Nonparametric Statistical Inference with an Emphasis on Information-Theoretic Methods

• Autore: Mielniczuk Jan
• Pubblicazione: MDPI - Multidisciplinary Digital Publishing Institute, 2022
• Descrizione fisica: 1 online resource (226 p.)
• Soggetto topico: History of engineering and technology; Mechanical engineering and materials; Technology: general issues
• Soggetto non controllato: adaptive splines; archimedean copula; B-splines; change points; CIFE; CMI; conditional infomax feature extraction; conditional mutual information; consistency; consistent selection; entropy; estimation; extreme-value copula; gaussian mixture; generalized information criterion; generative tree model; high-dimensional regression; high-dimensional time series; influence functions; information measures; information theory; JMI; joint mutual information criterion; kernel estimation; learning systems; loss function; Markov blanket; maximum likelihood estimation; minimum distance estimation; misclassification risk; misspecification; model misspecification; multivariate analysis; n/a; network estimation; nonparametric variable selection criteria; nonstationarity; parameter estimation; penalized estimation; prediction methods; privacy; random predictors; right-censored data; robustness; semiparametric regression; statistical learning theory; subgaussianity; supervised classification; synthetic data transformation; tail dependency; time series; variable selection consistency
• Persona (resp. second.): MielniczukJan
• Sommario/riassunto: This book addresses contemporary statistical inference issues when no or minimal assumptions on the nature of studied phenomenon are imposed. Information theory methods play an important role in such scenarios. The approaches discussed include various high-dimensional regression problems, time series and dependence analyses.
• Titolo autorizzato: Nonparametric Statistical Inference with an Emphasis on Information-Theoretic Methods
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910576873203321
• Lo trovi qui: Univ. Federico II