Multivariate Methods for Social Researchers

About

Workshop Contents and Objectives

The goal of this workshop is to introduce tools dealing with many variables (multivariate analysis): building models with several variables and reducing complexity (data reduction). Statistical tools are only useful and meaningful when they serve a research project, based on a well-defined theoretical framework (research question, research design, hypotheses) and good quality data. The focus of this workshop is methodological, conceptual and practical, oriented towards the application of these tools to typical analysis problems in social research.

The objectives of this workshop are:

Lie sound foundations of knowledge and skills with multivariate statistical tools for participants who had an introductory course in statistics and need to go beyond basics.
Acquire practical skills with data and statistical software, as well as awareness of both the potential and shortcomings and limitations (assumptions, pitfalls) of commonly used statistical tools.
Stress the importance of embedding the use of statistical tools in a full research process, from the initial research question, to data collection and analytics, as well as reporting the results.
At the end of the workshop, active participants should be able to

Apply the appropriate statistical tools to their own research projects, within a well-designed and defined, theoretically grounded, as well as realistic (i.e. applicable) framework.
Understand and critically assess publications reporting results based on statistical techniques.

Workshop design

Lectures and exercises with a focus on group projects. At least 50% of teaching time will be allotted to practical work.

Detailed lecture plan (dayily schedule)

Day 1.
Introduction to multivariate analysis; quick review of univariate and bivariate statistics, statistical inference and concepts of empirical research in the social sciences focused on a multivariate view of basic tools.

Day 2.
Multiple linear regression; regression assumptions and diagnosis; analysis of residuals; building models.

Day 3.
Regression with categorical variables, logistic regression and related techniques.

Day 4.
Unidimensional and multidimensional scaling: Likert, Guttman scales, data reduction (Principal component analytics, factor analysis).

Day 5.
Outlook: tree models and classification; AI and statistics. Presentation of participants’ projects.

Class materials

A website will provide all materials, including slides, exercises and project related materials.

**The Summer School cannot grant credits. We only deliver a Certificate of Participation, i.e. we certify your attendance.**

If you consider using Summer School workshops to obtain credits (ECTS), you will have to investigate at your home institution (contact the person/institute responsible for your degree) to find out whether they recognise the Summer School, how many credits can be earned from a workshop/course with roughly 35 hours of teaching, no graded work, and no exams.

Make sure to investigate this matter before registering if this is important to you.

Course leader

Eugène Horber is a professor emeritus of methodology at the Department of Political Science and International relations, University of Geneva, as well as an affiliated researcher at FORS.

Target group

graduate students, doctoral researchers, early career researchers in social sciences

Prerequisites

Background in basic statistics and statistical software. You should able to perform basic statistical analyses and data transformations (recoding, variable combination) using statistical software (SPSS).

If this is not the case or you are unsure, consider the 3-day preliminary workshop Statistics with SPSS for Social Scientists mandatory for you.

Fee info