![[PDF]](/pb-assets/Icons/adobe-pdf-icon-1498649896243.png){kind=icon}
Abstract
Conventional methods for mediation analysis generate biased results when the mediator–outcome relationship depends on the treatment condition. This article shows how the ratio-of-mediator-probability weighting (RMPW) method can be used to decompose total effects into natural direct and indirect effects in the presence of treatment-by-mediator interactions. The indirect effect can be further decomposed into a pure indirect effect and a natural treatment-by-mediator interaction effect. Similar to other techniques for causal mediation analysis, RMPW generates causally valid results when the sequential ignorability assumptions hold. Yet unlike the model-based alternatives, including path analysis, structural equation modeling, and their latest extensions, RMPW requires relatively few assumptions about the distribution of the outcome, the distribution of the mediator, and the functional form of the outcome model. Correct specification of the propensity score models for the mediator remains crucial when parametric RMPW is applied. This article gives an intuitive explanation of the RMPW rationale, a mathematical proof, and simulation results for the parametric and nonparametric RMPW procedures. We apply the technique to identifying whether employment mediated the relationship between an experimental welfare-to-work program and maternal depression. A detailed delineation of the analytic procedures is accompanied by online Stata code as well as a stand-alone RMPW software program to facilitate users’ analytic decision making.
References
|
Abadie, A., Chingos, M. M., West, M. R. (2013). Endogenous stratification in randomized experiments (Working Paper 19742). Cambridge, MA: National Bureau of Economic Research. Retrieved from http://www.nber.org/papers/w19742 Google Scholar | |
|
Alwin, D. F., Hauser, R. M. (1975). The decomposition of effects in path analysis. American Sociological Review, 40, 37–47. Google Scholar | Crossref | |
|
Austin, P. C. (2011). Optimal caliper widths for propensity-score matching when estimating differences in means and differences in proportions in observational studies. Pharmaceutical Statistics, 10, 150–161. Google Scholar | Crossref | Medline | |
|
Avin, C., Shpitser, I., Pearl, J. (2005). Identifiability of path-specific effects. Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence (pp. 357–363). Edinburgh, Scotland, UK. Google Scholar | |
|
Baron, R. M., Kenny, D. A. (1986). The moderator-mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. Journal of Personality and Social Psychology, 51, 1173–1182. Google Scholar | Crossref | Medline | |
|
Bein, E., Deutsch, J., Porter, K., Qin, X., Yang, C., Hong, G. (2015). Technical report on two-step estimation in RMPW analysis. Oakland, CA: MDRC. Google Scholar | |
|
Bollen, K. A. (1989). Structural equations with latent variables. Wiley Series in Probability and Mathematical Statistics. New York, NY: John Wiley. Google Scholar | Crossref | |
|
Bullock, J. G., Green, D. P., Ha, S. E. (2010). Yes, but what’s the mechanism? (Don’t Expect an Easy Answer). Journal of Personality and Social Psychology, 98, 550–558. Google Scholar | Crossref | Medline | |
|
Cameron, A. C., Trivedi, P. K. (2005). Microeconometrics: Methods and applications. Cambridge, England: Cambridge University Press. Google Scholar | Crossref | |
|
Cheng, T. C. (2007). Impact of work requirements on the psychological well-being of TANF recipients. Health and Social Work, 32, 41–48. Google Scholar | Crossref | Medline | |
|
Coffman, D. L., Zhong, W. (2012). Assessing mediation using marginal structural models in the presence of confounding and moderation. Psychological Methods, 17, 642–664. Google Scholar | Crossref | Medline | |
|
Collins, L., Graham, J., Flaherty, B. (1998). An alternative framework for defining mediation. Multivariate Behavioral Research, 33, 295–312. Google Scholar | Crossref | Medline | |
|
Cook, T., Steiner, P. (2010). Case matching and the reduction of selection bias in quasi-experiments: The relative importance of pretest measures of outcome, of unreliable measurement, and of mode of data analysis. Psychological Methods, 15, 56–68. Google Scholar | Crossref | Medline | |
|
Drake, C. (1993). Effects of misspecification of the propensity score on estimators of treatment effects. Biometrics, 49, 1231–1236. Google Scholar | Crossref | |
