Student guide Faculty of Engineering A.Y. 2008/09

Statistical Probability Methods and Stochastic Processes
Aim of the course
The uncertainty and variability inherent in industrial problems calls for students to be familiar with statistical methods and probability calculation models. The course therefore provides an introduction to probabilistic modelling and its applications for the quantitative resolution of engineering-managerial problems.
In the first part, statistical methods are illustrated with particular reference to analysis of the data, estimation of parameters and linear regression, with application examples in to the fields of logistics and managerial forecasting.
The second part covers the fundamentals of stochastic computation. The Poisson processes and Markov processes are analysed, with examples of applications to the reliable modelling of systems and to models for inventory management and sales forecasting.
The teaching method adopted is intuitive, with an emphasis on the practical applications of the various methods illustrated.
Analysis of experimental data and statistics – Mathematical analysis I.
PART I: Statistical and probabilistic methods
Fundamentals of probability theory
Multivariate probability calculation
Analysis of data:
-    Estimators
-    Method for estimating the maximum likelihood.
-    Other estimation methods.
-     Simple linear regression.
-   Multiple linear regression.
PART II: Stochastic processes
Poisson processes
Discrete Markov processes
Continuous Markov processes
Application to inventory management
Application to analysis of reliability and production
Reading list
Reference textbooks:
Borgonovo E., Metodi Probabilistici, Statistici e Processi Stocastici, Edizioni Cusl 2003
Further reading:
Kulkarni V., Modeling, Analysis, Design, and Control of Stochastic Systems (Springer Texts in Statistics),  Springer Verlag, 1999
Ross S.M., Stochastic Processes, John Wiley and Sons, 1996
Cifarelli D.M., Introduzione al Calcolo delle Probabilità, Mc-Graw Hill, 1998