Hostname: page-component-78c5997874-t5tsf Total loading time: 0 Render date: 2024-11-20T00:04:46.962Z Has data issue: false hasContentIssue false
  • English
  • Français

Causal Inference without Ignorability: Identification with Nonrandom Assignment and Missing Treatment Data

Published online by Cambridge University Press:  04 January 2017

Walter R. Mebane Jr.  and
Paul Poast
Walter R. Mebane Jr.*
Affiliation:
Department of Political Science and Department of Statistics, University of Michigan, 5700 Haven Hall, Ann Arbor, MI 48109
Paul Poast
Affiliation:
Department of Political Science, Rutgers University, Hickman Hall, New Brunswick, NJ 08901 e-mail: [email protected]
*
e-mail: [email protected] (corresponding author)
Get access Rights & Permissions [Opens in a new window]

Abstract

How a treatment causes a particular outcome is a focus of inquiry in political science. When treatment data are either nonrandomly assigned or missing, the analyst will often invoke ignorability assumptions: that is, both the treatment and missingness are assumed to be as if randomly assigned, perhaps conditional on a set of observed covariates. But what if these assumptions are wrong? What if the analyst does not know why—or even if—a particular subject received a treatment? Building on Manski, Molinari offers an approach for calculating nonparametric identification bounds for the average treatment effect of a binary treatment under general missingness or nonrandom assignment. To make these bounds substantively more informative, Molinari's technique permits adding monotonicity assumptions (e.g., assuming that treatment effects are weakly positive). Given the potential importance of these assumptions, we develop a new Bayesian method for performing sensitivity analysis regarding them. This sensitivity analysis allows analysts to interpret the assumptions' consequences quantitatively and visually. We apply this method to two problems in political science, highlighting the method's utility for applied research.

Type
Research Article
Information
Political Analysis , Volume 21 , Issue 2 , Spring 2013 , pp. 233 - 251
Copyright
Copyright © The Author 2013. Published by Oxford University Press on behalf of the Society for Political Methodology 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Footnotes

Authors' note: Thanks to Peter Aronow for many important contributions. Comments from Don Green, Arthur Spirling, Allison Sovey, Rory Truex, and the participants of the 2011 MPSA Annual National Conference and the 2011 Annual Meeting of the Society for Political Methodology are greatly appreciated. Supplementary materials for this article are available on the Political Analysis Web site. Replication materials are in study hdl:1902.1/19368 at IQSS Dataverse Network.

