This Special Issue on Statistics contains 6 invited articles presented at the 5th Stochastic Modelling Techniques and Data Analysis International Conference (SMTDA2018) (Chania, Crete,Greece, June 12–15, 2018). The SMTDAConference solicited articles, both theoretical and practical, presenting new results and having potential for solving real‐life problems. An important objective was to select articles presenting new methods for solving these problems by analyzing relevant data and leading to the advancement of the related fields.
The following articles have thus been selected for this Special Issue: Dominika Ballová, with the paper on “Detecting Long Term and Abrupt Changes of River Overflows in Slovakia,” proposes nonparametric methods and applies them to the river overflow data in Slovakia. Significant trends and change‐points in time series were detected by applying appropriate tests. Then, trend analysis is carried out.
Vladimir Anisimov and Matthew Austin discuss a “Centralized Statistical Monitoring of Clinical Trial Enrollment Performance.” They use Poissongamma enrollment model developed by Anisimov and Fedorov to model the performance of clinical centers and to detect outliers (low and high wenrolling centers) using interim enrollment data.
Ali Hayek et al. use extreme value theory (EVT) to describe statistical properties of extreme events in temperature and precipitation in their paper on “Analysis of the Extreme and Records Values for Temperature and Precipitation in Lebanon.” They use the theory of record‐breaking data to study the evolution of temperature and precipitation during 2003–2019.Appropriate predictions are then done.
Rafik Abdesselam presents “A Topological Approach of Multiple Correspondence Analysis.” He compares proximity measures and proposes a topological criterion for choosing the best association measure, adapted to the data considered. The proposed methodology is then illustrated using a real data set with conventional proximity measures for binary variables from the literature.
Emanuela Raffinetti proposes “An Extended Study to Measure Dependence with Grouped‐ordinal Variables Generated by Unobserved Non‐normal Variables.” The paper then develops a new measure that fills the gap where, in the analysis (mainly social or psychometric attitudinal scales and surveys), responses are expressed through grouped‐continuous scales.
Elena Babatsouli discusses “Estimating the Accuracy of Word‐initial Consonant Clusters in Child Speech Data.” The measure for cluster proximity (MCP), which differentiates stages in cluster development, is then compared to the proportion of clusters correct (PClC) that differentiates only correct fromincorrect consonant clusters. Children's speech samples across the whole spectrum of cluster accuracy show that the correlation between the two measures is strong and statistically significant.
Our sincere thanks go to all the authors for their contributions and the reviewers for their sincere and timely reviewwork.We also express our thanks to the Editor‐in‐Chief, Professor Narayanaswamy Balakrishnan, for accepting this Special Issue and to the Editorial Assistant, Ms. Debbie Iscoe, for her valuable support in the preparation and production of this special issue.