Ficha

Versión en español

Course: 2018/2019

Advanced Statistical Data Analysis

(17467)

Study: Bachelor in Management of Information and Digital Contents (340)

Coordinating teacher: CABRAS , STEFANO

Department assigned to the subject: Department of Statistics

Type: Compulsory

ECTS Credits: 6.0 ECTS

Course: 4º

Semester: 1º

Competences and skills that will be acquired and learning results. Further information on this link

SPECIFIC SKILLS and COMPETENCES 1. To know and use advanced statistical techniques, with last generation software support. 2. To extract and analyze information from large data sets. TRANSVERSAL SKILLS and COMPETENCES 1. Ability of information analysis and synthesis. 2. Modelization and resolution of practical problems in Data Mining. 3. Oral and written communication skills.

Description of contents: programme

1. Statistical problems for multivariate data: interpretation versus prediction. 2. Interpretation by means of visual representation methods and Cluster analysis 2.1 Multidimensional Scaling. 2.2 Biplots. 2.3 Perceptual Mappings. 2.4. Cluster Analysis. Hierarchical Methods, k-means and mixture models. 2.4.1 Bottom up hierarchical clustering algorithms. 2.4.2 k-means and related algorithms. 3. Prediction of a random outcome: Parametric and non-parametric regression methods. 3.1 Linear and quadratic discriminant analysis. 3.2 Regression for quantitative and categorical data. 3.3 Regression trees and Random Forests 4. Text Mining. 4.1 Main concepts. 4.2 Word clouds. 4.3 Term by document matrix.

Learning activities and methodology

14 Theoretical support materials available on the Web, and 14 sessions based on problem-solving sessions and practical computing. No group tutorials except during the last week.

Assessment System

60% of the final grade will be achieved by a final examination for assessing the knowledge acquired. A minimum of 4 points (out of 10) is required in the final exam. The remaining 40% is obtained by two midterm exams (15%+20%) and the compulsory tasks assigned in the computational labs (5%). Theoretical questions as well as queries on computational laboratories can be asked in the exams.

% end-of-term-examination 60
% of continuous assessment (assigments, laboratory, practicals...) 40

Basic Bibliography

E. Alpaydin. Introduction to Machine Learning, 2nd Edition. MIT Press. 2010
T. Hastie, R. Tibshirani, J. Friedman. Elements of Statistical Learning, 2d Ed. Springer. 2009

The course syllabus and the academic weekly planning may change due academic events or other reasons.