Abstract
In this paper, we develop a graphical interface that allows to calculate the efficacy of one or more treatments before adopting an experimental economics design. The graphical interface is built with Java according to a model-based treatment design. The aim is twofold. We are first interested in designing treatments in order to increase their efficacy, evaluating how experimental factors can affect the treatment process design. The second aim is to enhance the internal and external validity of the experiment to be run. The general idea behind this research is to implement a Graphical Experimenter Interface (GEI) capable to support economists when deciding which experimental treatment design to adopt and thus which factors to include.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A large body of scientific literature is concerned with modelling the effects of a treatment on an outcome of interest [see 1,2,3]. In economics experiments, therefore, the experimenter selects variables which may affect the dependent variable and, thus, she considers them treatment variables (independent variables). The experimenter observes the effect on the dependent variable generated by one or more variations or manipulations of independent variables, ruling out any competing explanation.
- 2.
In fact, “a “material” model is a model of flesh and blood, the exogenous variables of which are controlled by the experimental design in order to see how the endogenous variables react to changes in the treatment variables.” Schmidt J. [6] p. 15. Although the model is general and can be applied to several experimental contexts, we introduce it in the context of designing economics experiments.
- 3.
For treatment group we intend the group of experimental subjects to which the experimenter applies a treatment. For treatment we intend the change of one (single treatment) or more experimental factors (multiple treatment) compared to the value of those same factors tested in the control group or baseline group (group of basic experimental subjects).
- 4.
According to Shadish et al. [17], a treatment should not be applied to nonmanipulable experimental variables. For example, the authors suggest not to consider gender to be a cause in an experiment because it cannot be manipulated due to the presence of so many co-variates based on life experience. A stronger inference is possible if experimenters are able to manipulate independent variables such as the dosage in medical investigations or the word choice in media messages.
- 5.
This first factor \( (x_{1} ) \) summarizes three factors originally considered by [7]: (i) subject pool, (ii) information, and (iii) environment. Indeed, among the original six factors taken into account in [7], only the three aforementioned factors can determine the experimental design context. If we do not summarize them, moreover, we obtain some vectors non-representative of the possible control and treatment groups. The opportunity to summarize these three factors enables us to exclude non-representative vectors and, at the same time, to overcome related problems of redundancy with experimental factors.
- 6.
The connection between economics experiments and economic theories is very close. In this regard, there is a broad consensus among economists on the fact that economics experiments can be run to test economic theories [20,21,22]. According to [13, 23], when testing theories, experimenters can design laboratory, extra-lab and field contexts which, in a certain way, remind the economic theories – only for what is needed in regard to a particular knowledge of the world insofar as the economic theory itself does – while, in other ways, it represents the world in a different way, by replacing unrealistic assumptions with experimental subjects’ actual behavior.
- 7.
We aim to represent the complementarity of lab and field designs, also including the extra-lab environment in order to represent the mechanism of treatment according to internal and external validity criteria [7,8,9, 12]. The matrices include no. 12 vectors that is to say no. 12 possible control groups and no. 24 treatment groups that is to say no. 24 possible treatment groups. Therefore, we have no. 36 possible experimental groups.
