Data Analysis and Rationality in a Complex World (Studies in Classification, Data Analysis, and Knowledge Organization)

✍ Scribed by Theodore Chadjipadelis (editor), Berthold Lausen (editor), Angelos Markos (editor), Tae Rim Lee (editor), Angela Montanari (editor), Rebecca Nugent (editor)

• Publisher: Springer
• Year: 2021
• Tongue: English
• Leaves: 344
• Category: Library

✦ Synopsis

This volume presents the latest advances in statistics and data science, including theoretical, methodological and computational developments and practical applications related to classification and clustering, data gathering, exploratory and multivariate data analysis, statistical modeling, and knowledge discovery and seeking. It includes contributions on analyzing and interpreting large, complex and aggregated datasets, and highlights numerous applications in economics, finance, computer science, political science and education. It gathers a selection of peer-reviewed contributions presented at the 16th Conference of the International Federation of Classification Societies (IFCS 2019), which was organized by the Greek Society of Data Analysis and held in Thessaloniki, Greece, on August 26-29, 2019.

✦ Table of Contents

Preface
Contents
Contributors
PerioClust: A Simple Hierarchical Agglomerative Clustering Approach Including Constraints
1 Introduction and Motivation
2 Existing Constrained HAC Methods
3 The Proposed Clustering Method: PerioClust
3.1 A Distance-Based Approach
3.2 Resampling Strategy
4 Results and Comparison on Two Real Datasets
4.1 Archaeological Dataset: Temporal Constraints
4.2 Estuary Dataset: Geographical Constraints
5 Conclusions
References
What Was Really the Case? Party Competition in Europe at the Occasion of the 2019 European Parliament Elections
1 Introduction
2 The Context of the 2019 European Parliament Elections
3 Operationalization: Data and Method
4 Findings
5 Concluding Remarks
6 Appendix
References
A Fast Electric Vehicle Planner Using Clustering
1 Introduction
2 Problem Formulation and Base Planner
3 Clustering
4 Empirical Evaluation
5 Conclusion
References
A Generalized Coefficient of Determination for Mixtures of Regressions
1 Introduction and Background Results
2 A Deviance-Based Coefficient of Determination R2
3 A Real Data Example
4 Conclusions
References
Distance Measurement When Fuzzy Numbers Are Used. Survey of Selected Problems and Procedures
1 Introduction
2 Distance Measurement for Results in the Form of Fuzzy Numbers
3 Measurement. Linguistic Form of Determining the Values of Characteristics
4 Conclusions and Future Work
References
Performance Measures in Discrete Supervised Classification
1 Introduction
2 Performance Measures
3 Experimental Results
4 Conclusions
References
Using EVT to Assess Risk on Energy Market
1 Introduction
2 Literature Review
3 Methodology
4 Empirical Analysis
5 Conclusions
References
Measuring and Testing Mutual Dependence for Functional Data
1 Introduction
2 Functional Data
3 K=2 Case
4 K>2 Case
5 Example
5.1 Univariate Case
5.2 Multivariate Case
6 Conclusions
References
Single Imputation Via Chunk-Wise PCA
1 Introduction
2 Dealing with Missing Data in PCA
3 Chunk-Wise PCA
4 Chunk-Wise Single Imputation Via PCA
5 Application
6 Conclusion
References
Clustering Mixed-Type Data: A Benchmark Study on KAMILA and K-Prototypes
1 Introduction
2 Experimental Design and Methodology
2.1 Evaluating Clustering Performance
2.2 Simulation Design
3 Results and Discussion
4 Conclusion
References
Exploring Social Attitudes Toward the Green Infrastructure Plan of the Drama City in Greece
1 Introduction
2 Methods
3 Results
4 Conclusions
References
Spatial Perception for Structured and Unstructured Data In topological Data Analysis
1 Introduction
2 TDA Mapper
3 Application to Drug Data
3.1 Qualitative Data on Drugs
3.2 Quantitative Data on Drugs
3.3 Integration Between Qualitative and Quantitative Data
3.4 Result of the Classification
4 Summary
References
Text, Content and Data Analysis of Journal Articles: The Field of International Relations
1 Introduction
2 Corpus Context
3 Data and Methodology
4 Conclusions
References
Quantile Measures of Extreme Risk on Metals Market
1 Introduction
2 Extreme Risk
3 Hill Estimator and Its Modification
4 Empirical Study
5 Conclusions
References
Evaluation of Text Clustering Methods and Their Dataspace Embeddings: An Exploration
1 Introduction: Motivations and Goals
2 Methodology
2.1 Choice of Test Corpora
2.2 Truncating the Vocabularies
2.3 Choice of Clustering Methods
2.4 Choice of Dataspaces
2.5 Choice of Evaluation Measures
2.6 Code Implementation and Computer Efficiency
3 Evaluation Results
3.1 Partial Commonalities:
3.2 Global Commonalities
4 Conclusions and Perspectives
References
Specification of Basis Spacing for Process Convolution Gaussian Process Models
