Install the app
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Menu
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Date: Monday 22 – Friday 26 July 2024
Time: 09:30 – 12:30 CEST
This course will provide you with a highly interactive online teaching and learning environment, using state of the art online pedagogical tools. It is designed for a demanding audience (researchers, professional analysts, advanced students) and capped at a maximum of 16 participants so that the instructor can cater to the specific needs of each individual.
The course offers an introduction to the main statistical techniques used to analyse cross-national comparative data analysis, particularly survey data. This course highlights the most important methods of quantitative analysis in the social sciences but revisits them from the perspective of comparing the statistical estimates between countries.
The central enquiry revolves around how different statistical methods treat the ‘country effect’ and identify it: how statistical models (linear regression, logit models, multilevel regression models), scaling techniques of data reduction methods (PCA analysis for instance) test for the ‘invariance’ of the relationship between variables across countries.
The course seeks to address a couple of seemingly straightforward questions, that unearth methodological intricacies far beyond initial expectations: Can we feasibly compare coefficient values derived from primary statistical methods in political science across different countries? What are the primary pitfalls and viable resolutions within this pursuit?
The objective of a statistical analysis between countries is, in fact, to determine whether the variance between countries is greater than the variance within each country. To do this, most researchers compare the values of the coefficients (for example the coefficients of regression models, indicators of goodness of fit). However, they often do so empirically without taking a certain number of methodological precautions (for example, the fact that the sample size is not the same, or that the residuals are not distributed the same). The objective of the course is thus to teach simple but efficient methods to avoid falling into certain traps of comparative analysis using quantitative techniques.
The course has also two pedagogical focal points:
3 ECTS credits awarded for engaging fully in class activities.
1 additional ECTS credit awarded for completing a post-course assignment.
Bruno Cautrès is attached to CEVIPOF – Centre de recherches politiques de Sciences Po (Paris), at the Fondation Nationale des Sciences Politiques in Paris.
He is a senior CNRS research fellow with interests in voting behaviour, political attitudes and behaviours, comparative survey research and quantitative techniques.
Bruno is involved in a variety of projects, including the European Social Survey, European Values Studies, International Social Survey Programme and European elections studies; and he participates in the development of elections studies in France. His current research programme concerns political trust and attitudes to democracy in France.
The course consists of five sessions, organised into four main topics.
In this topic, you will review substantial and methodological issues in multivariate statistical analysis for comparing countries, particularly what is a 'country effect' and how this translates in statistical terms. You will also engage in very simple recalls using descriptive and bivariate techniques applied to 'country effects' problems.
In this topic, you will learn how regression methods respond to a much more complex problem than commonly acknowledged: How can we compare the values of estimated parameters, goodness of fit statistics, and statistical tests between countries? Notably, this varies significantly for linear regression and logistic regression. There’s even a debate over whether we can compare logit coefficients between countries directly. What strategies can we employ to navigate this challenge?
In this topic, you will learn how data reduction techniques such as principal components (and more generally scaling techniques) respond to the main question of the course, a seemingly simple question but in fact much more complex: Can we directly compare the values of the coefficients of a PCA type factor analysis obtained between different countries?You will discover that researchers have proposed interesting technical solutions to compare factor loadings (Procruste rotations, Tucker coefficient for example). But what are the limits of these methods, and can we go further in the comparison between countries? What steps should we take?
In this topic, you will learn that regression analysis of harmonised data from multiple countries (like the ESS, Eurobarometers, Share) in which individual-level responses are modeled as a function of both individual-level and country-level characteristics, the so-called ‘multilevel models’ or ‘hierarchical models’ are among the most popular of quantitative approaches. Is this the best way to approach cross-national comparisons and how do these methods deal with comparing estimated coefficients? What are the limitations? Can we apply these techniques to a small number of countries?
Live classes will be held daily for three hours on Zoom, allowing you to interact with both the instructor and other participants in real-time.
The course is designed to exploit the interactive capabilities of online technology, combining annotated readings, short pre-recorded lectures, and live group work. It combines pre-class activities and live/online interaction. You will be given annotated and interactive readings which we will discuss ahead of the course.
You should have completed the readings and watched the pre-recorded lectures on the key topics. The pre-recorded lectures take two forms: a methodological presentation and an illustration, through a published text or a data analysis, explained in plain English. The main tables or graphics will serve as key elements to understand the substantive issues of the methods.
The instructor will conduct live Q&A sessions and offer designated office hours for one-to-one consultations.
You must have some introductory familiarity with basic descriptive statistics, statistical inference and some basics about regression models. If you are not, take the course Introduction to Inferential Statistics before you sign up for this one.
This course description may be subject to subsequent adaptations (e.g. taking into account new developments in the field, participant demands, group size, etc.). Registered participants will be informed at the time of change.
By registering for this course, you confirm that you possess the knowledge required to follow it. The instructor will not teach these prerequisite items. If in doubt, please contact us before registering.