The course provides an overview of the use of controlled experiments to investigate research questions in economics and social sciences. The focus is methodological, and illustrated by examples and applications taken from the literature. The course goes through the main methodological questions related to the use of controlled experiments to produce empirical knowledge : why are controlled experiments needed (i.e., what kind of question ios best answered thans to controlled experiments) ? How to design a controlled experiment (i.e., internal validity issues) ? And what are experimental results useful for (i.e., external validity) ?
Jacquemet N., L’Haridon O. (2018). Experimental Economics : Method and Applications. Cambridge University Press.
This course takes place every day
Topics : B. Boulu-Reshef, O. L’Haridon, A. Secchi and F. Etilé
The aim of the four “topics” module is to provide participants an overview on some more specific issues of running experiments and methods to overcome them. Each sessions dedicate to the issues at hand, the available methods and their limits and strengths (in particular in comparison with each other).
TOPIC 1 : Methods and tricks of the trade, Béatrice Boulu-Reshef
The first session is an “experimental lecture”, in which by putting participants in the shoe of an experimental subject aims at pointing to classical problems and solutions to the practical implementation of a lab experiment. The purpose is to show them in vivo how experimental protocols can be implemented and illustrate the relevance or shortcomings of some practices and methods. Moreover, being in the shoes of a subject in the lab makes salient what typical mistakes can be avoided when researchers design an experiment and what effects some features can have on observed behavior. Either classic studies that have set standards for the field or counter-examples to good practice will be run. The second session is dedicated to the writing of instructions, a topic often neglected although of critical importance. The goal of instructions is to make sure that the experimental subjects fully understand the rules of an experiment. If subjects do not understand the rules, control is lost, and the experiment is invalidated and unpublishable. Thus, learning how to write experimental instructions is crucial. This lecture focuses on teaching how to write experimental instructions. We explain what experimental instructions need to achieve, and hence, list the rules that are commonly used by experimental economists. We also review the features of experimental instructions that are debated in the literature. The lecture reviews typical instructions for the main types of experiments. Students will work on writing instructions and will discuss their work in class. The third session deals with how to extend lab experiment to the field.
Key references :
Davis, D. and C. A. Holt (1993), “Experimental Economics”, Princeton University Press.
D. Friedman and S. Sunder (1994), “Experimental Methods : A Primer for Economists”, Cambridge University Press.
Guala F. (2005), “The Methodology of Experimental Economics”. New York : Cambridge University Press.
TOPIC 2 : Preferences over time and uncertainty, Olivier L’Haridon
Preferences over time and uncertainty are critical drivers of economic behavior in many contexts. Several experimental methods have been developed to measure them. These methods serve to elicit preferences over time and uncertainty either as control variables in more general experiments, but also to test decision-theoretic models. These methods are presented in this lecture with a specific focus on their relative merits. A special emphasis will be put on robust methods to elicit cumulative prospect theory parameters for decision under risk.
Key references :
Abdellaoui, M. (2000). “Parameter-free elicitation of utility and probability weighting functions”. Management Science, 46(11), 1497-1512.
Abdellaoui, M., Bleichrodt, H., l’Haridon, O., & Paraschiv, C. (2013). « Is there one unifying concept of utility ? An experimental comparison of utility under risk and utility over time”. Management Science, 59(9), 2153-2169.
Wakker, P., & Deneffe, D. (1996). “Eliciting von Neumann-Morgenstern utilities when probabilities are distorted or unknown”. Management science, 42(8), 1131-1150.
Wakker, P. P. (2010). “Prospect theory : For risk and ambiguity”. Cambridge university press.
TOPICS 3 : Psychometric methods, Fabrice Etilé
This class will introduce the main principles of psychometrics, present the technical stages of development and validation of a stage, show how psychometrics can be used in empirical economics, and finally discuss identification problems and epistemological issues. The course will be based on three sets of papers : (1) articles that develop and validate psychometric scales (with a specific focus on the BIS/BAS scale that measures dispositional sensitivity to rewards and punishments ; (2) works that use psychometric scales (especially the BIS/BAS) for interpreting the individual heterogeneity of behaviours in standard experimental games : (3) studies investigating some methodological aspects and limits of psychometrics scales.
Key references :
Kline, P. (2014). “The new psychometrics : Science, psychology and measurement”. New York : Routledge.
Carver, C. S., & White, T. L. (1994). Behavioral inhibition, behavioral activation, and affective responses to impending reward and punishment : the BIS/BAS scales. Journal of personality and social psychology, 67(2), 319.
Skatova, A., & Ferguson, E. (2011). What makes people cooperate ? Individual differences in BAS/BIS predict strategic reciprocation in a public goods game. Personality and Individual Differences, 51(3), 237-241.
Borghans, L., Golsteyn, B. H., Heckman, J., & Humphries, J. E. (2011), “Identification problems in personality psychology.”, Personality and individual differences, 51(3), 315-320.
TOPIC 4 : Econometrics for experimental data, Angelo Secchi
This module provides an overview on econometrics for experimental data with a strong emphasis on non-parametric techniques. Estimating probability densities, distribution free tests et nonparametric regressions will be discussed together with examples and practical suggestions on how to implement them.
Key references :
Silverman, B.W., (1986). “Density Estimation for Statistics and Data Analysis”, Chapman & Hall.
Racine, J.S. (2008), “Nonparametric Econometrics : A Primer, Foundations and Trends” in Econometrics : Vol. 3 : No 1, pp 1-88.
Hollander, M., Dougla A. Wolfe and E. Chicken (2014), “Nonparametric Statistical Methods”, third edition, Wiley.
Workshop sessions : Béatrice Boulu-Reshef, Fabrice Etilé, Nicolas Jacquemet, Fabrice Le Lec, Olivier L’Haridon, Angelo Secchi
Wokshops : Some sessions are dedicated to the presentation of ongoing projects by participants, in order to get feedback both from the professors and the other participants. Additional sessions re dedicated to the free discussion of participants’ project, with a strong emphasis on getting early stage feedback. In this perspective, the discussion of on-going projects (experimental design conception) are particularly encouraged to permit a maximal methodological gain.
Contents - Experimental Economics