Data Analysis and Applications: Clustering and Regression, Modeling-estimating, Forecasting and Data Mining

Cover
Half-Title Page
Title Page
Copyright Page
Contents
Preface
Introduction: 50 Years of Data Analysis: From Exploratory Data Analysis to Predictive Modeling and Machine Learning
	I.1. The revolt against mathematical statistics
	I.2. EDA and unsupervised methods for dimension reduction
		I.2.1. The time of syntheses
		I.2.2. The time of clusterwise methods
		I.2.3. Extensions to new types of data
		I.2.4. Nonlinear data analysis
		I.2.5. The time of sparse methods
	I.3. Predictive modeling
		I.3.1. Paradigms and paradoxes
		I.3.2. From statistical learning theory to empirical validation
		I.3.3. Challenges
	I.4. Conclusion
	I.5. References
PART 1: Clustering and Regression
1. Cluster Validation by Measurement of Clustering Characteristics Relevant to the User
	1.1. Introduction
	1.2. General notation
	1.3. Aspects of cluster validity
		1.3.1. Small within-cluster dissimilarities
		1.3.2. Between-cluster separation
		1.3.3. Representation of objects by centroids
		1.3.4. Representation of dissimilarity structure by clustering
		1.3.5. Small within-cluster gaps
		1.3.6. Density modes and valleys
		1.3.7. Uniform within-cluster density
		1.3.8. Entropy
		1.3.9. Parsimony
		1.3.10. Similarity to homogeneous distributional shapes
		1.3.11. Stability
		1.3.12. Further Aspects
	1.4. Aggregation of indexes
	1.5. Random clusterings for calibrating indexes
		1.5.1. Stupid K-centroids clustering
		1.5.2. Stupid nearest neighbors clustering
		1.5.3. Calibration
	1.6. Examples
		1.6.1. Artificial data set
		1.6.2. Tetragonula bees data
	1.7. Conclusion
	1.8. Acknowledgment
	1.9. References
2. Histogram-Based Clustering of Sensor Network Data
	2.1. Introduction
	2.2. Time series data stream clustering
		2.2.1. Local clustering of histogram data
		2.2.2. Online proximity matrix updating
		2.2.3. Off-line partitioning through the dynamic clustering algorithm for dissimilarity tables
	2.3. Results on real data
	2.4. Conclusions
	2.5. References
3. The Flexible Beta Regression Model
	3.1. Introduction
	3.2. The FB distribution
		3.2.1. The beta distribution
		3.2.2. The FB distribution
		3.2.3. Reparameterization of the FB
	3.3. The FB regression model
	3.4. Bayesian inference
	3.5. Illustrative application
	3.6. Conclusion
	3.7. References
4. S-weighted Instrumental Variables
	4.1. Summarizing the previous relevant results
	4.2. The notations, framework, conditions and main tool
	4.3. S-weighted estimator and its consistency
	4.4. S-weighted instrumental variables and their consistency
	4.5. Patterns of results of simulations
		4.5.1. Generating the data
		4.5.2. Reporting the results
	4.6. Acknowledgment
	4.7. References
PART 2: Models and Modeling
5. Grouping Property and Decomposition of Explained Variance in Linear Regression
	5.1. Introduction
	5.2. CAR scores
		5.2.1. Definition and estimators
		5.2.2. Historical criticism of the CAR scores
	5.3. Variance decomposition methods and SVD
	5.4. Grouping property of variance decomposition methods
		5.4.1. Analysis of grouping property for CAR scores
		5.4.2. Demonstration with two predictors
		5.4.3. Analysis of grouping property using SVD
		5.4.4. Application to the diabetes data set
	5.5. Conclusions
	5.6. References
6. On GARCH Models with Temporary Structural Changes
	6.1. Introduction
	6.2. The model
		6.2.1. Trend model
		6.2.2. Intervention GARCH model
	6.3. Identification
	6.4. Simulation
