Advertisement

Latent Class Dynamic Mediation Model with Application to Smoking Cessation Data

  • Jing Huang
  • Ying Yuan
  • David Wetter
Article
  • 29 Downloads

Abstract

Traditional mediation analysis assumes that a study population is homogeneous and the mediation effect is constant over time, which may not hold in some applications. Motivated by smoking cessation data, we propose a latent class dynamic mediation model that explicitly accounts for the fact that the study population may consist of different subgroups and the mediation effect may vary over time. We use a proportional odds model to accommodate the subject heterogeneities and identify latent subgroups. Conditional on the subgroups, we employ a Bayesian hierarchical nonparametric time-varying coefficient model to capture the time-varying mediation process, while allowing each subgroup to have its individual dynamic mediation process. A simulation study shows that the proposed method has good performance in estimating the mediation effect. We illustrate the proposed methodology by applying it to analyze smoking cessation data.

Keywords

Bayesian inference dynamic mediation latent class time-varying coefficients 

Notes

Supplementary material

11336_2018_9653_MOESM1_ESM.pdf (207 kb)
Supplementary material 1 (pdf 206 KB)

References

  1. Anatchkova, M. D., Velicer, W. F., & Prochaska, J. O. (2006). Replication of subtypes for smoking cessation within the precontemplation stage of change. Addictive Behaviors, 31(7), 1101–1115.Google Scholar
  2. Baker, T. B., Piper, M. E., McCarthy, D. E., Majeskie, M. R., & Fiore, M. C. (2004). Addiction motivation reformulated: An effective processing model of negative reinforcement. Psychological Review, 111(1), 33.Google Scholar
  3. 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(6), 1173.Google Scholar
  4. Bind, M. A., Vanderweele, T. J., Coull, B. A., & Schwartz, J. D. (2015). Causal mediation analysis for longitudinal data with exogenous exposure. Biostatistics, 17(1), 122–134.Google Scholar
  5. Bollen, K. A. (2002). Latent variables in psychology and the social sciences. Annual Review of Psychology, 53, 605–634.Google Scholar
  6. Bommelé, J., Kleinjan, M., Schoenmakers, T. M., Burk, W. J., Van Den Eijnden, R., & Van De Mheen, D. (2015). Identifying subgroups among hardcore smokers: A latent profile approach. PLoS ONE, 10(7), e0133570.Google Scholar
  7. Brandon, T. H., Wetter, D. W., & Baker, T. B. (1996). Affect, expectancies, urges, and smoking: Do they conform to models of drug motivation and relapse? Experimental and Clinical Psychopharmacology, 4(1), 29.Google Scholar
  8. Brown, R. L. (1997). Assessing specific mediational effects in complex theoretical models. Structural Equation Modeling: A Multidisciplinary Journal, 4(2), 142–156.Google Scholar
  9. Chmura Kraemer, H., 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(2S), S101.Google Scholar
  10. Cole, D. A., & Maxwell, S. E. (2003). Testing mediational models with longitudinal data: Questions and tips in the use of structural equation modeling. Journal of Abnormal Psychology, 112(4), 558.Google Scholar
  11. Daniels, M. J., Roy, J. A., Kim, C., Hogan, J. W., & Perri, M. G. (2012). Bayesian inference for the causal effect of mediation. Biometrics, 68(4), 1028–1036.Google Scholar
  12. Didelez, V., Dawid, P., & Geneletti, S. (2012). Direct and indirect effects of sequential treatments. arXiv: 1206.6840.
  13. Dijkstra, A., & De Vries, H. (2000). Clusters of precontemplating smokers defined by the perception of the pros, cons, and self-efficacy. Addictive Behaviors, 25(3), 373–385.Google Scholar
