Statistical Models and Learning Methods for Complex Data / / edited by Giuseppe Giordano, Michele La Rocca, Marcella Niglio, Marialuisa Restaino, Maurizio Vichi

• Autore: Giordano Giuseppe
• Pubblicazione: Cham : , : Springer Nature Switzerland : , : Imprint : Springer, , 2025
• Edizione: 1st ed. 2025.
• Descrizione fisica: 1 online resource (312 pages)
• Disciplina: 519.5
• Soggetto topico: Mathematical statistics - Data processing; Statistics; Data mining; Quantitative research; Statistics and Computing; Statistical Theory and Methods; Applied Statistics; Data Mining and Knowledge Discovery; Data Analysis and Big Data
• Altri autori: La RoccaMichele NiglioMarcella RestainoMarialuisa VichiMaurizio
• Nota di contenuto: - Exploring latent evolving ability in test equating and its effects on final rankings -- Hidden Markov and related discrete latent variable models An application to compositional data -- An application of Natural Language Processing Analysis on TripAdvisor Reviews -- Modelling football players field position via mixture of Gaussians with flexible weights -- Estimation Issues in Multivariate Panel Data -- Testing linearity in the single functional index model for dependent data -- A multi-step approach for streamflow classification -- Identification of misogynistic accounts on Twitter through Graph Convolutional Networks -- Topic modeling of publication activity in Hungary and Poland in the fields of economics, finance, and business -- Circular kernel classification with errors-in-variables -- Classification Trees Applied to Time Lagged Data to Improve Quality in Official Statistics -- Trimmed factorial k-means a clustering application to a cookies dataset_Farné and Camillo -- Visualization of Proximity and Role-based Embeddings in a Regional Labour Flow Network -- Bridging the Gap Investigating Correlation Clustering and Manifold Learning Connections -- Improving Performance in Neural Networks by Dendrite-Activated Connection -- Regression models with compositional regressors in case of structural zeros -- Multi-Dimensional Robinson Dissimilarities -- Composite selection criteria for the number of components of a finite mixture for ordinal data -- Clustering of Italian higher education institutions based on a destination–specific approach -- Analyzing Italian crime data using matrix-variate hidden Markov models.
• Sommario/riassunto: This book on statistical models and learning methods for complex data comprises a selection of peer-reviewed post-conference papers presented at the 14th Scientific Meeting of the Classification and Data Analysis Group of the Italian Statistical Society (CLADAG 2023), held in Salerno, Italy, September 11–13, 2023. The contributions span a variety of topics, including different approaches to clustering and classification, multidimensional data analysis, panel data, social networks, time series, statistical inference, and mixture models. These methodologies are applied to a range of empirical domains such as economics, finance, hydrology, the social sciences, education, and sports. Organized biennially by international scientific committees, the CLADAG meetings advance methodological research in multivariate statistics, with a strong focus on data analysis and classification. They facilitate the exchange of ideas in these fields and promote the dissemination of concepts, numerical methods, algorithms, and computational and applied results. Chapter "Identification of misogynistic accounts on Twitter through Graph Convolutional Networks" is available open access under a Creative Commons Attribution 4.0 International License via link.springer.com.
• Titolo autorizzato: Statistical Models and Learning Methods for Complex Data
• ISBN: 3-031-84702-4
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9911031662903321
• Lo trovi qui: Univ. Federico II
• Serie: Studies in Classification, Data Analysis, and Knowledge Organization, . 2198-3321