1 Introduction
2 Simulation Setup
2.1 Data Generation
2.2 Model Specification
3 Simulation Results
4 Summary
References
Estimation of Classification Rules From Partially Classified Data
1 Introduction
2 History of SSL in Statistics
3 Asymptotic Expected Error Rate of CML Approach
4 Asymptotic Relative Efficiency of ML Approach
5 Modelling Missingness for Unobserved Class Labels
6 Fractionally Supervised Classification
References
Correspondence Analysis and Kriging: Projection of Quantitative Information on the Factorial Maps
1 Introduction
2 Simple and Multiple Correspondence Analysis
3 The Kriging Method
3.1 Introduction to Kriging
3.2 Kriging Types and Modelling Tools for Interpolation
4 Application of the Proposed Method
5 Conclusions
References
Intertemporal Exploratory Analysis of E-Commerce From Greek Households from Official Statistics Data
1 Introduction
2 Methodology
3 Results
4 Conclusions
References
Benchmarking in Cluster Analysis: A Study on Spectral Clustering, DBSCAN, and K-Means
1 Introduction
2 Methodology
2.1 Benchmarking Evaluation Criteria
3 Simulated Data Sets
4 Empirical Data Sets
5 Conclusion
References
Detection of Topics and Time Series Variation in Consumer Web Communication Data
1 Introduction
2 Bayesian Networks
3 Data Preparation
4 Detection of Topics and Time Series Variation
5 Conclusion
References
Classification Through Graphical Models: Evidences From the EU-SILC Data
1 Introduction
2 Chain Graph Models
2.1 Learning Procedure
2.2 Classification
3 Application
3.1 Results
4 Conclusion
References
A Simulation Study for the Identification of Missing Data Mechanisms Using Visualisation
1 Introduction
2 Methodology
2.1 Subset Multiple Correspondence Analysis
2.2 Partitioning Around Medoids
3 Simulated Data
4 Results
5 Final Remarks
References
Triplet Clustering of One-Mode Two-Way Proximities
1 Introduction
2 Procedure for Assembling One-Mode Three-Way Proximities from One-Mode Two-Way Proximities
3 Method for Hierarchical Clustering
4 An Application
5 Discussion
References
First-Time Voters in Greece: Views and Attitudes of Youth on Europe and Democracy
1 Introduction
2 Methodology
2.1 Sample
2.2 Study Instrument
2.3 Data Analysis
3 Results
4 Discussion
References
Comparison of Hierarchical Clustering Methods for Binary Data From SSR and ISSR Molecular Markers
1 Introduction
2 Material and Methods
3 Results
4 Discussion
References
One-Way Repeated Measures ANOVA for Functional Data
1 Introduction
2 Repeated Measures ANOVA for Functional Data
2.1 Model and Test Statistics
2.2 Testing Procedures
3 Simulation Studies
3.1 Simulation Setup
3.2 Discussion on Simulation Results
4 Conclusions
References
Flexible Clustering
1 Introduction
2 Method
3 Example
References
Classification of Entrepreneurial Regimes: A Symbolic Polygonal Clustering Approach
1 Introduction
2 Polygonal Variables in Symbolic Data Analysis
3 Discussion and Conclusion
References
Multidimensional Factor and Cluster Analysis Versus Embedding-Based Learning for Personalized Supermarket Offer Recommendations
1 Introduction
2 Methods
2.1 Dataset and Data Preparation
2.2 Multiple Correspondence Analysis and Hierarchical Clustering
2.3 Personalized Prediction With Embedding Approach
3 Results
4 Conclusion
References
Motivation for Participating in the Sharing Economy: The Case of Hungary
1 Introduction
2 Sharing Economy
3 Data and Method
4 Results and Conclusions
References
Benchmarking Minimax Linkage in Hierarchical Clustering
1 Introduction
2 Benchmark Study
2.1 Evaluation Metrics
2.2 Data Sets
3 Evaluation Results
3.1 Results for True k
3.2 Results Across All k
4 Discussion and Conclusion
References
Clustering Binary Data by Application of Combinatorial Optimization Heuristics
1 Introduction
2 Clustering Binary Data
3 Using Combinatorial Optimization Heuristics
3.1 Simulated Annealing
3.2 Threshold Accepting
3.3 Tabu Search
3.4 Genetic Algorithm
3.5 Ant Colonies
4 Simulated Data
5 Results
6 Concluding Remarks
References
Classifying Users Through Keystroke Dynamics
1 Introduction
2 Related Work
3 Method
3.1 Keystroke Dynamics Dataset
3.2 Feature Extraction and Feature Selection
3.3 Experimental Procedure and Validation of Models
4 Experiments and Results
5 Conclusion
References
Technological Innovation and the Critical Raw Material Stock
1 Introduction
2 Critical Raw Materials in the World
3 Database and Methodology
4 Empirical Research
5 Summary
References
Redundancy Analysis for Binary Data Based on Logistic Responses
1 Introduction
2 RDA for Quantitative Variables
3 RDA for Binary Variables
4 Examples
4.1 Spiders Data
5 Software Note
References
Predictive Power of School Motivation Clusters in Secondary Education
1 Introduction
2 Method
2.1 Sample and Population
2.2 Measurements
2.3 Statistical Analysis Plan
3 Results
4 Discussion
References