  14. Elliott, M. R., Gallo, J. J., Ten Have, T. R., Bogner, H. R., & Katz, I. R. (2005). Using a Bayesian latent growth curve model to identify trajectories of positive affect and negative events following myocardial infarction. Biostatistics, 6(1), 119–143.Google Scholar
  15. Eilers, P. H., & Marx, B. D. (1996). Flexible smoothing with \(B\)-splines and penalties. Statistical Science, 11(2), 89–102.Google Scholar
  16. Foshee, V. A., Bauman, K. E., & Linder, G. F. (1999). Family violence and the perpetration of adolescent dating violence: Examining social learning and social control processes. Journal of Marriage and the Family, 61(2), 331–342.Google Scholar
  17. Garrett, E. S., & Zeger, S. L. (2000). Latent class model diagnosis. Biometrics, 56(4), 1055–1067.Google Scholar
  18. Gelman, A., Meng, X. L., & Stern, H. (1996). Posterior predictive assessment of model fitness via realized discrepancies. Statistica Sinica, 6(4), 733–760.Google Scholar
  19. Geneletti, S. (2007). Identifying direct and indirect effects in a non-counterfactual framework. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 69(2), 199–215.Google Scholar
  20. Gollob, H., & Reichardt, C. (1991). Interpreting and estimating indirect effects assuming time lags really matter. In L. Collins & J. Horn (Eds.), Best methods for the analysis of change: Recent advances, unanswered questions, future directions (pp. 243–259). Washington, D.C: American Psychological Association.Google Scholar
  21. Green, D. E. (1979). Teenage smoking: Immediate and long-term patterns. Washington, D.C: U.S. Government Printing Office.Google Scholar
  22. Hafeman, D. M., & VanderWeele, T. J. (2011). Alternative assumptions for the identification of direct and indirect effects. Epidemiology, 22(6), 753–764.Google Scholar
  23. Hayes, A. F., & Preacher, K. J. (2014). Statistical mediation analysis with a multicategorical independent variable. British Journal of Mathematical and Statistical Psychology, 67(3), 451–470.Google Scholar
  24. Heagerty, P. J., & Comstock, B. A. (2013). Exploration of lagged associations using longitudinal data. Biometrics, 69(1), 197–205.Google Scholar
  25. Hoyle, R. H., & Kenny, D. A. (1999). Sample size, reliability, and tests of statistical mediation. In R. H. Hoyle (Ed.), Statistical strategies for small sample research (pp. 195–222). Thousand Oaks: Sage.Google Scholar
  26. Huang, J., & Yuan, Y. (2017). Bayesian dynamic mediation analysis. Psychological Methods, 22(4), 667.Google Scholar
  27. Husten, C. G., McCarty, M. C., Giovino, G. A., Chrismon, J. H., & Zhu, B. P. (1998). Intermittent smokers: A descriptive analysis of persons who have never smoked daily. American Journal of Public Health, 88(1), 86–89.Google Scholar
  28. Imai, K., Keele, L., & Tingley, D. (2010a). A general approach to causal mediation analysis. Psychological Methods, 15(4), 309.Google Scholar
  29. Imai, K., Keele, L., & Yamamoto, T. (2010b). Identification, inference and sensitivity analysis for causal mediation effects. Statistical Science, 25(1), 51–71.Google Scholar
  30. Jarvis, M. J. (2004). Why people smoke. BMJ, 328(7434), 277–279.Google Scholar
  31. Jullion, A., & Lambert, P. (2007). Robust specification of the roughness penalty prior distribution in spatially adaptive Bayesian \(P\)-splines models. Computational Statistics & Data Analysis, 51(5), 2542–2558.Google Scholar
  32. Joffe, M. M., Small, D., & Hsu, C. Y. (2007). Defining and estimating intervention effects for groups that will develop an auxiliary outcome. Statistical Science, 22(1), 74–97.Google Scholar
  33. Kirchner, T. R., & Sayette, M. A. (2007). Effects of smoking abstinence and alcohol consumption on smoking-related outcome expectancies in heavy smokers and tobacco chippers. Nicotine & Tobacco Research, 9(3), 365–376.Google Scholar
