Models for Data Analysis: SIS 2018, Palermo, Italy, June 20–22

✍ Scribed by Eugenio Brentari, Marcello Chiodi, Ernst-Jan Camiel Wit

• Publisher: Springer
• Year: 2023
• Tongue: English
• Leaves: 320
• Series: Springer Proceedings in Mathematics & Statistics, 402
• Category: Library

✦ Synopsis

The 49Th Scientific meeting of the Italian Statistical Society was held in June 2018 in Palermo, with more than 450 attendants. There were plenary sessions as well as specialized and solicited and contributed sessions.

This volume collects a selection of twenty extended contributions covering a wide area of applied and theoretical issues, according to the modern trends in statistical sciences. Only to mention some topics, there are papers on modern textual analysis, sensorial analysis, social inequalities, themes on demography, modern modeling of functional data and high dimensional data, and many other topics.

This volume is addressed to academics, PhD students, professionals and researchers in applied and theoretical statistical models for data analysis.

✦ Table of Contents

Organization
Preface
Contents
Environmental Vibration Data Analysis for Damage Detection on a Civil Engineering Structure
1 Introduction
2 The Statistical Method to Detect Structural Damage
3 Damage Detection: The Case of a Sicilian Highway Bridge
4 Sampling Distribution and Hypothesis Testing of Cos(θk)
5 Conclusion
References
Using Differential Geometry for Sparse High-Dimensional Risk Regression Models
1 Introduction
2 Cox Regression Model and Its Extensions
3 Geometrical Structure of a Relative Risk Regression Model
4 Extending dgLARS to Relative Risk Regression Models
5 Simulation Study
6 Application to Survival Datasets
7 Conclusions
References
Perceived Benefits and Individual Characteristics of Internationally Mobile Students: A Discrete Latent Variable Analysis
1 Introduction
2 Data on International Study Mobility
2.1 The Questionnaire
2.2 Data Description
3 Methods
3.1 The Latent Class Item Response Model
3.2 Model Selection
4 Results and Discussion
4.1 Model Specification and Student Profiles
4.2 Item Parameters
4.3 Effect of Individual Characteristics
5 Conclusions
References
Consumers’ Preferences for Coffee Consumption: A Choice Experiment Integrated with Tasting and Chemical Analyses
1 Introduction
2 Outlined Theory for the Case-Study
2.1 An Optimal Design for the Choice Experiment
2.2 The RUMs Applied for the Case-Study
3 The Case-Study
3.1 The Choice Experiment Planning
3.2 The Consumers’ Guided Tasting
4 Model Results
5 Final Remarks and Discussion
References
Urban Transformations and the Spatial Distribution of Foreign Immigrants in Messina
1 Introduction
2 Urban Activities and Migrant Settlement Patterns
3 Data and Methods
4 Results
5 Conclusions
References
Cultural Participation and Social Inequality in the Digital Age: A Multilevel Cross-National Analysis in Europe
1 Cultural Participation and Social Inequality in a Cross-National Perspective
2 Outline of the Study
3 Data
4 Methods
4.1 A Synthetic Index of Cultural Participation at European Level
4.2 The Determinants of Cultural Participation in the European Countries: A Multilevel Approach
5 Results
6 Conclusions
References
Reducing Bias of the Matching Estimator of Treatment Effect in a Nonexperimental Evaluation Procedure
1 Introduction
2 Model Specification
2.1 Assessing Bias Evaluation
3 Monte Carlo Experiment
3.1 Comparison of Matching Estimators
3.2 Comparing Simulation Results of Matching Procedures
4 Concluding Remarks
Appendix
References
Gender Gap Assessment and Inequality Decomposition
1 Introduction
2 The Dagum's Gini Index Decomposition
3 Gender Gap Analysis by Means of Inequality Decomposition
3.1 The Inequality Within Subgroups
3.2 The Inequality Between Subgroups and the Overlapping Component
3.3 The Informative Content of Subgroups Means
3.4 The Inequality Structure
4 Gender Income Inequality Among Italian Households
