Edgar Acuña and Caroline Rodriguez, University of Puerto Rico, ``The Treatment of Missing Values and Its Effect on Classifier Accuracy''

Kohei Adachi, Ritsumeikan University, ``An Oblique Procrustes Technique for Simultaneously Rotating Component and Loading Matrices''

F. Afonso, University of Paris-Dauphine, Lynne Billard, University of Georgia, and Edwin Diday, University of Paris-Dauphine, ``Symbolic Linear Regression with Taxonomies''

Ulas Akkucuk and Doug Carroll, Rutgers University, ``Mapping of Nonlinear Manifolds: ISOMAP and a Version of PARAMAP''

Yasumasa Baba and Noboru Ohsumi, Institute of Statistical Mathematics, ``Chikio Hayashi and Data Science in Japan'' Chikio Hayashi was one of the leading researchers in the field of statistics and data analysis in Japan and also the pioneer of data science. Covering a wide range of statistics subjects for half a century, Hayashi continued to drive the development of data science in this country, particularly in the area of survey research and data analysis. Talking about his research achievements is talking about the progress of data science in Japan. Thus, this paper attempts to trace the footsteps of his research activities, focusing on his two important study themes: quantification methods (or named formally as quantification theory) for qualitative data and survey research. Hayashi always based his studies on observation of real phenomena maintaining his distinctive research style of ``from designing the experiments to analyzing data collected originally.'' A series of methods for analyzing qualitative data, named by social psychologist Hiroshi Akuto as Hayashi's quantification method type I, II and so on, were born out of a need for data analysis in the course of the professor's pursuit for individual research goals. The first method of the series was conceived in 1950 when Hayashi was groping for the procedures to evaluate criminal convicts for their post-release recidivism possibilities and divide them into two groups in accordance with resulting risk factors. Hayashi began his study on this subject in 1947, and in 1950 formulated a method of discriminant analysis based on multivariate categorical data which was to be named later as quantification method type II. This was followed by quantification method type IV (1951) which is now regarded as a kind of MDS (multidimensional scaling methods), quantification method type I (1952) which is a kind of multiple regression analysis of qualitative data, quantification method type III (1956) which is comparable to correspondence analysis proposed by Benzécri in 1960s, and so on. Placing a particular emphasis on sample survey, Hayashi conducted researches in a wide range of fields. His broad interest included such areas of marketing research, social survey research, and animal population assessment. In the late 1940s, Hayashi studied sample survey theory with his colleagues, and applied it to social survey. In 1953, the Institute of Statistical Mathematics (ISM) initiated a five-year interval sample survey project to study the Japanese national character. Hayashi, who played a leader in the initial project designing, has remained one of the project leaders until 1998. This project is now regarded that was contributing to the establishment of sample survey methods in Japan, and hence Hayashi is admired as the key person who enabled it to happen. Advancing his survey methodologies with interests extended to the field of international comparative survey, Hayashi was lately working on analysis of the national character of a nation by extracting its features from the findings of social surveys carried out there. One fruit born out his efforts was CLA (cultural link analysis), the cross-national studies to alternatively cast a distinctive light on the relationship among the Americans, the Japanese and Japanese-American people who embody culture of the both countries. Hayashi was proposing that this approach is applied to compare among other counties in Asia and Europe as the means to interpret complicated interrelations among many nations. After his death, his successors are continuing to advance his achievements in these studies. In advocating data science, Hayashi of late years was intending to break through traditional statistics and make an effort to find a new dimension with much broader perspective.

Kaddour Bachar, Ecole Supérieure des Sciences Commerciales d'Angers, and Israël Lerman, University of Rennes 1, ``Fixing Parameters in the Constrained Hierarchical Classification Method: Application to Digital Image Segmentation''

Daniel Baier, Brandenburg University of Technology Cottbus, ``Pharmaceutical eDetailing and Market Sementation''

Simona Balbi and Emilo Di Meglio, University of Naples, ``Contributions of Textual Data Analysis to Text Retrieval''

Xinli Bao and Hamparsum Bozdogan, University of Tennessee at Knoxville, ``Subsetting Kernel Regression Models Using Genetic Algorithm and the Information Measure of Complexity''

Jean-Pierre Barthélemy, GET-ENST Bretagne, ``Binary Clustering and Boolean Dissimilarities''

Vladimir Batagelj and Matjaz Zaversnik, University of Ljubljana, ``Islands, an Approach to Clustering in Large Networks''

François Bavaud, University of Lausanne, ``Generalized Factor Analysis for Contingency Tables''

Mónica Bécue, Universitat Politècnica de Catalunya, J. Pagès, Institut Nationales Supérieur, and Campo-Elías Pardo, Universidad Nacional de Colombia, ``Analysis of Cross-Language Open-Ended Questions Through MFACT''

Halima Bensmail and Hamparsum Bozdogan, University of Tennessee, ``Bayesian Unsupervised Clustering for Mixed Data with Missing Observations''

Patrice Bertrand, GET-ENST Bretagne, and Ghazi Bel Mufti, ESSEC, ``Loevinger's Measures of Rule Quantity for Assessing Cluster Stability''

Lynne Billard, University of Georgia, ``Symbolic Data Analysis: An Overview of Principles and Some Descriptive Statistics''

David Birnbaum, University of Pittsburgh, and David Dubin, University of Illinois at Urbana-Champaign, ``Measuring Similarity in the Contents of Medieval Miscellany Manuscripts''

Hans-Hermann Bock, University of Aachen, ``Classification in the Life Span of Chikio Hayashi''