|
Duncan, O. D. (1966). Path analysis: Sociological examples. American Journal of Sociology, 72, 1–16. Google Scholar | Crossref | |
|
Grogger, J., Karoly, L. A. (2005). Welfare reform: Effects of a decade of change. Cambridge, MA: Harvard University Press. Google Scholar | Crossref | |
|
Hamilton, G., Freedman, S., Gennetian, L., Michalopoulos, C., Walter, J., Adams-Ciardullo, D.…Brooks, J. (2001). How effective are different welfare-to-work approaches?: Five-year adult and child impacts for eleven programs. New York, NY: MDRC. Google Scholar | |
|
Hastie, T., Tibshirani, R., Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.). New York, NY: Springer. Google Scholar | Crossref | |
|
Hawkins, D. M. (2004). The problem of overfitting. Journal of Chemical Information and Computer Sciences, 44, 1–12. Google Scholar | Crossref | Medline | |
|
Heckman, J. J., Robb, R. (1985). Alternative methods for evaluating the impact of an intervention. Journal of Econometrics, 30, 239–267. Google Scholar | Crossref | |
|
Holland, P. W. (1986). Statistics and causal inference. Journal of the American Statistical Association, 81, 945–960. Google Scholar | Crossref | |
|
Holland, P. (1988). Causal inference, path analysis, and recursive structural equations models. Sociological Methodology, 18, 449–484. Google Scholar | Crossref | |
|
Hong, G. (2010a). Ratio of mediator probability weighting for estimating natural direct and indirect effects. In JSM Proceedings (pp. 2401–2415), Biometrics Section. Alexandria, VA: American Statistical Association. Google Scholar | |
|
Hong, G. (2010b). Marginal mean weighting through stratification: Adjustment for selection bias in multilevel data. Journal of Educational and Behavioral Statistics, 35, 499–531. Google Scholar | SAGE Journals | |
|
Hong, G. (2012). Marginal mean weighting through stratification: A generalized method for evaluating multi-valued and multiple treatments with non-experimental data. Psychological Methods, 17, 44–60. Google Scholar | Crossref | Medline | |
|
Hong, G. (2015). Causality in a social world: Moderation, mediation and spill-over. West Sussex, UK: John Wiley & Sons, Ltd. Google Scholar | Crossref | |
|
Hong, G., Nomi, T. (2012). Weighting methods for assessing policy effects mediated by peer change. Journal of Research on Educational Effectiveness (special issue on the statistical approaches to studying mediator effects in education research), 5, 261–289. Google Scholar | Crossref | |
|
Huber, M. (2014). Identifying causal mechanisms (primarily) based on inverse probability weighting. Journal of Applied Econometrics, 29, 920–943. Google Scholar | Crossref | |
|
Imai, K., Keele, L., Tingley, D. (2010a). A general approach to causal mediation analysis. Psychological Methods, 15, 309–334. Google Scholar | Crossref | Medline | |
|
Imai, K., Keele, L., Yamamoto, T. (2010b). Identification, inference and sensitivity analysis for causal mediation effects. Statistical Science, 25, 51–71. Google Scholar | Crossref | |
|
Imai, K., Keele, L., Tingley, D., Yamamoto, T. (2011). Unpacking the black box of causality: Learning about causal mechanisms from experimental and observational studies. American Political Science Review, 105, 765–789. Google Scholar | Crossref | |
|
Jagannathan, R., Camasso, M. J., Sambamoorthi, U. (2010). Experimental evidence of welfare reform impact on clinical anxiety and depression levels among poor women. Social Science & Medicine, 71, 152–160. Google Scholar | Crossref | Medline | |
|
Jo, B. (2008). Causal inference in randomized experiments with mediational processes. Psychological Methods, 13, 314–336. Google Scholar | Crossref | Medline | |
|
Jöreskog, K. G. (1970). A general method for analysis of covariance structures. Biometrika, 57, 239–251. Google Scholar | Crossref | |
|
Judd, C. M., Kenny, D. A. (1981). Process analysis: Estimating mediation in treatment evaluation. Evaluation Review, 5, 602–619. Google Scholar | SAGE Journals | |
|
Kang, J. D., Schafer, J. L. (2007). Demystifying double robustness: A comparison of alternative strategies for estimating a population mean from incomplete data. Statistical science, 22, 523–539. Google Scholar | Crossref | |
|
Kling, J. R., Liebman, J. B., Katz, L. F. (2007). Experimental analysis of neighborhood effects. Econometrica, 75, 83–119. Google Scholar | Crossref | |
