, 2005, Proceedings, Part II
The second volume contains 162 contributions related to Formal Models and their Applications and deals with new neural network models, supervised learning algorithms, ensemble-based learning, unsupervised learning, recurent neural networks, reinforcement learning, bayesian approaches to learning, learning theory, artificial neural networks for system modeling, decision making, optimalization and control, knowledge extraction from neural networks, temporal data analysis, prediction and forecasting, support vector machines and kernel-based methods, soft computing methods for data representation, analysis and processing, data fusion for industrial, medical and environmental applications, non-linear predictive models for speech processing, intelligent multimedia and semantics, applications to natural language processing, various applications, computational intelligence in games, and issues in hardware implementation.
