On the Identification of the Causal Effects of Audit Activity under Measurement and Selection Biases
Keywords:
causal effect, counterfactual, measurement bias, selection bias, tax auditAbstract
We propose a causal analysis based on a linear Structural Equation Model (SEM) of the effect of audits on the compliance level of tax payers. Generally, when the audit rule is not based on randomization and we also have unobserved variables, it is very likely to have confounding and the causal effect estimate can be biased, if not detected by inspection of the graphical model related to the SEM and removed. In addition, both measurement bias and selection bias arise naturally in real situation of observed data, thus increasing the complexity of the problem to be solved. In this case, the classical causal effect identification techniques (backdoor, frontdoor and instrumental variable) cannot be directly applied. To solve the causal effect identification problem in such a context, we extend the effect restoration method for the measurement bias, according to the selection recoverability condition. The proposed method, combining the two techniques, can be used to obtain an estimate of the causal effect closer to the real one, compared to the previous estimation approach adopted in this field. Moreover, the methodology can be applied also in other contexts, on problems sharing the same causal structure, or having an equivalent one.
References
. Allingham, M.G., Sandmo, A. “Income tax evasion: A theoretical analysis”. Journal of Public Economics. 1972. 1(3-4): 323-338.
. Santoro, A., Fiorio, C.V. “Taxpayer behavior when audit rules are known: evidence from Italy”. Public Finance Review. 2011. 39(1): 103-123.
. Fudenberg, D., Tirole, J. Game Theory. MIT Press. 1991.
. Rasmusen, E. Games and Information: An Introduction to Game Theory (4th ed.). Blackwell Publishing. 2006.
. Dubin, J.A., Wilde, L. “An Empirical Analysis of Federal Income Tax Auditing and Compliance”. National Tax Journal. 1988 41(1): 61-74.
. Plumley, A.H. The Impact of the IRS on Voluntary Tax Compliance: Preliminary Empirical Results. National Tax Association, 95th Annual Conference of Taxation. Orlando, Florida. 2002.
. Tagkalakis, A.O. “The Direct and Indirect Effects of Audits on the Tax Revenue in Greece”. Economics Bulletin. 2014. 34(2): 984-1001.
. Niu, Y. “Tax audit impact on voluntary compliance”. Journal of Economic and Social Measurement. 2011. 36(4): 237-251.
. Ratto, M., Richard, T., David, U. “The indirect effects of auditing taxpayers”. Public Finance Review. 2013.
. Hernán M.A., Hernández-Díaz S., Robins J.M. “A structural approach to selection bias”. Epidemiology. 2004. 15: 615– 625.
. D’Agosto, E., Manzo, M., Pisani, S., D’Arcangelo, F.M. “The Effect of Audit Activity on Tax Declaration: Evidence on Small Business in Italy”. Public Finance Review. 2018. 46(1): 29-57.
. Pearl, J. Causality: Models, reasoning, and inference (2nd ed.). Cambridge University Press. 2009.
. Pearl, J., Glymour M., Jewell N.P. Causal inference in statistics: A Primer. Wiley. 2016.
. Santoro A. “Do Small Businesses Respond to a Change in Tax Audit Rules? Evidence from Italy.” Public Finance Review. 2016. 45(6): 792-814.
. Fox, J. Effect Analysis in Structural Equation Models: Extensions and Simplified Methods of Computation. Sociological Methods & Research. 1980. 9(1): 3-28.
. Bollen, K.A. “Total, Direct, and Indirect Effects in Structural Equation Models”. In Clifford Clogg (ed.) Sociological Methodology. Washington, DC: American Sociological Association. 1987. 37-69.
. Balke, A., Pearl, J. Counterfactuals and Policy Analysis in Structural Models. Proceedings of the XI Conference on Uncertainty in Artificial Intelligence. 1995. 11-18.
. Cai, Z., Kuroki M. Counterfactual Reasoning in Linear Structural Equation Models. Proceedings of the XXI Conference on Uncertainty in Artificial Intelligence. 2005. 77-84
. Koller D., Friedman N. Probabilistic Graphical Models: Principles and Techniques. The MIT Press. 2009.
. Newman M. Networks (2nd ed.). New York, NY: Oxford University Press. 2018.
. Vicard, P. “On the identification of a single-factor model with correlated residuals”. Biometrika. 2000. 87(1): 199–205.
. Stanghellini, E. “Instrumental variables in Gaussian directed acyclic graph models with an unobserved confounder”. Environmetrics. 2004. 15(5): 463-469.
. Stanghellini, E., Wermuth, N. 2005. “On identification of path analysis models with one hidden variable”. Biometrika. 2005. 92(2): 337-350.
. Grzebyk, M., Wild, P., Chouaniere, D. “On identification of multi-factor models with correlated residuals”. Biometrika. 2004. 91(1): 141-151.
. Cai, Z., Kuroki M. On identifying total effects in the presence of latent variables and selection bias. Proceedings of the XXIV Conference on Uncertainty in Artificial Intelligence. 2008. 62-69.
. Kuroki, M., Pearl, J. “Measurement bias and effect restoration in causal inference”. Biometrika. 2014. 101(2): 423-437.
. Bareinboim, E., Tian, J., and Pearl, J. “Recovering from Selection Bias in Causal and Statistical Inference”. In Brodley, C. E., and Stone, P., eds., Proceedings of the Twenty-eighth AAAI Conference on Artificial Intelligence. 2014. 2410-2416.
. Correa, J. D., and Bareinboim, E. Causal Effect Identification by Adjustment under Confounding and Selection Biases. Proceedings of the 31th Conference on Artificial Intelligence. 2017. 3740-3746.
. Correa, J. D., Tian J. & Bareinboim, E. Generalized Adjustment Under Confounding and Selection Biases. Proceedings of the 32th Conference on Artificial Intelligence. (pp. 6335-6342). Menlo Park, CA: AAAI Press. 2018.
. Bishop, C. M. Pattern Recognition and Machine Learning. New York, NY: Springer. 2006.
. Bollen, K.A. Structural Equations with Latent Variables. Wiley. 1989.
Downloads
Published
How to Cite
Issue
Section
License
Authors who submit papers with this journal agree to the following terms.
