Visual Conjoint Designs

online course

Learn to master visual conjoint designs, a crucial tool for social scientists, covering design, deployment, and analysis, in this comprehensive course.

Conjoint designs have become one of the most important tools in the social scientist's toolbox today, allowing researchers to understand political preferences and attitude formation in a wide range of contexts and conditions. This course introduces you to visual conjoint designs, which build on the key concepts of traditional conjoint designs but incorporate visual rather than textual stimuli, such as social media profiles, candidate images, or real online environments. You will learn how to design a visual conjoint experiment, how to use combinatorial and randomised designs to control choice sets and attributes when relying on visual material, and how to create and deploy your own visual conjoint experiments using free and open source software.

Need to Know

We will rely on open source software at every stage of the research workflow, from the conjoint conceptualisation stage, through the design and randomisation stage, to the actual deployment and hosting of a conjoint experiment. While this course relies heavily on various js libraries, no prior knowledge of JavaScript or TypeScript is required to take the course. For data analysis, we will rely on the R programming language and the tidyverse framework, so basic knowledge of these two frameworks is helpful, but not a prerequisite.

In Depth - Key topics covered

The course is structured around the key components of the research workflow of a visual conjoint design:

Topic 1: Design of the visual conjoint framework
- Designing the attributes
- Creating visual stimuli and mimicking real online environments

Topic 2: Randomisation strategy and choice set design
- Constructing choice sets based on random designs
- Constructing choice sets based on combinatorial designs
- Constructing choice sets in an adaptive style

Topic 3: Running and deploying the conjoint experiment
- Running your visual conjoint experiment locally
- Deploying your visual conjoint experiment online
- Integration with other survey frameworks

Topic 4: Analysing the experimental data
- Effectively visualising the effects
- Relying on advanced techniques for analysing effect heterogeneity

Course leader

Julia Schulte-Cloos is Assistant Professor of Political Science at the University of Marburg. Her areas of expertise revolve around around comparative politics, political behaviour, computational social science, and reproducibility.

Target group

Social Scientists

Course aim

By the end of this course, you will have a comprehensive understanding of visual conjoint designs, their similarities and differences to traditional tabular conjoint designs and the main use cases of visual conjoint designs in the social sciences. You will understand the opportunities offered by choice-based visual conjoint experiments, recognise the requirements for conducting a visual conjoint research project, be able to design, conduct and deploy your own small-scale visual conjoint experiment, and master the skills necessary to analyse real data sets from visual conjoint experiments.

Credits info

4 EC
You can earn up to four credits for attending this course.
3 ECTS credits – Attend 100% of live sessions and engage fully with class activities.
4 ECTS credits – Attend 100% of live sessions, engage fully with class activities and complete a post-class assignment.

Fee info

GBP 492: ECPR member - check whether your institution is a member here: https://ecpr.eu/Membership/CurrentMembers
GBP 985: ECPR non-member

Scholarships

Funding applications for the 2024 ECPR Methods School summer programme are now opening for applications. Apply before mid-April 2024. For more details on funding opportunities for ECPR's other events, please visit https://ecpr.eu/Funding/Funding