Data Analysis and Applications 4

Andreas Makrides is Associate Lecturer of Statistics at the University of Central Lancashire, Cyprus (UClan) and conducted postdoctoral research at the Laboratoire de Mathématiques Raphaël Salem, Université de Rouen, France. Alex Karagrigoriou is Professor of Probability and Statistics at the University of the Aegean, Greece. He is also the faculty�s Head of Graduate Studies and Director of the in-house Laboratory of Statistics and Data Analysis. Christos H. Skiadas is former vice-Rector at the Technical University of Crete, Greece and founder of its Data Analysis and Forecasting Laboratory. He continues his research in ManLab, in the faculty�s Department of Production Engineering and Management.

• Preface xiiiPart 1 Financial Data Analysis and Methods 1Chapter 1 Forecasting Methods in Extreme Scenarios and Advanced Data Analytics for Improved Risk Estimation 3George-Jason SIOURIS, Despoina SKILOGIANNI and Alex Karagrigoriou1.1 Introduction 31.2 The low price effect and correction 61.2.1 Percentage value at risk and low price correction 91.2.2 Expected Percentage Shortfall (EPS) and Low Price Correction 121.2.3 Adjusted Evaluation Measures 141.2.4 Backtesting and Method’s Advantages 151.3 Application 171.3.1 The Alpha warrant 171.3.2 The ARTX stock 241.4 Conclusion 281.5 Acknowledgements 301.6 References 30Chapter 2 Credit Portfolio Risk Evaluation with Non-Gaussian One-factor Merton Models and its Application to CDO Pricing 33Takuya FUJII and Takayuki SHIOHAMA2.1 Introduction 332.2 Model and assumptions 362.3 Asymptotic evaluation of credit risk measures 402.4 Data analysis 442.5 Conclusion 482.6 Acknowledgements 482.7 References 48Chapter 3 Towards an Improved Credit Scoring System with Alternative Data: the Greek Case 51Panagiota GIANNOULI and Christos E. KOUNTZAKIS3.1 Introduction 513.2 Literature review: stages of credit scoring 523.3 Performance definition 533.4 Data description 543.4.1 Alternative data in credit scoring 543.4.2 Credit scoring data set 543.4.3 Data pre-processing 553.5 Models’ comparison 563.6 Out-of-time and out-of-sample validation 583.7 Conclusion 593.8 References 59Chapter 4 EM Algorithm for Estimating the Parameters of the Multivariate Stable Distribution 61Leonidas SAKALAUSKAS and Ingrida VAICIULYTE4.1 Introduction 614.2 Estimators of maximum likelihood approach 634.3 Quadrature formulas 674.4 Computer modeling 684.5 Conclusion 714.6 References 71Part 2. Statistics and Stochastic Data Analysis and Methods 75Chapter 5 Methods for Assessing Critical States of Complex Systems 77Valery ANTONOV5.1 Introduction 775.2 Heart rate variability 785.3 Time-series processing methods 805.4 Conclusion 875.5 References 88Chapter 6 Resampling Procedures for a More Reliable Extremal Index Estimation 89Dora PRATA GOMES and M. Manuela NEVES6.1 Introduction and motivation 896.2 Properties and difficulties of classical estimators 926.3 Resampling procedures in extremal index estimation 936.3.1 A simulation study of mean values and mean square error patterns of the estimators 946.3.2 A choice of δ and k: a heuristic sample path stability criterion 966.4 Some overall comments 986.5 Acknowledgements 996.6 References 99Chapter 7 Generalizations of Poisson Process in the Modeling of Random Processes Related to Road Accidents 103Franciszek GRABSKI7.1 Introduction 1037.2 Non-homogeneous Poisson process 1047.3 Model of the road accident number in Poland 1067.3.1 Estimation of model parameters 1077.3.2 Anticipation of the accident number 1087.4 Non-homogeneous compound Poisson process 1097.5 Data analysis 1137.6 Anticipation of the accident consequences 1137.7 Conclusion 1167.8 References 