References

Arnborg, Stefan. 2006. Robust Bayesianism: Relation to evidence theory. Journal of Advances in Information Fusion 1: 75–90.Google Scholar
Aronow, Peter, and Samii, Cyrus. 2012. Estimating average causal effects under general interference. Paper presented at the 2012 Summer Meeting of the Society for Political Methodology, University of North Carolina, Chapel Hill, July 19–21.Google Scholar
Beresteanu, Arie, and Molinari, Francesca. 2008. Asymptotic properties for a class of partially identified models. Econometrica 76: 763–814.CrossRefGoogle Scholar
Bernhard, Judith K., Goldring, Luin, Young, Julie, Berinstein, Carolina, and Wilson, Beth. 2007. Living with precarious legal status in Canada: Implications for the well-being of children and families. Refuge: Canada's Periodical on Refugees 24: 101–14.Google Scholar
Blattman, C. 2009. From violence to voting: War and political participation in Uganda. American Political Science Review 103: 231–47.Google Scholar
Bowers, Jake, Fredrickson, Mark, and Panagopoulos, Costas. 2012. Interference is interesting: Statistical inference for interference in social network experiments. Paper presented at the 2012 Summer Meeting of the Society for Political Methodology, University of North Carolina, Chapel Hill, July 19–21.Google Scholar
Cederman, Lars-Erik, Weidmann, Nils B., and Gleditsch, Kristian Skrede. 2011. Horizontal inequalities and ethnonationalist civil war: A global comparison. American Political Science Review 105: 478–95.Google Scholar
Cingranelli, David, and Richards, David. 2010. The Cingranelli-Richards (CIRI) human rights dataset. http://www.humanrightsdata.org.Google Scholar
Cochran, William G., and Rubin, Donald B. 1973. Controlling bias in observational studies: A review. Sankya: The Indian Journal of Statistics 35: 417–66.Google Scholar
Davenport, Christian. 2007a. State repression and political order. Annual Review of Political Science 10: 1–23.Google Scholar
Davenport, Christian. 2007b. State repression and the tyrannical peace. Journal of Peace Research 4: 485–504.Google Scholar
Efron, Bradley. 2011. Bayesian inference and the parametric bootstrap. Working paper.Google Scholar
Gleditsch, Nils Petter, Wallensteen, Peter, Eriksson, Mikael, Sollenberg, Margareta, and Strand, Håvard. 2002. Armed conflict 1946–2001: A new dataset. Journal of Peace Research 39: 615–37.Google Scholar
Glynn, Adam N., and Quinn, Kevin M. 2010. An introduction to the augmented inverse propensity weighted estimator. Political Analysis 18: 36–56.CrossRefGoogle Scholar
Hainmueller, Jens, and Hiscox, Michael J. 2007. Educated preferences: Explaining attitudes toward immigration in Europe. International Organization 61: 399–442.Google Scholar
Hainmueller, Jens, and Hiscox, Michael J. 2010. Attitudes toward highly skilled and low-skilled immigration: Evidence from a survey experiment. American Political Science Review 104: 61–84.Google Scholar
Hastie, Trevor J. 1992. Generalized additive models. In Statistical models in S, eds. Chambers, John M. and Hastie, Trevor J. New York: Wadsworth & Brooks/Cole.Google Scholar
Holland, Paul W. 1986. Statistics and causal inference. Journal of the American Statistical Association 81: 945–60.Google Scholar
Imai, Kosuke, Keele, Luke, Tingley, Dustin, and Yamamoto, Teppei. 2011. Unpacking the black box of causality: Learning about causal mechanisms from experimental and observational studies. American Political Science Review 105: 765–89.Google Scholar
Imai, Kosuke, Keele, Luke, and Yamamoto, Teppei. 2010. Identification, inference, and sensitivity analysis for causal mediation effects. Statistical Science 25: 51–71.CrossRefGoogle Scholar
Karlsson, Alexander. 2010. Evaluating credal set theory as a belief framework in high-level information fusion for automated decision-making. Technical Report. Örebro Studies in Technology 38.Google Scholar
Karlsson, Alexander, Johansson, Ronnie, and Andler, Sten F. 2011. Characterization and empirical evaluation of Bayesian and credal combination operators. Journal of Advances in Information Fusion 6: 150–66.Google Scholar
Levi, Isaac. 1983. The enterprise of knowledge. Cambridge, MA: MIT Press.Google Scholar
Lichbach, Mark Irving. 1987. Deterrence or escalation? The puzzle of aggregate studies of repression and dissent. Journal of Conflict Resolution 31: 266–97.Google Scholar
Manski, Charles. 1990. Nonparametric bounds on treatment effects. American Economic Review Papers and Proceedings 80: 319–23.Google Scholar
