Statistics for Social Sciences I or a similar introductory statistics course.

Specific competences: 1. Understanding the basic concepts of statistical multivariate analysis and its applications in the social sciences. 2. Capacity to apply simple linear regression and interpret the results. 3. Capacity to apply multiple linear regression and interpret the results. 4. Capacity to apply binomial logistic regression and interpret the results. 5. Capacity to apply principal components analysis and interpret the results. 5. Capacity to apply cluster analysis and interpret the results. 7. Capacity to use effectively statistical software. Transversal competences: 1. Capacity for analysis and synthesis. 2. Capacity for mathematical and statistical modeling. 3. Problem solving. 4. Critical reasoning. 5. Oral and written communication.

Topic 1. Linear regression. 1.1. Linear regression. Introduction; simple and multiple regression; motivation; graphical data analysis; model formulation; dummy variables; parameter interpretation; examples; applications. 1.2. Fitting the model to the data; the least squares criterion; using the fitted model. 1.3. Model assumptions; inference on model parameters I: confidence intervals; inference on the response. 1.4. Inference on model parameters II: hypothesis testing; statistical significance of estimated parameters. 1.5. Assessing model fit; ANOVA. 1.6. Selection of predictor variables; multicollinearity; model diagnostics; model validation. Topic 2. Binomial logistic regression. 2.1. Motivation; model assumptions and formulation; parameter interpretation; examples; applications. 2.2. Fitting the model to the data; using the fitted model; inference on model parameters; statistical significance of estimated parameters. 2.3. Assessing model fit; selection of predictor variables; multicollinearity. Topic 3. Principal component analysis. 3.1. Motivation; formulation; variance explained; examples; applications. 3.2. Deciding how many components to keep; component scores; interpretation of components; graphical representations. Topic 4. Cluster analysis. 4.1. Motivation; k-means clustering. 4.2. Hierarchical methods; similarity measures; dendrograms. 4.3. Applications and examples.

Theory (3 ECTS). Theory classes with supporting material available in the course's web page. Practical classes (3 ECTS). Problem-solving classes. Practical classes in computer rooms. Weekly individual tutoring sessions. The teaching methodology will be eminently practical, being based on the study of diverse data sets through multivariante analysis techniques, both in the theory and practical classes, as motivation and illustration of the theory.