B8268 - SOCIAL RESEARCH

Academic Year 2025/2026

  • Teaching Mode: Traditional lectures
  • Campus: Bologna
  • Corso: Second cycle degree programme (LM) in Statistical Sciences (cod. 6810)

    Also valid for Second cycle degree programme (LM) in Statistical Sciences (cod. 9222)

Learning outcomes

In this course, students develop both an awareness of the range of issues considered in quantitative social research and expertise in multivariate regression analysis, with a specific focus on population studies and life course analysis. In the first part of the course, students are introduced to the logic of quantitative analysis in social and demographic research, gaining skills in multivariate statistical analysis, including multi-process modeling and unobserved heterogeneity components to address selection bias and endogeneity in regression models. The second part of the course focuses on quantitative life course analysis. The usefulness of longitudinal data and hazard models for causal analysis in the social sciences is emphasized. Starting from the key concepts of the life course approach in quantitative analysis, the course covers basic elements for organizing event-oriented data, developing multivariate models, and interpreting results. The course concludes with a discussion on possible "holistic" approaches to address life course analysis. At the end of the course, students will be able to: § assess and apply the main demographic measures; § collect data from major social and demographic surveys at an international level; § apply appropriate statistical research strategies; § critically evaluate the results of data analysis by connecting them to suitable sociodemographic theories; § deal with selection bias and endogeneity in regression modeling; § structure and autonomously conduct a research project based on the analysis of datasets related to the social sciences.

Course contents

1. Regression modelling in social research

Data sources for social and demographic research. Micro and macro approach. Causal explanation and multivariate analysis. Spurious effects. Prior and intervening variables. Regression model specification. Linear and logistic regression models. Multi-process modelling and unobserved heterogeneity components. Facing selectivity and endogeneity in regression modelling. The Heckman’s selection model.

 

2. Life Course Analysis

The powerful of longitudinal data. Causal modelling and observation plans. The relevance of the past. Data for the life course analysis. Computer programs for life course analysis.

Event history data structures. Key concepts and basic terminology. Censoring and truncation.

Nonparametric survival analysis. Life table method. Survival curves. Kaplan-Meier estimator.

Exponential hazard model. Piecewise constant exponential models. Time fixed and time-varying variables. Restructuring data for the time-varying covariates. The episode splitting. Going beyond the basic approach: developments in the EHA and other life course analysis.

A “holistic” perspective: the sequence analysis. Dissimilarity matrix and cluster analysis applied to sequences.

 

3. Key issues

During the course, the following key issues will be addressed: gender system, transition to adulthood in Western countries, union formation and dissolution, low fertility, international migration, and geographical mobility.

Readings/Bibliography

- Lesson notes, selected papers, exercises, datasets and documents (available on the VIRTUALE platform ).

- Blossfeld H-P., Golsch K., Rohwer G. (2007) Event history analysis with Stata. Mahwah (NJ): Erlbaum (chapters 1-6)

- Mills M. (2011), Introducing Survival and Event History Analysis, Sage.

Teaching methods

Class activities (30 h) include lectures, data manipulation exercises, and practical sessions on methods and models in Social Research. The course enables students to independently design and carry out a research project based on the analysis of social science data sets. As part of the class activities, students will present and discuss their research reports.

Attendance is strongly recommended to successfully complete the course.

Assessment methods

Requirements

Students should be familiar with basic knowledge in the field of statistics and computer science. A basic knowledge of STATA is suggested.

Students are required to develop a research project based on real data.

 

Assessment method (for attending students)

  • Research paper (10 pt): developed by small groups (2/3 students) and presented at the end of the course
  • EHA computer exercise (10 pt): to be made in the computer lab at the end of the course (see Calendar)
  • Final discussion (10 pt): oral discussion on the whole program and activities.

Please note that the points awarded for the Research Paper and the EHA test remain valid until the end of September. Exams and activities are not compulsory; however, a minimum total score of 18 is required to pass the course.

 

Assessment method (for non-attending students)

Oral exam (20 pt) + Research paper (10 pt). The research paper must be made individually.

Teaching tools

Online material (slides, papers, exercises, datasets, etc.).

Use of computing equipment for statistical analysis (STATA software). Authorised students can download the software and the related licence here.

Office hours

See the website of Roberto Impicciatore