		6.4.1. Simulation on trend model
		6.4.2. Simulation on intervention trend model
	6.5. Application
	6.6. Concluding remarks
	6.7. References
7. A Note on the Linear Approximation of TAR Models
	7.1. Introduction
	7.2. Linear representations and linear approximations of nonlinear models
	7.3. Linear approximation of the TAR model
	7.4. References
8. An Approximation of Social Well-Being Evaluation Using Structural Equation Modeling
	8.1. Introduction
	8.2. Wellness
	8.3. Social welfare
	8.4. Methodology
	8.5. Results
	8.6. Discussion
	8.7. Conclusions
	8.8. References
9. An SEM Approach to Modeling Housing Values
	9.1. Introduction
	9.2. Data
	9.3. Analysis
	9.4. Conclusions
	9.5. References
10. Evaluation of Stopping Criteria for Ranks in Solving Linear Systems
	10.1. Introduction
	10.2. Methods
		10.2.1. Preliminaries
		10.2.2. Iterative methods
	10.3. Formulation of linear systems
	10.4. Stopping criteria
	10.5. Numerical experimentation of stopping criteria
		10.5.1. Convergence of stopping criterion
		10.5.2. Quantiles
		10.5.3. Kendall correlation coefficient as stopping criterion
	10.6. Conclusions
	10.7. Acknowledgments
	10.8. References
11. Estimation of a Two-Variable Second- Degree Polynomial via Sampling
	11.1. Introduction
	11.2. Proposed method
		11.2.1. First restriction
		11.2.2. Second restriction
		11.2.3. Third restriction
		11.2.4. Fourth restriction
		11.2.5. Fifth restriction
		11.2.6. Coefficient estimates
	11.3. Experimental approaches
		11.3.1. Experiment A
		11.3.2. Experiment B
	11.4. Conclusions
	11.5. References
PART 3: Estimators, Forecasting and Data Mining
12. Displaying Empirical Distributions of Conditional Quantile Estimates: An Application of Symbolic Data Analysis to the Cost Allocation Problem in Agriculture
	12.1. Conceptual framework and methodological aspects of cost allocation
	12.2. The empirical model of specific production cost estimates
	12.3. The conditional quantile estimation
	12.4. Symbolic analyses of the empirical distributions of specific costs
	12.5. The visualization and the analysis of econometric results
	12.6. Conclusion
	12.7. Acknowledgments
	12.8. References
13. Frost Prediction in Apple Orchards Based upon Time Series Models
	13.1. Introduction
	13.2. Weather database
	13.3. ARIMA forecast model
		13.3.1. Stationarity and differencing
		13.3.2. Non-seasonal ARIMA models
	13.4. Model building
		13.4.1. ARIMA and LR models
		13.4.2. Binary classification of the frost data
		13.4.3. Training and test set
	13.5. Evaluation
	13.6. ARIMA model selection
	13.7. Conclusions
	13.8. Acknowledgments
	13.9. References
14. Efficiency Evaluation of Multiple-Choice Questions and Exams
	14.1. Introduction
	14.2. Exam efficiency evaluation
		14.2.1. Efficiency measures and efficiency weighted grades
		14.2.2. Iterative execution
		14.2.3. Postprocessing
	14.3. Real-life experiments and results
	14.4. Conclusions
	14.5. References
15. Methods of Modeling and Estimation in Mortality
	15.1. Introduction
	15.2. The appearance of life tables
	15.3. On the law of mortality
	15.4. Mortality and health
	15.5. An advanced health state function form
	15.6. Epilogue
	15.7. References
16. An Application of Data Mining Methods to the Analysis of Bank Customer Profitability and Buying Behavior
	16.1. Introduction
	16.2. Data set
	16.3. Short-term forecasting of customer profitability
	16.4. Churn prediction
	16.5. Next-product-to-buy
	16.6. Conclusions and future research
	16.7. References
List of Authors
Index