Exploratory Data Analysis in Empirical Research: Proceedings of the 25th Annual Conference of the Gesellschaft Für Klassifikation E.V., University of

ISBN-13: 9783540441830 / Angielski / Miękka / 2002 / 536 str.

R. F. Nagaev;Gesellschaft F Ur Klassifikation; O. Opitz

Opis

Facing rapidly growing challenges in empirical research, this volume presents a selection of new methods and approaches in the field of Exploratory Data Analysis. The interested reader will find numerous ideas and examples for cross disciplinary applications of classification and data analysis methods in fields such as data and web mining, medicine and biological sciences as well as marketing, finance and management sciences.

Spis treści

1: Classification, Data Analysis and Statistics.- Sliced Inverse Regression for High-dimensional Time Series.- Symbolic Clustering of Constrained Probabilistic Data.- On Memory Requirement with Normal Symbolic Form.- On the Roles of Galois Connections in Classification.- Mining Sets of Time Series: Description of Time Points.- Spatial Smoothing with Robust Priors in Functional MRI.- Clustering in the Presence of Outliers.- Two Models of Random Intersection Graphs for Classification.- Classification Techniques based on Methods of Computational Intelligence.- Constrained Correspondence Analysis for Seriation in Archaeology Applied to Sagalassos Ceramic Tablewares.- The Moment Preservation Method of Cluster Analysis.- On The General Distance Measure.- Tests for One-dimensional Nearest Neighbors Clusters.- Integration of Cluster Analysis and Visualization Techniques for Visual Data Analysis.- Bayesian Space-time Analysis of Health Insurance Data.- On Clustering by Mixture Models.- Using Additive Conjoint Measurement in Analysis of Social Network Data.- Bayesian Latent Class Metric Conjoint Analysis — A Case Study from the Austrian Mineral Water Market.- Diagnostics in Multivariate Data Analysis: Sensitivity Analysis for Principal Components and Canonical Correlations.- Classification of Natural Languages by Word Ordering Rule.- Combining Mental Fit and Data Fit for Classification Rule Selection.- Bayesian Analysis of Econometric Models for Count Data: A Survey.- k-Means Clustering with Outlier Detection, Mixed Variables and Missing Values.- 2: Web Mining, Data Mining and Computer Science.- Repeat-buying Theory and its Application for Recommender Services.- Joker — Visualization of an Object Model for a Cost Accounting Educational Software.- Data Preparation in Large Real-world Data Mining Projects: Methods for Imputing Missing Values.- Clustering of Document Collections to Support Interactive Text Exploration.- Web Usage Mining — Languages and Algorithms.- Thesaurus Migration in Practice.- Relational Clustering for the Analysis of Internet Newsgroups.- The Theory of On-line Learning — A Statistical Physics Approach.- A Framework for Web Usage Mining on Anonymous Logfile Data.- 3: Medicine, Biological Sciences and Health.- Knee Replacement Surgery and Learning Effects — Data Evidence from a German Hospital.- Self-organizing Maps and its Applications in Sleep Apnea Research and Molecular Genetics.- Automated Classification of Optic Nerve Head Topography Images for Glaucoma Screening.- Comparing Split Criteria for Constructing Survival Trees.- A Type of Bayesian Small Area Estimation for the Analysis of Cancer Mortality Data.- DEA-Benchmarks for Austrian Physicians.- Data Mining Tools for Quality Management in Health Care.- The Effects of Simultaneous Misclassification on the Attributable Risk.- Statistical Genetics — Present and Future.- 4: Marketing, Finance and Management Science.- Market Simulation Using Bayesian Procedures in Conjoint Analysis.- Value Based Benchmarking and Market Partitioning.- Optimization of Corporate Reorganization Portfolios based on a Genetic Algorithm.- Key Success Factors in City Marketing — Some Empirical Evidence.- From Credit Scores to Stable Default Probabilities: A Model Based Approach.- Dimensions of Credit Risk.- Cognitive Organization of Person Attributes: Measurement Procedures and Statistical Models.- Manufacturing Branches in Poland — A Classification Attempt.- Market-Segments of Automotive Brands: Letting Multivariate Analyses Reveal Additional Insights.- Sequence Mining in Marketing.- Portfolio Management Using Multivariate Time Series Forecasts.- Value-at-Risk for Financial Assets Determined by Moment Estimators of the Tail Index.- Keywords.- Authors.

O autorze

PD Dr. Manfred Schwaiger ist Oberassistent am Lehrstuhl für Mathematische Methoden der Wirtschaftswissenschaften der Universität Augsburg.