Journal of the Korean Data and Information Science Society

The Korean Data and Information Science Society (한국데이터정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Simple power analysis in causal mediation models for a dichotomous outcome based on the mediation proportion

  • Received : 2017.03.16
  • Accepted : 2017.05.08
  • Published : 2017.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

Mediation models are widely used in many fields of research and have recently gained attention in epidemiology. The mediation proportion is a standard measure to evaluate what part of the total exposure effect on an outcome may be explained by a particular mediator and to examine how important that pathway is relative to the overall exposure effect. A common question is how large a sample size is needed to achieve high statistical power or, equivalently, what magnitude of effect can be detected. Current power and sample size calculations for mediation analysis are limited and additional research is needed. We therefore propose a computer-intensive power analysis using the mediation proportion. We conduct simulation studies to calculate statistical powers and sample sizes. And then, we illustrate our power analysis using an example from the Adult Health Study of atomic-bomb survivors and demonstrate that the method is relatively straightforward to understand and compute.

Keywords

References

  1. Akahoshi, M., Amasaki, Y., Soda, M., Hida, A., Imaizumi, M., Nashima, E., Maeda, R., Seto, S. and Yano, K. (2003). Effects of radiation on fatty liver and metabolic coronary risk factors among atomic bomb survivors in Nagasaki. Hypertension Research, 6, 965-970.
  2. Baron, R. M. and 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. https://doi.org/10.1037/0022-3514.51.6.1173
  3. Carpenter, J. and Bithell, J. (2000). Bootstrap confidence intervals: When, which, what? A practical guide for medical statisticians. Statistics in Medicine, 19, 1141-1164. https://doi.org/10.1002/(SICI)1097-0258(20000515)19:9<1141::AID-SIM479>3.0.CO;2-F
  4. Cohen, J. (1988). Statistical power analysis for the behavior sciences 2nd edition. Lawrence Eribaum Associates, New Jersey.
  5. Davison, A. C., and Hinkley, D. V. (1997).Bootstrap methods and their application. Cambridge University Press.
  6. Ditlevsen, S., Christensen, U., Lynch, J., Damsgaard, M. T. and Keiding, N. (2005). The mediation proportion : A structural equation approach for estimating the proportion of exposure effect on outcome explained by an intermediate variable. Epidemiology, 16, 114-120. https://doi.org/10.1097/01.ede.0000147107.76079.07
  7. Freedman, L. S., Graubard, B. I. and Schatzkin, A. (1992). Statistical validation of intermediate endpoints for chronic diseases. Statistics in Medicine, 11, 167-178. https://doi.org/10.1002/sim.4780110204
  8. Fritz, M. S. and MacKinnon, D. P. (2007). Required sample size to detect the mediated effect. Psychological science, 18, 233-239. https://doi.org/10.1111/j.1467-9280.2007.01882.x
  9. Hafeman, D. M. and Schwartz, S. (2009). Opening the black box: a motivation for the assessment of mediation. American Journal of Epidemiology, 38, 838-845.
  10. Hernan, M. A. (2004). A definition of causal effect for epidemiological research. Journal of Epidemiology and Community Health, 58, 265-271. https://doi.org/10.1136/jech.2002.006361
  11. Hong Y., Jang, G. and Choi, C. (2016). Life satisfaction and self-esteem of children from low-income class: Testing mediation model of depression. Journal of the Korean Data & Information Science Society, 27, 179-189. https://doi.org/10.7465/jkdi.2016.27.1.179
  12. Ito, C., Maeda, R., Ishida, S., Sasaki, H. and Harada, H. (2000). Correlation among fasting plasma glucose, two-hour plasma glucose levels in OGTT and HbA1c. Diabetes Research and Clinical Practice, 50, 225-230.
  13. Jeong, K. (2017). Quantile causality from dollar exchange rate to international oil price. Journal of the Korean Data & Information Science Society, 28, 367-369.
  14. Kenny, D. A. and Judd, C. M. (2014). Power anomalies in testing mediation. Psychological science, 25, 334-339. https://doi.org/10.1177/0956797613502676
  15. Lynch, J. W., Kaplan, G. A., Cohen, R. D., Tuomilehto, J. and Salonen, J. T. (1996). Do cardiovascular risk factors explain the relation between socioeconomic status, risk of all-cause mortality, cardiovascular mortality and acute myocardial infarction? American Journal of Epidemiology, 144, 934-942. https://doi.org/10.1093/oxfordjournals.aje.a008863
