Course teached as: B003958 - MODELLI STATISTICI 3-years First Cycle Degree (DM 270/04) in STATISTICS
Teaching Language
Italian
Course Content
This course deals with statistical models for the analysis of quantitative and qualitative data. The statistical methods studied are the general linear model for quantitative responses (including multiple regression, analysis of variance and analysis of covariance), binomial regression models for binary data (logistic regression ).
Marchetti, G. (2013). Introduzione ai modelli statistici, Dipartimento di Statistica, Firenze. (downloadable it from the e-learning page)
Mehmetoglu M., Tor G. J. (2018). Applied Statistics Using Stata
A Guide for the Social Sciences, SAGE Publications Ltd.
Weisberg, S. (2014). Applied Linear Regression, 4th Ed., Wiley, Hoboken NJ.
Learning Objectives
At the end of the course, the students should be able to understand the basics of statsitical modelling.
The students will be able model a real phenomenon and to fit the model on sample data in order to analyse and interpret variables relationships. The students should be able to give a correct interpretation of model parameters, to predict new values for the response variable giving the appropriate uncertainty measures.
Prerequisites
Statistics, Calculus
Teaching Methods
Lectures and lab sessions. Lab session are conducted using statistical software.
Further information
Lab session are conducted using statistical software.
Type of Assessment
Written and oral examination. The written exam includes data analysis and requires the use of statitistical software.
For the students enrolled in B027527 - INTRODUCTION TO STATISTICAL MODELLING the exam includes only the topics of PART I (see below).
Course program
PART I (6 credits). Probability and random variables, estimation, test of hypothesis and sample distributions, models for the comparison of two groups, simple linear regression,
PART II (3 credits). Likelihood based inference, the logistic linear model, the general linear regression model, model specification and goodness of fit, general linear logistic model.