|
Kraemer, H. C., Wilson, G. T., Fairburn, C. G., Agras, W. S. (2002). Mediators and moderators of treatment effects in randomized clinical trials. Archives of General Psychiatry, 59, 877–883. Google Scholar | Crossref | Medline | |
|
Kraemer, H. C., Kiernan, M., Essex, M., Kupfer, D. J. (2008). How and why criteria defining moderators and mediators differ between the Baron & Kenny and MacArthur approaches. Health Psychology, 27, S101–S108. Google Scholar | Crossref | Medline | |
|
Little, R. J. A., Rubin, D. B. (2002). Statistical analysis with missing data. New York, NY: John Wiley. Google Scholar | Crossref | |
|
MacKinnon, D. P. (2008). Introduction to statistical mediation analysis. New York, NY: Erlbaum. Google Scholar | |
|
MacKinnon, D. P., Krull, J. L., Lockwood, C. M. (2000). Equivalence of the mediation, confounding and suppression effect. Prevention Science, 1, 173–181. Google Scholar | Crossref | Medline | |
|
McCaffrey, D. F., Ridgeway, G., Morral, A. R. (2004). Propensity score estimation with boosted regression for evaluating causal effects in observational studies. Psychological Methods, 9, 403–425. Google Scholar | Crossref | Medline | |
|
Morris, P. A. (2008). Welfare program implementation and parents’ depression. Social Service Review, 82, 579–614. Google Scholar | Crossref | Medline | |
|
Muller, D., Judd, C. M., Yzerbyt, V. Y. (2005). When moderation is mediated and mediation is moderated. Journal of Personality and Social Psychology, 89, 852–863. Google Scholar | Crossref | Medline | |
|
Pearl, J. (2001). Direct and indirect effects. In Proceedings of the American Statistical Association Joint Statistical Meetings (pp. 1572–1581). Minneapolis, MN: MIRA Digital Publishing, August 2005. Google Scholar | |
|
Pearl, J. (2010). The mediation formula: A guide to the assessment of causal pathways in non-linear models (Technical report R-363, July 2010). Los Angeles, CA: University of California, Los Angeles. Google Scholar | |
|
Peck, L. R. (2003). Subgroup analysis in social experiments: Measuring program impacts based on posttreatment choice. American Journal of Evaluation, 24, 157–187. Google Scholar | SAGE Journals | |
|
Peck, L. R. (2007). What are the effects of welfare sanction policies? Or, using propensity scores as a subgroup indicator to learn more from social experiments. American Journal of Evaluation, 28, 256–274. Google Scholar | SAGE Journals | |
|
Petersen, M. L., Sinisi, S. E., van der Laan, M. J. (2006). Estimation of direct causal effects. Epidemiology, 17, 276–284. Google Scholar | Crossref | Medline | |
|
Powers, D. E., Swinton, S. S. (1984). Effects of self-study for coachable test item types. Journal of Educational Psychology, 76, 266–278. Google Scholar | Crossref | |
|
Preacher, K. J., Hayes, A. F. (2008). Asymptotic and resampling strategies for assessing and comparing indirect effects in multiple mediator models. Behavior Research Methods, 40, 879–891. Google Scholar | Crossref | Medline | |
|
Preacher, K. J., Rucker, D. D., Hayes, A. F. (2007). Addressing moderated mediation hypotheses: Theory, methods, and prescriptions. Multivariate Behavioral Research, 42, 185–227. Google Scholar | Crossref | Medline | |
|
Radloff, L. S. (1977). The CES-D scale: A self-report depression scale for research in the general population. Applied Psychological Measurement, 1, 385–401. Google Scholar | SAGE Journals | |
|
Raudenbush, S. W., Reardon, S. F., Nomi, T. (2012). Statistical analysis for multisite trials using instrumental variables with random coefficients. Journal of Research on Educational Effectiveness Special Issue on the Statistical Approaches to Studying Mediator Effects in Education Research, 5, 303–332. Google Scholar | |
|
Robins, J. M. (1999). Marginal structural models versus structural nested models as tools for causal inference. In Elizabeth Halloran, M., Berry, D. (Eds.), Statistical models in epidemiology, the environment, and clinical trials (pp. 95–134). New York, NY: Springer. Google Scholar | |
|
Robins, J. M. (2003). Semantics of causal DAG models and the identification of direct and indirect effects. In Green, P. J., Hjort, N. L., Richardson, S. (Eds.), Highly structured stochastic systems (pp. 70–81). New York, NY: Oxford University Press. Google Scholar | |
|
