Longitudinal and survival data analysis

Course objectives

Learning goals. Learning goal of the course is to acquire a basic knowledge of methods for the analysis of survival and longitudinal data. Knowledge and understanding. At the end of the course, the students have a basic knowledge of regression models for survival and longitudinal data Applying knowledge and understanding. Thanks to practical, computer-aided, classes, students learn how to apply regression models to observed survival and longitudinal data. Making judgements. Reviewing different estimators make students able in making judgements on observed data. Communication skills. At the ned of the course, students acquire basic notation and communication skills to be used in the context of the analysis of survival and longitudinal data. Learning skills. Students with a positive mark acquire a basic knoledge of surival and longitudinal data analysis that can be used in different empirical application fields.

Channel 1
MARCO ALFO' Lecturers' profile

Program - Frequency - Exams

Course program
First section: Longitudnal data analysis Examples Longitudinal designs Regression models for longitudinal designs Mixed effect models ML estimation for parametric mixing ML estimation for nonparametric mixing Second section: Survival data analysis Examples Basic quantities, definition Censoring and truncation nonparametric estimators in the case of RC LT data Other designs Testing statistical hypotheses on the survival funtion Proportional hazerd model Diagnostic and inference in PH model
Prerequisites
Basic knowledge of (generalized) linear models, matrix algebra, statistical inference
Books
John P. Klein and Melvin L. Moeschberger (2003). Survival Analysis: Techniques for Censored and Truncated Data, Springer, 2nd edition. Peter J. Diggle, Patrick J. Heagerty, Kung-Yee Liang, Scott L. Zeger (2002). Analysis of Longitudinal Data, Oxford University Press, 2nd edition.
Teaching mode
Attendance of teaching classes is not compulsory. The course is structured in frontal theoretical and practical lessons, for a global amount of 72 hours of teaching (9 CFU) At the end of the course, a self-assessment test will take place, to verify students' level of understanding, and review some key aspects of the program.
Frequency
Attendance of teaching classes is not compulsory.
Exam mode
The exam test aims at verifying the students' level of understanding with regards to basic topic of parametrical statistical inference, with a view towards comprehension of its basic concepts, and skills acquired in applied perspective. The final mark ranges from 18/30 to 30/30 cum laude. The assessment consists in a written exam (4 items, free text) and a viva discussion of the text. The assessment does not change when the exam is taken in remote mode. The aim is at veryfing whether the student has achieved the objectives in terms of understanding and correctly applying main inferential procedures and regression models for longitudinal and survival data
Bibliography
Hsiao, C. (2014). Analysis of Panel Data, Cambridge University Press, 3rd edition.
Lesson mode
Attendance of teaching classes is not compulsory. The course is structured in frontal theoretical and practical lessons, for a global amount of 72 hours of teaching (9 CFU) At the end of the course, a self-assessment test will take place, to verify students' level of understanding, and review some key aspects of the program.
  • Lesson code1038458
  • Academic year2024/2025
  • CourseStatistical Sciences
  • CurriculumBiostatistica
  • Year1st year
  • Semester2nd semester
  • SSDSECS-S/01
  • CFU9
  • Subject areaStatistico