Nicholas I. Bohnen, Marius Buliga, and Gregory M. Constantine, University of Pittsburgh, ``Classifying the State of Parkinsonism by Using Electronic Force Platform Measures of Balance''

Kathy Bogie, Jiayang Sun, and Xiaofeng Wang, Case Western University, ``Mining Huge-p-Small-n Data and New Image Registration Procedures''

Stefan Born, Liebig University, and Lars Schmidt-Thieme, University of Freiburg ``Optimal Discretization of Quantitative Attributes for Association Rules''

Helena Brás Silva, Paula Brito, and Joaquim Costa, University of Porto, ``Clustering and Validation Using Graph Theory: Application to Data Sets with Numerical and Categorical Values''

Matevz Bren, University of Maribor, and Vladimir Batagelj, University of Ljubljana, ``Compositional Data Analysis with R''

- operations on compositions: perturbation and power multiplication, subcomposition with or without residuals, centering of the data, solving perurbation equations, computing Aitchison's, Euclidean, Bhattacharyya distances, compositional Kullback-Leibler divergence, and so forth
- graphical presentation of compositions in ternary diagrams and tetrahedrons with additional features: barycenter, geometric mean of the data set, the percentiles lines, marking and coloring of subsets of the data set, theirs geometric means, notation of individual data in the set, and so forth.

François Brucker, GET-ENST Bretagne, ``Bijection Between Dissimilarities and Binary Realizations''

Gilles Celeux, INRIA, ``Choosing a Model for Purposes of Classification''

Seong-San Chae, Daejeon University, Chansoo Kim, and William D. Warde, Oklahoma State University, ``Cluster Analysis Using Robust Estimators''

Anil Chaturvedi, Capital One Services, J. Douglas Carroll, Rutgers University, and Vicki Caxsrtwright, Capital One Services, ``A Three-Way, Three-Mode Hybrid Factor/Components Analysis Model''

Marie Chavent, University of Bordeaux, ``A Hausdorff Distance Between Hyper-Rectangles for Clustering Interval Data''

Chih-Chou Chiu, National Taipei University of Technology, and Tian-Shyug Lee, Fu-Jen Catholic University, ``Integrating Classification and Regression Trees with Multivariate Adaptive Regression Splines in Mining Customer Credit Data''

C. Cifaelli and L. Nieddu, University of Rome, ``An Iterative k-Means-Like Algorithm for Statistical Face Recognition''

Gilles Clermont, Carson Chow, Greg Constantine, et al., University of Pittsburgh, ``Mathematical Modeling of Acute Inflammation''

Kevin Coakley, National Institute of Standards and Technology, ``A Classification Problem in Neutrino Physics''

Brieuc Connan-Guez, INRIA-Rocquencourt, and Frabrice Rossi, University of Paris IX-Dauphine, ``Phoneme Discrimination with Functional Multi-Layer Perceptrons''

Gregory Constantine, University of Pittsburgh, ``A Multidimensional Parameter Estimation Algorithm Based on Optimal Linear Codes''

Raphaël Couturier, LIFC-IUT Belfort-Montbéliard, Régis Gras, and F. Guillet, École Polytechnique de l'Université de Nantes, ``Reducing the Number of Variables Using Implicative Analysis''

Di Cook, Iowa State University, ``Visualizing Class and Cluster Structure beyond 3D''

Marc Csernel, INRIA, Francisco de A. T. Carvalho, Universidade Federal de Pernambuco, and Yves Lechevallier, INRIA, ``Partitioning of Constrained Symbolic Data''

Guy Cucumel, Université du Québec à Montréal, ``Average Consensus and -consensus: Comparison of Two Consensus Methods for Ultrametric Trees''

Ana Lorga da Silva, Universidade Lusofona de Humanidades e Tecnologias, G. Saporta, CNAM, and H. Bacelar-Nicolau, University of Lisbon, ``Missing Data and Imputation Methods in Partition of Variables''

Francisco de A. T. Carvalho, Universidade Federal de Pernambuco, Yves Lechevallier, INRIA-Rocquencourt, Renata M. C. R. de Souza, Cidade Universitaria-Brazil, ``A Dynamic Clustering Algorithm Based on -Distances for Quantitative Data''

Stefano De Cantis and Antonino Oliveri, University of Palermo, ``An Overview of Collapsibility''

Sérgio R. de M. Queiroz and Francisco A. T. de Carvalho, Universidade Federal de Pernambuco, ``A Symbolic Model-Based Approach for Making Collaborative Group Recommendations''

Mark de Rooij, Leiden University, ``Scaling the Odds''

Renata M. C. R. de Souza, Cidade Universitaria-Brazil, Francisco A. T. de Carvalho, Universidade Federal de Pernambuco, Camilo P. Tenório, and Yves Lechevallier, INRIA-Rocquencourt, ``Dynamic Clustering Methods for Interval Data Based on Mahalanobis Distances''

Reinhold Decker, University of Bielefeld ``Self-Controlled Growing Neural Networks and Their Application to Pattern Representation in Data Analysis''

Markus Demleitner, University of Heidelberg, Michael Kurtz, Harvard University, et al., ``Automated Resolution of Noisy Bibliographic References''

José G. Dias, Instituto Superior de Ciências do Trabalho e da Empresa, ``Controlling the Level of Separation of Components in Monte Carlo Studies of Latent Class Models''

Edwin Diday, University of Paris IX-Dauphine, ``Introduction to Spatial Classification''

Arta Doci and Peter Bryant, University of Colorado at Denver, ``An MDL Criterion for k-Means Clustering''

Pedro Domingos, University of Washington, ``A General Framework for Mining Massive Data Streams''