  16. MacKinnon, D. P. (2008). An introduction to statistical mediation analysis. Lawrence Erlbaum Associates, New York.
  17. Nakanishi, S., Yamada, M., Hattori, N. and Suzuki, G. (2005). Relationship between HbA(1)c and mortality in a Japanese population. Diabetologia, 48, 230-234. https://doi.org/10.1007/s00125-004-1643-9
  18. Ozasa, K., Shimizu, Y., Suyama, A., Kasagi, F., Soda, M., Grant, E. J., Sakata, R., Sugiyama, H. and Kodama, K. (2012). Studies of the mortality of atomic bomb survivors, Report 14, 1950-2003: An overview of cancer and noncancer diseases. Radiation Research, 177, 229-243. https://doi.org/10.1667/RR2629.1
  19. Pearl, J. (2001). Direct and indirect effects. In: Proceedings of the seventeenth conference on uncertainty and artificial intelligence. San Francisco, CA: Morgan Kaufmann 411-420.
  20. Preacher, K. J. and Kelley, K. (2011). Effect size measures for mediation models: quantitative strategies for communicating indirect effects. Psychological Methods, 16, 93-115. https://doi.org/10.1037/a0022658
  21. Preacher, K. J. and Selig, J. P. (2012). Advantages of Monte Carlo confidence intervals for indirect effects. Communication Methods and Measures, 6, 77-98. https://doi.org/10.1080/19312458.2012.679848
  22. Richiardi, L., Bellocco, R. and Zugna, D. (2013). Mediation analysis in epidemiology: methods, interpretation and bias. International Journal of Epidemiology, 42, 1511-1519. https://doi.org/10.1093/ije/dyt127
  23. Robin, J. M. and Greenland, S. (1992). Identifiability and exchangeability for direct and indirect effects. Epidemiology, 3, 143-155. https://doi.org/10.1097/00001648-199203000-00013
  24. Rubin, D. B. (1990). Formal mode of statistical inference for causal effects. Journal of Statistical Planning and Inference, 25, 279-292. https://doi.org/10.1016/0378-3758(90)90077-8
  25. Saito, I., Kokubo, Y., Yamagishi, K., Iso, H. and Inoue, M. (2011). Diabetes and the risk of coronary heart disease in the general Japanese population: The Japan public health center-based prospective (JPHC) study. Atherosclerosis, 216, 187-191. https://doi.org/10.1016/j.atherosclerosis.2011.01.021
  26. Sedlmaier, P. and Gigerenzer, G. (1989). Do studies of statistical power have an effect on the power of studies? Psychological Bulletin, 105, 309-316. https://doi.org/10.1037/0033-2909.105.2.309
  27. Tsiatis, A. A., DeGruttola, V. and Wulfsohn, M. S. (1995). Modeling the relationship of survival to longitudinal data measured with error: Applications to survival and CD4 counts in patients with AIDs. Journal of the American Statistical Association, 90, 27-37. https://doi.org/10.1080/01621459.1995.10476485
  28. Valeri, L. and 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. https://doi.org/10.1037/a0031034
  29. VanderWeele, T. J. (2015). Explanation in causal inference: Methods for mediation and interaction. Oxford University Press, New York, U.S.A.
  30. VanderWeele, T. J. and Vansteeland, S. (2010). Odds ratios for mediation analysis for a dichotomous outcome. American Journal of Epidemiology, 172, 1339-1348. https://doi.org/10.1093/aje/kwq332
  31. Vittinghoff, E. and Neilands, T. B. (2015). Sample size for joint testing of indirect effects. Prevention Science, 16, 1128-1135. https://doi.org/10.1007/s11121-014-0528-5
  32. Vittinghoff, E. Sen, S. and McCulloch, C. E. (2009). Sample size calculations for evaluating mediation. Statistics in Medicine, 28, 541-557. https://doi.org/10.1002/sim.3491
  33. Wang, C. and Xue, X. (2012). Power and sample size calculations for evaluating mediation effects in longitudinal studies. Statistical methods in Medical Research, 25, 686-705.
  34. Wang, Y. and Taylor, J. M. G. (2002). A measure of the proportion of treatment effect explained by a surrogate marker. Biometrics, 58, 803-812. https://doi.org/10.1111/j.0006-341X.2002.00803.x
  35. Yamada, M., Wong, F. L., Fujiwara, S., Akahoshi, M. and Suzuki, G. (2004). Noncancer disease incidence in atomic bomb survivors, 1958-1998. Radiation Research, 161, 622-632. https://doi.org/10.1667/RR3183
  36. Zhang, Z. (2014). Monte Carlo based statistical power analysis for mediation models: Methods and software. Behavior Research Methods, 46, 1184-1198. https://doi.org/10.3758/s13428-013-0424-0

Cited by

  1. Causal mediation analysis in nested case‐control studies using conditional logistic regression vol.62, pp.8, 2017, https://doi.org/10.1002/bimj.201900120