Robins, J. M., Greenland, S. (1992). Identifiability and exchangeability for direct and indirect effects. Epidemiology, 3, 143–155. Google Scholar | Crossref | Medline | |
|
Rosenbaum, P. R. (1987). Model-based direct adjustment. Journal of the American Statistical Association, 82, 387–394. Google Scholar | Crossref | |
|
Rosenbaum, P. R., Rubin, D. B. (1984). Reducing bias in observational studies using subclassification on the propensity score. Journal of the American Statistical Association, 79, 516–524. Google Scholar | Crossref | |
|
Rubin, D. B. (1978), Bayesian inference for causal effects: The role of randomization. The Annals of Statistics, 6, 34–58. Google Scholar | Crossref | |
|
Rubin, D. B. (1986). Statistics and causal inference: Comments: Which ifs have causal answers. Journal of the American Statistical Association, 81, 961–962. Google Scholar | |
|
Schafer, J. L., Kang, J. (2008). Average causal effects from nonrandomized studies: A practical guide and simulated example. Psychological Methods, 13, 279–313. Google Scholar | Crossref | Medline | |
|
Schochet, P. Z., Burghardt, J. (2007). Using propensity scoring to estimate program-related subgroup impacts in experimental program evaluations. Evaluation Review, 31, 95–120. Google Scholar | SAGE Journals | |
|
Sheets, V. L., Braver, S. L. (1999). Organizational status and perceived sexual harassment: Detecting the mediators of a null effect. Personality and Social Psychology Bulletin, 25, 1159–1171. Google Scholar | SAGE Journals | |
|
Shrout, P. E., Bolger, N. (2002). Mediation in experimental and nonexperimental studies: New procedures and recommendations. Psychological Methods, 4, 422–445. Google Scholar | Crossref | |
|
Sobel, M. E. (2008). Identification of causal parameters in randomized studies with mediating variables. Journal of Educational and Behavioral Statistics, 33, 230–251. Google Scholar | SAGE Journals | |
|
Spencer, S. J., Zanna, M. P., Fong, G. T. (2005). Establishing a causal chain: Why experiments are often more effective than mediational analysis in examining psychological processes. Journal of Personality and Social Psychology, 89, 845–851. Google Scholar | Crossref | Medline | |
|
Tchetgen Tchetgen, E. J. (2013). Inverse odds ratio weighted estimation for causal mediation analysis. Statistics in Medicine, 32, 4567–4580. Google Scholar | Crossref | Medline | |
|
Tchetgen Tchetgen, E. J., Shpitser, I. (2012). Semiparametric theory for causal mediation analysis: Efficiency bounds, multiple robustness and sensitivity analysis. The Annals of Statistics, 40, 1816–1845. Google Scholar | Crossref | Medline | |
|
Valeri, L., VanderWeele, T. J. (2013). Mediation analysis allowing for exposure-mediator interactions and causal interpretation: Theoretical assumptions and implementation with SAS and SPSS macros. Psychological Methods, 18, 137–150. Google Scholar | Crossref | Medline | |
|
van der Laan, M. J., Petersen, M. L. (2008). Direct effect models. The International Journal of Biostatistics, 4, Article 23. Google Scholar | Crossref | |
|
VanderWeele, T. J. (2009). Marginal structural models for the estimation of direct and indirect effects. Epidemiology, 20, 18–26. Google Scholar | Crossref | Medline | |
|
VanderWeele, T. J. (2010). Bias formulas for sensitivity analysis for direct and indirect effects. Epidemiology, 21, 540–551. Google Scholar | Crossref | Medline | |
|
VanderWeele, T. J. (2013). A three-way decomposition of a total effect into direct, indirect, and interactive effects. Epidemiology, 24, 224–232. Google Scholar | Crossref | Medline | |
|
VanderWeele, T. J., Vansteelandt, S. (2009). Conceptual issues concerning mediation, interventions and composition. Statistics and Its Interface, 2, 457–468. Google Scholar | Crossref | |
|
VanderWeele, T. J., Vansteelandt, S. (2010). Odds ratios for mediation analysis for a dichotomous outcome. American Journal of Epidemiology, 172, 1339–1348. Google Scholar | Crossref | Medline | |
|
Waernbaum, I. (2012). Model misspecification and robustness in causal inference: Comparing matching with doubly robust estimation. Statistics in Medicine, 31, 1572–1581. Google Scholar | Crossref | Medline | |
|
Wooldridge, J. M. (2012). Introductory econometrics: A modern approach (5th ed.). Mason, OH: Cengage Learning. Google Scholar | |
|
Wright, S. (1934). The method of path coefficients. Annals of Mathematical Statistics, 5, 161–215. Google Scholar | Crossref |
