Statistical Modeling and Analysis for Complex Data Problems

ISBN-13: 9780387245546 / Angielski / Twarda / 2005 / 324 str.

Pierre Duchesne; Bruno Remillard; Bruno Rimillard

Opis

Statistical Modeling and Analysis for Complex Data Problems treats some of today s more complex problems and it reflects some of the important research directions in the field. Twenty-nine authors largely from Montreal s GERAD Multi-University Research Center and who work in areas of theoretical statistics, applied statistics, probability theory, and stochastic processes present survey chapters on various theoretical and applied problems of importance and interest to researchers and students across a number of academic domains."

Spis treści

Foreword.- Contributing Authors.- Preface.- Dependence Properties of Meta-Elliptical Distributions.- The Statistical Significance of Palm Beach County.- Bayesian Functional Estimation of Hazard Rates for Randomly Right Censored Data Using Fourier Series Methods.- Conditions for the Validity of F-Ratio Tests for Treatment and Carryover Effects in Crossover Designs.- Bias in Estimating the Variance of K-Fold Cross Validation.- Effective Construction of Modified Histograms in Higher Dimensions.- On Robust Diagnostics at Individual Lags Using RA-ARX Estimators.- Bootstrap Confidence Intervals for Periodic Preventive Replacement Policies.- Statistics for Comparison of Two Independent cDNA Filter Microarrays.- Large Deviations for Interacting Processes in the Strong Topology.- Asymptotic Distribution of a Simple Linear Estimator for VARMA Models in Echolon Form.- Recent Results for Linear Time Series Models with Non Independent Innovations.- Filtering of Images for Detecting Multiple Targets Trajectories.- Optimzal Detection of Periodicities in Vector Autoregressive Models.- The Wilcoxon Signed-Rank Test for Cluster Correlated Data.

Blurb

STATISTICAL MODELING AND ANALYSIS FOR COMPLEX DATA PROBLEMS treats some of today’s more complex problems and it reflects some of the important research directions in the field. Twenty-nine authors—largely from Montreal’s GERAD Multi-University Research Center and who work in areas of theoretical statistics, applied statistics, probability theory, and stochastic processes—present survey chapters on various theoretical and applied problems of importance and interest to researchers and students across a number of academic domains. Some of the areas and topics examined in the volume are: an analysis of complex survey data, the 2000 American presidential election in Florida, data mining, estimation of uncertainty for machine learning algorithms, interacting stochastic processes, dependent data & copulas, Bayesian analysis of hazard rates, re-sampling methods in a periodic replacement problem, statistical testing in genetics and for dependent data, statistical analysis of time series analysis, theoretical and applied stochastic processes, and an efficient non linear filtering algorithm for the position detection of multiple targets.

The book examines the methods and problems from a modeling perspective and surveys the state of current research on each topic and provides direction for further research exploration of the area.