  34. Lau, R. S., & Cheung, G. W. (2010). Estimating and comparing specific mediation effects in complex latent variable models. Organizational Research Methods.  https://doi.org/10.1177/1094428110391673.
  35. Lu, Z., & Song, X. (2012). Finite mixture varying coefficient models for analyzing longitudinal heterogenous data. Statistics in Medicine, 31(6), 544–560.Google Scholar
  36. MacKinnon, D. P. (2000). Contrasts in multiple mediator models. In J. S. Rose, L. Chassin, C. C. Presson, & S. J. Sherman (Eds.), Multivariate applications in substance use research: New methods for new questions (pp. 141–160). Mahwah: Lawrence Erlbaum Associates Publishers.Google Scholar
  37. MacKinnon, D. P., Lockwood, C. M., Homan, J. M., West, S. G., & Sheets, V. (2002). A comparison of methods to test mediation and other intervening variable effects. Psychological Methods, 7(1), 83.Google Scholar
  38. MacKinnon, D. P., Warsi, G., & Dwyer, J. H. (1995). A simulation study of mediated effect measures. Multivariate Behavioral Research, 30(1), 41–62.Google Scholar
  39. Norman, G. J., Velicer, W. F., Fava, J. L., & Prochaska, J. O. (2000). Cluster subtypes within stage of change in a representative sample of smokers. Addictive Behaviors, 25(2), 183–204.Google Scholar
  40. Pearl, J. (2001). Direct and indirect effects. In Proceedings of the seventeenth conference on uncertainty in artificial intelligence (pp. 411–420). Morgan Kaufmann Publishers Inc.Google Scholar
  41. Petersen, M. L., Sinisi, S. E., & van der Laan, M. J. (2006). Estimation of direct causal effects. Epidemiology, 17(3), 276–284.Google Scholar
  42. Poland, B. D., Cohen, J. E., Ashley, M. J., Adlaf, E., Ferrence, R., Pederson, L. L., et al. (2000). Heterogeneity among smokers and non-smokers in attitudes and behaviour regarding smoking and smoking restrictions. Tobacco Control, 9(4), 364–371.Google Scholar
  43. 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(3), 879–891.Google Scholar
  44. Reitzel, L. R., Cromley, E. K., Li, Y., et al. (2011). The effect of tobacco outlet density and proximity on smoking relapse during a specific quit attempt. American Journal of Public Health, 101, 315–320.Google Scholar
  45. Roberts, G. O., & Rosenthal, J. S. (2009). Examples of adaptive MCMC. Journal of Computational and Graphical Statistics, 18(2), 349–367.Google Scholar
  46. Robins, J. M. (2003). Semantics of casual DAG models and the identification of direct and indirect effects. In P. J. Green, N. L. Hjort, & S. Richardson (Eds.), Highly structured stochastic systems (pp. 70–81). Oxford: Oxford University Press.Google Scholar
  47. Robins, J. M., & Greenland, S. (1992). Identifiability and exchangeability for direct andindirect effects. Epidemiology, 3(2), 143–155.Google Scholar
  48. Robins, J. M., Hernan, M. A., & Brumback, B. (2000). Marginal structural models and causal inference in epidemiology. Epidemiology, 11, 550–560.Google Scholar
  49. Robins, J. M., & Richardson, T. S. (2010). Alternative graphical causal models and the identification of direct effects. In Causality and psychopathology: Finding the determinants of disorders and their cures (pp. 103–158).Google Scholar
  50. Rubin, D. B. (1974). Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of Educational Psychology, 66(5), 688–701.Google Scholar
  51. Rubin, D. B. (1990). Comment: Neyman (1923) and causal inference in experiments and observational studies. Statistical Science, 5(4), 472–480.Google Scholar
  52. Rubin, D. B. (2000). Causal inference without counterfactuals: Comment. Journal of the American Statistical Association, 95(450), 435–438.Google Scholar
  53. Rubin, D. B. (2004). Direct and indirect causal effects via potential outcomes. Scandinavian Journal of Statistics, 31(2), 161–170.Google Scholar