117Chapter 8 Dependability and Performance Analysis for a Two Unit Multi-state System with Imperfect Switch 119Vasilis P. KOUTRAS, Sonia MALEFAKI and Agapios N. PLATIS8.1 Introduction 1208.2 Description of the system under maintenance and imperfect switch 1228.3 Dependability and performance measures 1248.3.1 Transient phase 1258.3.2 Asymptotic analysis 1288.4 Optimal maintenance policy 1298.4.1 Optimal maintenance policy for maximizing system availability 1308.4.2 Optimal maintenance policy for minimizing total expected operational cost 1308.4.3 Optimal maintenance policy for multi-objective optimization problems 1318.5 Numerical results 1328.5.1 Transient and asymptotic dependability and performance 1328.5.2 Optimal asymptotic maintenance policies implemented in the transient phase 1438.6 Conclusion and future work 1478.7 Appendix 1488.8 References 152Chapter 9 Models for Time Series Whose Trend Has Local Maximum and Minimum Values 155Norio WATANABE9.1 Introduction 1559.2 Models 1569.2.1 Model 1 1569.2.2 Model 2 1589.3 Simulation 1599.4 Estimation of the piecewise linear trend 1619.5 Conclusion 1649.6 References 165Chapter 10 How to Model the Covariance Structure in a Spatial Framework: Variogram or Correlation Function? 167Giovanni PISTONE and Grazia VICARIO10.1 Introduction 16710.2 Universal Krige setup 16810.3 The variogram matrix 17010.4 Inverse variogram matrix Γ −1 17310.5 Projecting on span (1) ⊥ 17710.6 Elliptope 17910.7 Conclusion 18210.8 Acknowledgements 18210.9 References 183Chapter 11 Comparison of Stochastic Processes 185Jesús Enrique GARCÍA, Ramin GHOLIZADEH and Verónica Andrea GONZÁLEZ-LÓPEZ11.1 Introduction 18511.2 Preliminaries 18611.3 Application to linguistic data 19111.4 Conclusion 19511.5 References 196Part 3 Demographic Methods and Data Analysis 197Chapter 12 Conjoint Analysis of Gross Annual Salary Re-evaluation: Evidence from Lombardy ELECTUS Data 199Paolo MARIANI, Andrea MARLETTA and Mariangela ZENGA12.1 Introduction 19912.2 Methodology 20112.2.1 Coefficient of economic valuation 20212.3 Application and results 20412.4 Conclusion 21112.5 References 212Chapter 13 Methodology for an Optimum Health Expenditure Allocation 215George MATALLIOTAKIS13.1 Introduction 21513.2 The Greek case 21613.3 The basic table for calculations 21913.4 The health expenditure in hospitals 22113.5 Conclusion 22113.6 References 222Chapter 14 Probabilistic Models for Clinical Pathways: The Case of Chronic Patients 225Stergiani SPYROU, Anatoli KAZEKTSIDOU and Panagiotis BAMIDIS14.1 Introduction 22514.2 Models and clinical practice 22714.3 The Markov models in medical diagnoses 22814.3.1 The case of chronic patients 22914.3.2 Results 23114.4 Conclusion 23214.5 References 233Chapter 15 On Clustering Techniques for Multivariate Demographic Health Data 235Achilleas ANASTASIOU, George MAVRIDOGLOU, Petros HATZOPOULOS and Alex KARAGRIGORIOU15.1 Introduction 23515.2 Literature review 23615.3 Classification characteristics 23715.3.1 Distance measures 23815.3.2 Clustering methods 23915.4 Data analysis 24015.4.1 Data 24015.4.2 The analysis 24215.5 Conclusion 24915.6 References 249Chapter 16 Tobacco-related Mortality in Greece: The Effect of Malignant Neoplasms, Circulatory and Respiratory Diseases, 1994–2016 251Konstantinos N. ZAFEIRIS16.1 Introduction 25116.1.1 Smoking-related diseases 25316.2 Data and methods 25416.3 Results 25616.3.1 Life expectancy at birth 25616.3.2 Effects of the diseases of the circulatory system on longevity 25816.3.3 Effects of smoking-related neoplasms on longevity 26116.3.4 Effects of respiratory diseases on longevity 26516.4 Discussion and conclusion 26816.5 References 272List of Authors 277Index 281