Computational Issues in the Statistical Design and Analysis of Experimental Games

Abstract

One goal of experimental economics is to provide data to identify models that best describe the behavior of experimental subjects and, more generally, human economic behavior. We discuss here what we think are the three main steps required to make experimental investigations of economic games as statistically informative as possible: finding the solution of the experimental game under the postulated equilibrium or other economic models, selecting from a potential class of experimental designs the optimal one for discriminating between those models, and choosing an optimal stopping rule that indicates when to stop sampling data and accept one model as the best explanation of the data. Each step can be computationally intensive. We offer an algorithmic presentation of the necessary computations in each of the three steps and illustrate these procedures by examples from our research on learning models in experimental games with incomplete information. These three steps of experimental design and analysis are not limited to experimental games, but the computational burden of implementing these algorithms in other experimental environments - for example, market experiments - requires further considerations with which we have not dealt.

Files

Additional details