Manski, Charles. 1995. Identification problems in the social sciences. Cambridge, MA: Harvard University Press.Google Scholar
Manski, Charles. 1997. Monotone treatment response. Econometrica 65: 1311–34.Google Scholar
Manski, Charles. 2011. Identification of treatment response with social interactions. Working paper.Google Scholar
Manski, Charles, and Pepper, John V. 2000. Monotone instrumental variables: With an application to the returns to schooling. Econometrica 68: 997–1010.Google Scholar
Molinari, Francesca. 2005. Missing treatments. CAE Working paper #05-11.Google Scholar
Molinari, Francesca. 2007. Missing treatments. Working paper.Google Scholar
Molinari, Francesca. 2010. Missing treatments. Journal of Business and Economic Statistics 28:82–95.CrossRefGoogle Scholar
Morgan, Stephen L., and Winship, Christopher. 2007. Counterfactuals and causal inference: Methods and principles for social research (Analytical Methods for Social Research). New York: Cambridge University Press.Google Scholar
Newton, Michael A., and Raftery, Adrian E. 1994. Approximate Bayesian inference with the weighted likelihood bootstrap. Journal of the Royal Statistical Society, Series B 56: 3–48.Google Scholar
Petersen, Roger D. 2002. Understanding ethnic violence: Fear, hatred, and resentment in twentieth-century Eastern Europe. Cambridge, UK: Cambridge University Press.Google Scholar
Poast, Paul. 2012. Does issue linkage work? Evidence from European alliance negotiations, 1860 to 1945. International Organization 66: 277–310.Google Scholar
Quinn, Kevin M. 2009. What Can Be Learned from a Simple Table? Bayesian inference and sensitivity analysis for causal effects from 2x2 and 2x2xK tables in the presence of unmeasured confounding. Working paper.Google Scholar
Rosenbaum, Paul. 2002. Covariance adjustment in randomized experiments and observational studies (with discussion). Statistical Science 17: 286–327.Google Scholar
Rubin, Donald B. 1978. Bayesian inference for causal effects: The role of randomization. Annals of Statistics 6: 34–58.Google Scholar
Rubin, Donald B. 1981. The Bayesian bootstrap. Annals of Statistics 9: 130–4.Google Scholar
Rubin, Donald B. 1991. Practical implications of modes of statistical inference for causal effects and the critical role of the assignment mechanism. Biometrics 47: 1213–34.Google Scholar
Rubin, Donald B. 2006. Matched sampling for causal effects. New York: Cambridge University Press.Google Scholar
Sambanis, Nicholas, and Zinn, Annalisa. 2006. From protest to violence: An analysis of conflict escalation with an application to self-determination movements. Working paper.Google Scholar
Scott, Alastair, and Smith, T. M. F. 1973. Survey design, symmetry and posterior distributions. Journal of the Royal Statistical Society, Series B 35: 57–60.Google Scholar
Sharp, Elaine B., and Joslyn, Mark. 2001. Individual and contextual effects on attributions about pornography. Journal of Politics 63: 501–19.Google Scholar
Sugden, R. A., and Smith, T. M. F. 1984. Ignorable and informative designs in survey sampling inference. Biometrika 71: 495–506.Google Scholar
Tarrow, Sidney. 1989. Democracy and disorder: Social conflict, political protest and democracy in Italy. New York: Oxford University Press.Google Scholar
Taylor, James W. 2000. A quantile regression neural network approach to estimating the conditional density of multiperiod returns. Journal of Forecasting 19: 299–311.Google Scholar
Wahba, Grace. 1983. Bayesian “confidence intervals” for the cross-validated smoothing spline. Journal of the Royal Statistical Society, Series B 45: 133–50.Google Scholar
Wahba, Grace. 1990. Spline models for observational data. Philadelphia: Society for Industrial and Applied Mathematics.Google Scholar
Wang, Yuedong, and Wahba, Grace. 1994. Bootstrap confidence intervals for smoothing splines and their comparison to Bayesian “confidence intervals.” Journal of Statistical Computation and Simulation 51: 263–79.Google Scholar
World Values Survey Association. 2009. WORLD VALUES SURVEY 2005 OFFICIAL DATA FILE v.20090901. Aggregate File Producer: ASEP/JDS, Madrid.Google Scholar
Yamamoto, Teppei. 2012. Understanding the past: Statistical analysis of causal attribution. American Journal of Political Science 56: 237–56.Google Scholar
Supplementary material: PDF

Mebane and Poast supplementary material

Supplementary Material

Download Mebane and Poast supplementary material(PDF)
PDF 1.8 MB