4.1 The Data
4.2 The Gender Gap by Subpopulations Means
4.3 The Gender Gap by Inequality Decomposition
5 Conclusions
References
Functional Linear Models for the Analysis of Similarity of Waveforms
1 Introduction
2 The Data
3 The Methodology
3.1 The Model
3.2 Analysis of Residuals Through Functional Data Depth
4 The Application
5 Results and Discussion
References
Capturing Measurement Error Bias in Volatility Forecasting by Realized GARCH Models
1 Introduction
2 A Brief Review of Realized Measures
3 The Realized GARCH Model
4 Modelling Heteroskedastic Measurement Errors and Dynamic Attenuation Bias Effects
5 The Data
6 In-sample Analysis
7 Out-of-Sample Analysis
8 Conclusion
References
Zero Inflated Bivariate Poisson Regression Models for a Sport (in)activity Data Analysis
1 Introduction
2 Motivating Example
3 Methods
3.1 Zero Inflated Univariate Poisson Model
3.2 Zero Inflated Bivariate Poisson Model
4 Data Analysis
5 Conclusion
References
Network-Based Dimensionality Reduction for Textual Datasets
1 Introduction
2 Background and Related Work
3 A Network-Based Strategy for Dimensionality Reduction
3.1 Dimensionality Reduction as a Community Detection Problem
3.2 The Proposed Strategy
4 A Case Study on COVID-19 Tweets
4.1 Dimensionality Reduction and Concepts' Identification
5 Conclusions and Final Remarks
References
Assessing the Performance of the Italian Translations of Modified MEIM, EIS and FESM Scales to Measure Ethnic Identity: A Case Study
1 Ethnic Identity: A Conceptualization
2 Measuring Ethnic Identity: A Case-Study
3 Results
3.1 The 9-Item MEIM Scale
3.2 The 7-Item EIS Scale
3.3 The FESM-1 Scale
3.4 The FESM-2 Scale
4 Conclusions
References
Towards Global Monitoring: Equating the Food Insecurity Experience Scale (FIES) and Food Insecurity Scales in Latin America
1 Introduction
2 Experience-Based Food Insecurity Scale
2.1 National and Regional Scales of Food Insecurity: ELCSA, EMSA, EBIA
2.2 The Food Insecurity Experience Scale (FIES)
3 Data and Methods
3.1 Data
3.2 Test Equating
4 Results
4.1 First Study: Equating FIES and National Scales
4.2 Second Study: Comparing Household- and Children-Referenced Item Scales
5 Conclusions
References
Position Weighted Decision Trees for Ranking Data
1 Introduction
2 Distances Between Rankings
2.1 Weighted Distances
3 A Suitable Rank Correlation Coefficient
4 Decision Trees for Preference Data
4.1 Splitting Criterion and Impurity Function for Preference Data
4.2 Rank Aggregation in the Leaves
5 Simulation Study
6 Conclusion
References
European Funds and Regional Convergence: From the European Context to the Italian Scenario
1 Introduction
2 Related Works
3 Method and Data
4 Results: The European Context
5 Results: The Italian Case
6 Discussion and Conclusions
References
A BoD Composite Indicator to Measure the Italian “Sole 24 Ore” Quality of Life
1 Introduction
2 “Il Sole 24 Ore” QoL Approach and the BOD Method
3 Comparing the Two Procedures: Results and Comments
4 Conclusions
References
Trends and Random Walks in Mortality Series
1 Introduction
2 On the Dynamics of Mortality Rates
3 The Evolution of Survivors at Age x
4 The Dynamics of Population Aged x
5 Unit Root Tests
6 Our Data
7 Unit Root Tests: Results
8 Summary and Conclusions
Appendix
References
Fuzzy and Model Based Clustering Methods: Can We Fruitfully Compare Them?
1 Introduction
2 Model-Based Clustering
2.1 Finite Mixtures of Gaussian Densities
2.2 Finite Mixtures of t Densities
2.3 Finite Mixtures of Generalised Hyperbolic Densities
3 Fuzzy Clustering
3.1 Fuzzy k-Means
3.2 The Gustafson-Kessel Variant of FkM
4 Simulation Study
4.1 Simulation Set-Up
4.2 Results
5 Final Discussion
References
An Analysis of Misclassification Rates in Rater Agreement Studies
1 Introduction
2 Definition of κ-type agreement coefficients
3 Non-parametric inferential benchmarking procedures
4 Monte Carlo Simulation
5 Conclusions
References
Author Index