References
LaLonde, R.J.: Evaluating the econometric evaluations of training programs with experimental data. Am. Econ. Rev. 76(4), 604–620 (1986)
Heckman, J.: Instrumental variables: a study of implicit behavioral assumptions used in making program evaluations. J. Hum. Resour. 32, 441–462 (1997)
Heckman, J., Navarro-Lozano, S.: Using matching, instrumental variables, and control functions to estimate economic choice models. Rev. Econ. Stat. 86, 30–57 (2004)
Angrist, J., Han, J.: When to control for covariates? Panel asymptotic for estimates of treatment effects. Rev. Econ. Stat. 86(1), 58–72 (2004)
Card, D., Della Vigna, S., Malmendier, U.: The role of theory in field experiments. J. Econ. Perspect. 25(3), 39–62 (2011)
Schmidt, K.M.: The role of experiments for the development of economic theory. Perspektiven der Wirtschaftspolitik 10, 14–30 (2009)
Harrison, G.W., List, J.A.: Field experiments. J. Econ. Lit. 42(4), 1013–1059 (2004)
Banerjee, A.V., Duflo, E.: The experimental approach to development economics. Ann. Rev. Econ. 1, 151–178 (2009)
Guala, F.: The Methodology of Experimental Economics. Cambridge University Press, New York (2005)
List, J.A., Sadoff, S., Wagner, M.: So you want to run an experiment, now what? Some simple rules of thumb for optimal experimental design. Exp. Econ. 14(4), 439–457 (2011)
Campbell, D.T., Stanley, J.C.: Experimental and Quasi-Experimental Designs for Research. Rand McNally College Publishing Co, Chicago (1966)
Alm, J., Bloomquist, K., McKee, M.: On the external validity of laboratory tax compliance experiment. Econ. Inq. 53(2), 1170–1186 (2015)
Charness, G., Gneezy, U., Kuhnb, M.A.: Experimental methods: extra-laboratory experiments-extending the reach of experimental economics. J. Econ. Behav. Organ. 91, 93–100 (2013)
Maxwell, S., Delaney, H.: Design Experiments and Analyzing Data: A Model Comparison Perspective, 2nd edn. Lawrence Erlbaum Associate, Publishers Mahway, Mahwah (2004)
Moffatt, P.: Experimetrics: Econometrics for Experimental Economics. Palgrave Higher Education, London (2015)
Bellemare, C., Kröger, S., Bissonnette, L.: Simulating power of economic experiments: the powerBBK package. J. Econ. Sci. Assoc. 2(2), 157–168 (2016)
Shadish, W.R., Cook, T.D., Campbell, D.T.: Experimental and Quasi-Experimental Designs for Generalized Causal Inference. Houghton Mifflin, Boston (2002)
Plott, C.R.: Will economics become an experimental science? South. Econ. J. 57(4), 901–919 (1991)
Bardsley, N., Cubitt, R., Loomes, G., Moffatt, P., Starmer, C., Sugden, R.: Experimental Economics: Rethinking the Rules. Princeton University Press, Princeton (2010)
Davis, D.D., Holt, C.A.: Experimental Economics. Princeton University Press, Princeton (1993)
Roth, A.: Lets keep the con out of experimental econ. A methodological note. In: Hey, J. (ed.) Experimental Economics. Studies in Empirical Economics, pp. 99–109. Springer, Heidelberg (1994)
Poindexter, J.C., Earp, J., Baumer, D.: An experimental economics approach toward quantifying online privacy choices. Inf. Syst. Front. 8, 363–374 (2006)
Sugden, R.: Experiments as exhibits and experiments as tests. J. Econ. Methodol. 12, 291–302 (2005)
Harrison, G.W.: Expected utility theory and the experimentalists. Empirical Econ. 19, 223–254 (1994)
Chamberlin, E.: An experimental imperfect market. J. Polit. Econ. 56, 95–108 (1948)
Durham, Y., McKinnon, T., Schulmane, C.: Classroom experiments: not just fun and games. Econ. Inq. 45(1), 162–178 (2006)
Bandiera, O., Barankay, I., Rasul, I.: Social connections and incentives in the workplace: evidence from personnel data. Econometrica 77(4), 1047–1094 (2009)
Ortmann, A., Fitzgerald, J., Boeing, C.: Trust, reciprocity, and social history: a re-examination. Exp. Econ. 3(1), 81–100 (2000)
Acknowledgements
The authors are grateful to Fioravante Patrone, Raffaele Dell’Aversana, and two anonymous reviewers for their helpful comments on earlier versions of this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Bucciarelli, E., Liberatore, A. (2018). Designing and Programming a Graphical Interface to Evaluate Treatments in Economics Experiments. In: Bucciarelli, E., Chen, SH., Corchado, J. (eds) Decision Economics: In the Tradition of Herbert A. Simon's Heritage. DCAI 2017. Advances in Intelligent Systems and Computing, vol 618. Springer, Cham. https://doi.org/10.1007/978-3-319-60882-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-60882-2_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-60881-5
Online ISBN: 978-3-319-60882-2
eBook Packages: EngineeringEngineering (R0)