LFU:online

Estimating causal effects is a central aim of quantitative empirical analysis in social sciences. Recently, Conjoint Analysis and Choice-Based Conjoint Experiments have gained interest among social scientists to understand and predict people's preferences in a multi-dimensional and multi-choice environment. This course offers and applied introduction to Choice-Based Conjoint, along with hands-on experience in lab sessions.

By the end of the course, you will:

1. Have a basic understanding of the structure, logical underpinnings, basic notions and analytical goals of conjoint analysis.
2. Identify areas of application where conjoint analysis could be successfully implemented.
3. Critically evaluate conjoint experiment applications and understand the advantages/disadvantages compared to more traditional methods.
4. Implement your own conjoint experiment into an (online) survey platform.
5. Understand and be able to apply different techniques to analyse conjoint experiments.
6. Be able to easily visualise the result of a conjoint experiment.
7. Be prepared for more advanced conjoint (and factorial experiments) courses or workshops.

This course is structured around seven key topics:

1. Presentation of the general idea of conjoint experiments; Introduction of the logic underlning conjoint experiments, their development, and the reasons behind their recent popularity in the social and behavioral sciences.

2. Brief introduction to the potential outcome framework at the base of modern causal analysis; In particular, an overview of the fundamental problem of causal inference (Holland 1980) is given and discussed wihtin the framework of conjoint analysis.

3. Different ways to measure individual perferences in a conjoint experiment are presented. The focus will be on Choice-Based Conjoint measurement but other measurements (e.g. Rating, Ranking, Combined, and Adaptive) will be discussed briefly.

4. An overview of different types of conjoint design is given, including their usage and limitations. Various elements of a conjoint design (alternatives, choice sets, and context) are presented and explained, paying particular attention to the design of conjoint alternatives.

5. The focus lies on the construction of the conjoint experiment. Using a JavaScript/Pythn program and R, it is shown how to design simple choice-based designs. More advanced designs with attibutes/levels constraints and randomisation are covered as well.

6. A simple workflow using Qualtrics is shown.

7. An overview of different methods to analyse a conjoint experiment is given. A special focus is given to AMCEs, marginal mean and omnibus F-Test. Subgroup differences and visualtistion will be discussed briefly.

8. Recent advances in conjoint analysis will be covered, including power analysis and the usafe of mixture modelling to discover treatment heterogeneity.

The course will present a variety of methods to analyze conjoint data. We focus on AMCEs, marginal mean and omnibus F-Test. Robust estimators will be explained and employed to analysis CJ data. Subgroup differences and visualisation will be discussed as well. Finite mixture modelling will be briefly discussed in the context of subgroup analysis and discovering of treatment heterogeneity.
This course will use R, which is a free and open source programming language primarily used for statistics and data analysis. Although you are allowed to use other sources, we will also use RStudio, which is an easy-to-us interface to R. The design of the conjoint experiments requires the usage of JavaScript/Python program with a graphical interface.

Immanent (presentations, peer group discussion, media adaptation of scientific projects).

Will be announced soon.