Methods of Statistical and Machine Learning (8 ECTS)

Distinguishing statistical learning methods as supervised and unsupervised and determining the type of statistical problems they treat, the concept of distance in Statistics, Clustering (K-means, Hierarchical clustering, Model-based clustering), Classification (LDA, QDA, K-nearest neighbors, Fisher’s discriminant analysis). Resampling methods (cross-validation, bootstrap), linear model selection and regularization (subset selection, shrinkage, dimension reduction), multinomial regression, , step functions, regression splines, tree methods, support vector machines, neural networks.

Recommended Reading

• Bartholomew D.J., Steele F., Moustaki I., Galbraithe J.I., Ανάλυση Πολυμεταβλητών Τεχνικών στις Κοινωνικές Επιστήμες, Εκδόσεις Κλειδάριθμος ΕΠΕ, 2011.
• Ιωαννίδης Δ., Αθανασιάδης Ι., Στατιστική και Μηχανική Μάθηση με την R, Εκδόσεις Τζιόλα, 2017.
• Rajaraman A., Ullman D.J., Εξόρυξη από Μεγάλα Σύνολα Δεδομένων, Εκδόσεις Νέων Τεχνολογιών, 2014.
• Sidney B., Everitt, Casella G., Fienberg, S., Ingram O., An R and S-PLUS Companion to Multivariate    Analysis, Springer-Verlag London Limited, 2005.
•  Hastie, Tibshirani and Friedman (2009) Elements of Statistical Learning, 2nd edition Springer
• James, Witten, Hastie and Tibshirani (2011) Introduction to Statistical Learning with applications in R, Springer
• B. S. Everitt, S. Landau, M. Leese, and D. Stahl (2011) Cluster Analysis, Fifth Edition, Wiley

(old title: "Multilinear Statistical Methods")

The course outline can be found here.