Stefanini F.M., 2016, Introduzione ai metodi Bayesiani in statistica applicata
Learning Objectives
Knowledge acquired:
Basic elements of Bayesian statistics.
Linear and logistic regression models for univariate responses. Foundations of experimental design.
Competence acquired (at the end of the course);
Recognizing the nature of variables investigated during the study of a phenomenon. Evaluation of critical features characterizing a designed experiment. Selection of suitable statistical techniques to perform the analysis of experimental results.
Skills acquired (at the end of the course):
1. Assesment of raw data quality by means of suitable indices; summarizing the key features of the investigated phenomenon.
2. Data analysis using the R software.
3. Fitting of linear and logist regression models. 4. Design of experiments.
Prerequisites
Courses to be used as requirements (required and/or recommended)
Courses required: none
Courses recommmended: basic calculus.
Teaching Methods
Contact hours for:
Lectures:48
Type of Assessment
Vivo examination on subjects of lectures, laboratory assignments and homework.
Course program
How to study for the final exam, the R software. Frequencies distributions, moments, quantiles. Graphical univariate and multivariate summaries.
Probability calculus and common random variables: Bernoulli, Binomiale, Normal, Poisson, Multinomial, Beta and Gamma families. Introduction to Bayesian subjective methods. Linear and logistic regression models: estimation and testing with qualitative and/or quantitative explanatory variables.
Randomized controlled experiments: random sampling, randomization, control, replication, target and baselines variables, random blocks, full factorial designs, Balanced Incomplete Blocks designs.