Universidad de Jaén

1. Experimental design . Importance of a good design. Hypothesis and predictions. Experimental manipulation versus natural variation. Variation between individuals and replication. Examples of experimental design. Data, observations and variables.
2. Exploratory data analysis . Assumptions of parametric linear models. Outliers,  transformation and standardizations.  Censored and missing data
3. Comparing groups or treatments. Types of Linear Models. Regression. Analysis of variance. Generalized linear models. Analyzing frequencies.

4. Introduction to multivariate analyses . Multiple regression. Multivariate analysis of variance (MANOVA). Ordination and cluster analysis. Principal components analysis. Graphical representation and data visualization.

5. Correspondence analysis. Canonical analysis. Discriminant analysis. Graphical representation and data visualization.

6. Distance matrices . Tests associated to the relationships between distance matrices : Mantel's Test, Partial Mantel's Test. The problems of Mantel's test. db-RDA analysis. Non-metric multidimensional scaling. Graphical representation and data visualization.

7. Introduction to geostatistics . Regionalized variable theory . Stochastic models of geological variables. Stationary models. Models with drift.

8. Variogram concept: structural analysis . Variogram properties. Estimation of the experimental variogram. Identification of spatial anisotropies. Theoretical variograms models. Adjustment of a theoretical model to an experimental variogram

9. Spatial interpolation by kriging . Main estimation methods by kriging: stationary and non-stationary variables.

10. Applications of geostatistics to environmental variables.

11. Introduction to Data Mining . Data mining. Relationship of DM with other disciplines. Phases of Knowledge Discovery in Databases. Challenges for Data Mining. Introduction to the use of RapidMiner software

12. Attributes selection. Phases of data analysis. Taxonomy of attributes selection methods. Attribute transformation

13. Data Mining Techniques. Typology of Data Mining Techniques. Taxonomy of Data Mining Techniques. Descriptive methods Predictive methods. Analysis of geo-environmental data with RapidMiner

For a better understanding of the concepts, the whole teaching will occur in the computer classroom. In this way, each theoretical concept will be immediately supported with practical exercises performing by means of different softwares: PAST, R-Studio, SPSS, Stat-graphics, EXCEL, RapidMiner, etc.

Students with special educational needs should contact the Student Attention Service (Servicio de Atención y Ayudas al Estudiante) in order to receive the appropriate academic support

The theoretical contents will be evaluated through an objective test (30%). The practical contents will be evaluated through a report with the exercises and statistical analyses started by the student in the classroom and completed with their subsequent autonomous work (70%).