Teaching

International Max Planck Research School for Population, Health and Data Science

Max Planck Institute for Demographic Research

February 2024

As part of the International Max Planck Research School for Population, Health and Data Science at the Max Planck Institute for Demographic Research, Ugofilippo Basellini and myself have taught a one-week course titled "Foundations in Statistical Demography". 

Course description from the MPIDR web-page can be found here.

Concerning the contents, we covered the following topics:

Day 1: An Introduction to Linear Model

Day 2: Binomial and Poisson distributions & Overdispersion

Day 3: Non-linear models: Discrete smoothing & P-splines 

Day 4: Non-linear models: Generalized Additive Models

Day 5: Presentation of the solutions to the exercises prepared by the students 

Organizational-wise, we prepared 4 lectures with associated 

• slides with detailed explanation of each topic

• handouts with fully reproducible R-codes

• exercises to be solved and presented by students during the Day 5 of the course

• office hours for discussing about introduced methods and approaches as well as possible solutions for the exercises

International Advanced Studies in Demography

Max Planck Institute for Demographic Research

June 2017  and May 2020

In 2017 and 2020, as part of the International Advanced Studies in Demography at the Max Planck Institute for Demographic Research, I have taught a 20-hours course titled "Smoothing Demographic Data: Flexible Models in Population Studies". 

Course description from the MPIDR web-page can be found here and twitter announcement for the second (on-line) edition of the course is available here. 

For this course, within a week, I prepared 5 lectures during the morning with associated lab-sessions in R in the afternoon (at least when in its first edition was proposed offline). Specifically I covered the following topics:

1. Introduction to Generalized Linear Model

   • Introduction to Generalized Linear Model

   • Basic linear model

   • Let’s forget about normality

   • The Iterative Weighted Least-Squares algorithm

   • Estimating Poisson model by hand

2. Discrete smoothing

   • The pursuit of smoothness

   • Penalty! (Double) Goal!

   • Optimizing the amount of smoothness

   • Smoothing histograms

   • Including exposures

3. P-splines

   • Let’s forget about linearity

   • B-splines: What’s that?

   • Penalizing the coefficients

   • Smoothing counts

   • Simple extrapolation

4. Extending P-splines

   • Dealing with more covariates

   • Smoothing spatial data

   • Tensor P-splines

   • Shape constraints

   • Calculus with smooth data

5. Introduction to Generalized Additive Models (for Location, Scale and Shape)

   • Presenting mgcv by examples

   • Presenting gamlss by examples

Ecole Nationale de la Statistique et de l’Analyse de l’Information (ENSAI)

Filière: Ingénierie statistique des territoires et de la santé

Campus de Ker Lann, Rennes

In September-October from 2013 to 2023

In 2013 the Ecole Nationale de la Statistique et de l’Analyse de l’Information (ENSAI) asked me to prepare a 18h-course in demography with particular focus on applications and techniques. This course was part of the curriculum in Ingénierie statistique des territoires et de la santé. 

I have been teaching this course since 2013 and I composed it in 6 2hr-lectures, each followed by lab-sessions of 1hr. I also prepared 2 (or 3) assignments for grading the students. Here a rough table of contents of the course:

1. Demographic accounting:

   • the balancing equation and growth rates

   • rates and person-years

   • the Lexis diagram

   • rates vs. probabilities

   • age-specific rates

   • age-standardization

   • decomposition of differences between rates

2. Life-table construction

   • a toy example

   • period life-tables

   • the issues of the ax , rate/probability conversion and open-ended interval

   • life-table in a continuous frame

   • life-table as a stationary population

3. Demographic models for aggregate data

   • parametric models over age

   • Relational models

   • Lee-Carter model and its variations

4. Smoothing methods in mortality

   • Quick Smoothing

   • Generalized Additive Model: a short overview

   • Direct Smoothing

   • P-splines

5. Fertility and reproduction

   • Period fertility rates

   • Cohort Fertility

   • Tempo effects

   • Reproduction measures

   • Coale-McNeil and Coale-Trussell models

   • Henry’s “Natural Fertility”

6. Population projection

   • Cohort component method

   • Projection matrix and age-classified model

   • Forecasting model parameters

   • The Lee-Carter model for forecasting mortality

École Nationale de la Statistique et de l'Administration Économique (ENSAE ParisTech)

3ème année DataScience

ENSAE Malakoff - Paris Saclay

March 2015, 2016, 2017, 2018, 2019

(link)

I have been involved in the course in Démographie (DES319) for the years 2014-15, 2015-16, 2016-17 and 2017-18, 2018-19 at the ENSAE ParisTech (École Nationale de la Statistique et de l'Administration Économique). Specifically I taught three classes: (1) Analysis of mortality: measures and developments, (2) Population Dynamics: an introduction, (3) Population Projection: an introduction. The course was organized by Anne Solaz (INED) and other instructors were associated: Carole Bonnet and Ariane Pailhe, always from INED.  

Here a rough table of contents of my classes:

1. Analysis of mortality: measures and developments

   • rates and person-years

   • the Lexis diagram

   • rates vs. probabilities

   • life table

   • mortality developments and determinants

2. Population Dynamics: an introduction

   • life table in a continuous framework 

   • the stationary population 

   • the stable population model

3. Population Projections: an introduction

   • Cohort Component Method

   • Matrix representation of the cohort component method

   • Forecasting with the Lee-Carter model

   • Some outcomes from projections

Ciclo de Conferencias y Curso postgrado

Consejo Superior de Investigaciones Cientificas, Sevilla. 

May 2012

The Spanish Spanish National Research Council (Consejo Superior de Investigaciones Cientificas) is regularly organizing courses and series of seminars either in their head-quarter in Madrid or in research centres around Spain. In May 2012, I was pleased to be invited for giving a course at the Institute of Statistics and Cartography of Andalusia (Instituto de Estadística y Cartografía de Andalucía) in Sevilla. In this occasion I gave three lectures with associated lab-sessions in R on the following topics:

• The Piece-Wise Constant Hazard Model

• Demographic Models for Aggregate Data

• Relational Models and Smoothing Approaches

Consejo Superior de Investigaciones Cientificas, Madrid. 

February 2010

In February 2010, I gave this intensive introductory course in R for PhD-students and researchers at the Instituto de Economía, Geografía y Demografía within the Spanish Spanish National Research Council (Consejo Superior de Investigaciones Cientificas). Students had already some basic knowledge about the software, therefore I started revising the fundamentals. I prepared handouts for each class and, during the lectures, I walked throughout them with the students. I covered the following topics:

• Revising the basic: flow-control & functions

• Enhancing your output: basic statistics & plots

• Distributions, Random Numbers & Manual Optimization

• Generalized Linear Models, a demographic perspective

• Matrix algebra and cohort component projection