  54. Ruppert, D. (2002). Selecting the number of knots for penalized splines. Journal of Computational and Graphical Statistics, 11(4), 735–757.Google Scholar
  55. Ruppert, D., Wand, M. P., & Carroll, R. J. (2003). Semiparametric regression. New York: Cambridge University Press.Google Scholar
  56. Schneider, J. E., Reid, R. J., Peterson, N. A., Lowe, J. B., & Hughey, J. (2005). Tobacco outlet density and demographics at the tract level of analysis in Iowa: Implications for environmentally based prevention initiatives. Prevention Science, 6(4), 319–25.Google Scholar
  57. Shiyko, M. P., Lanza, S. T., Tan, X., Li, R., & Shiffman, S. (2012). Using the time-varying effect model (TVEM) to examine dynamic associations between negative affect and self-confidence on smoking urges: Differences between successful quitters and relapsers. Prevention Science, 13(3), 288–299.Google Scholar
  58. Spiegelhalter, D. J., Best, N. G., Carlin, B. P., & Van Der Linde, A. (2002). Bayesian measures of model complexity and fit. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 64(4), 583–639.Google Scholar
  59. Sullivan, P. F., & Kendler, K. S. (1999). The genetic epidemiology of smoking. Nicotine & Tobacco Research, 1(Suppl2), S51–S57.Google Scholar
  60. Ten Have, T. R., Elliott, M. R., Joffe, M., Zanutto, E., & Datto, C. (2004). Causal models for randomized physician encouragement trials in treating primary care depression. Journal of the American Statistical Association, 99(465), 16–25.Google Scholar
  61. Ten Have, T. R., Joffe, M. M., Lynch, K. G., Brown, G. K., Maisto, S. A., & Beck, A. T. (2007). Causal mediation analyses with rank preserving models. Biometrics, 63(3), 926–934.Google Scholar
  62. 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(2), 137.Google Scholar
  63. VanderWeele, T. J., Tchetgen, E. J. T., Cornelis, M., & Kraft, P. (2014). Methodological challenges in Mendelian randomization. Epidemiology, 25(3), 427.Google Scholar
  64. VanderWeele, T., & Vansteelandt, S. (2009). Conceptual issues concerning mediation, interventions and composition. Statistics and Its Interface, 2, 457–468.Google Scholar
  65. VanderWeele, T. J., & Vansteelandt, S. (2010). Odds ratios for mediation analysis for a dichotomous outcome. American Journal of Epidemiology, 172(12), 1339–1348.Google Scholar
  66. Velicer, W. F., Redding, C. A., Sun, X., & Prochaska, J. O. (2007). Demographic variables, smoking variables, and outcome across five studies. Health Psychology, 26(3), 278.Google Scholar
  67. West, S. G., & Aiken, L. S. (1997). Toward understanding individual effects in multicomponent prevention programs: Design and analysis strategies. In K. J. Bryant, M. Windle, & S. G. West (Eds.), The science of prevention: Methodological advances from alcohol and substance abuse research (pp. 167–209). Washington, D.C: American Psychological Association.Google Scholar
  68. Wetter, D. W., McClure, J. B., Cofta-Woerpel, L., Costello, T. J., Reitzel, L. R., Businelle, M. S., et al. (2011). A randomized clinical trial of a palmtop computer-delivered treatment for smoking relapse prevention among women. Psychology of Addictive Behaviors, 25(2), 365.Google Scholar
  69. Yuan, Y., & MacKinnon, D. P. (2009). Bayesian mediation analysis. Psychological Methods, 14(4), 301.Google Scholar

Copyright information

© The Psychometric Society 2019

Authors and Affiliations

  1. 1.Department of Biostatistics, Epidemiology and InformaticsThe University of PennsylvaniaPhiladelphiaUSA
  2. 2.Department of BiostatisticsThe University of Texas MD Anderson Cancer CenterHoustonUSA
  3. 3.Huntsman Center for HOPE and the Department of Population Health SciencesThe University of UtahSalt Lake CityUSA

Personalised recommendations