Power of testing for exposure effects under incomplete mediation
-
Ruixuan R. Zhou
Abstract
Mediation analysis studies situations where an exposure may affect an outcome both directly and indirectly through intervening variables called mediators. It is frequently of interest to test for the effect of the exposure on the outcome, and the standard approach is simply to regress the latter on the former. However, it seems plausible that a more powerful test statistic could be achieved by also incorporating the mediators. This would be useful in cases where the exposure effect size might be small, which for example is common in genomics applications. Previous work has shown that this is indeed possible under complete mediation, where there is no direct effect. In most applications, however, the direct effect is likely nonzero. In this paper we study linear mediation models and find that under certain conditions, power gain is still possible under this incomplete mediation setting for testing the null hypothesis that there is neither a direct nor an indirect effect. We study a class of procedures that can achieve this performance and develop their application to both low- and high-dimensional mediators. We then illustrate their performances in simulations as well as in an analysis using DNA methylation mediators to study the effect of cigarette smoking on gene expression.
Acknowledgment
The results shown here are in whole or part based upon data generated by the TCGA Research Network: https://www.cancer.gov/tcga. The authors thank Dr. Yen-Tsung Huang for help obtaining the data.
-
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
-
Research funding: None declared.
-
Conflict of interest statement: The authors declare no conflicts of interest regarding this article.
References
1. Hayes, AF. Introduction to mediation, moderation, and conditional process analysis: a regression-based approach. New York: Guilford Press; 2013.Search in Google Scholar
2. Huang, YT, VanderWeele, TJ, Lin, X. Joint analysis of snp and gene expression data in genetic association studies of complex diseases. Ann Appl Stat 2014;8:352. https://doi.org/10.1214/13-aoas690.Search in Google Scholar
3. MacKinnon, DP. Introduction to statistical mediation analysis. New York: Routledge; 2008.Search in Google Scholar
4. Nicolae, DL, Gamazon, E, Zhang, W, Duan, S, Dolan, ME, Cox, NJ. Trait-associated SNPs are more likely to be eQTLs: annotation to enhance discovery from GWAS. PLoS Genet 2010;6:e1000888. https://doi.org/10.1371/journal.pgen.1000888.Search in Google Scholar PubMed PubMed Central
5. Hirschhorn, JN, Daly, MJ. Genome-wide association studies for common diseases and complex traits. Nat Rev Genet 2005;6:95–108. https://doi.org/10.1038/nrg1521.Search in Google Scholar PubMed
6. Manolio, TA, Collins, FS, Cox, NJ, Goldstein, DB, Hindorff, LA, Hunter, DJ, et al.. Finding the missing heritability of complex diseases. Nature 2009;461:747–53. https://doi.org/10.1038/nature08494.Search in Google Scholar PubMed PubMed Central
7. Kenny, DA, Judd, CM. Power anomalies in testing mediation. Psychol Sci 2014;25:334–9. https://doi.org/10.1177/0956797613502676.Search in Google Scholar PubMed
8. Loeys, T, Moerkerke, B, Vansteelandt, S. A cautionary note on the power of the test for the indirect effect in mediation analysis. Front Psychol 2015;5:1549. https://doi.org/10.3389/fpsyg.2014.01549.Search in Google Scholar PubMed PubMed Central
9. O’Rourke, HP, MacKinnon, DP. When the test of mediation is more powerful than the test of the total effect. Behav Res Methods 2015;47:424–42. https://doi.org/10.3758/s13428-014-0481-z.Search in Google Scholar PubMed PubMed Central
10. Wang, K. Understanding power anomalies in mediation analysis. Psychometrika 2018;83:387–406. https://doi.org/10.1007/s11336-017-9598-1.Search in Google Scholar PubMed
11. Zhao, SD, Cai, TT, Li, H. More powerful genetic association testing via a new statistical framework for integrative genomics. Biometrics 2014;70:881–90. https://doi.org/10.1111/biom.12206.Search in Google Scholar PubMed PubMed Central
12. Zhou, RR, Wang, L, Zhao, SD. Estimation and inference for the indirect effect in high-dimensional linear mediation models. Biometrika 2020;107:573–89. https://doi.org/10.1093/biomet/asaa016.Search in Google Scholar PubMed PubMed Central
13. MacKinnon, DP, Krull, JL, Lockwood, CM. Equivalence of the mediation, confounding and suppression effect. Prev Sci 2000;1:173–81. https://doi.org/10.1023/a:1026595011371.10.1023/A:1026595011371Search in Google Scholar
14. Prentice, RL. Surrogate endpoints in clinical trials: definition and operational criteria. Stat Med 1989;8:431–40. https://doi.org/10.1002/sim.4780080407.Search in Google Scholar PubMed
15. VanderWeele, TJ. Surrogate measures and consistent surrogates. Biometrics 2013;69:561–5. https://doi.org/10.1111/biom.12071.Search in Google Scholar PubMed PubMed Central
16. VanderWeele, TJ, Vansteelandt, S. Conceptual issues concerning mediation, interventions and composition. Stat Interface 2009;2:457–68. https://doi.org/10.4310/sii.2009.v2.n4.a7.Search in Google Scholar
17. McFatter, RM. The use of structural equation models in interpreting regression equations including suppressor and enhancer variables. Appl Psychol Meas 1979;3:123–35. https://doi.org/10.1177/014662167900300113.Search in Google Scholar
18. Huang, YT, Pan, WC. Hypothesis test of mediation effect in causal mediation model with high-dimensional continuous mediators. Biometrics 2016;72:402–13. https://doi.org/10.1111/biom.12421.Search in Google Scholar PubMed
19. Zhang, H, Zheng, Y, Hou, L, Zheng, C, Liu, L. Mediation analysis for survival data with high-dimensional mediators. Bioinformatics 2021;37:3815–21. https://doi.org/10.1093/bioinformatics/btab564.Search in Google Scholar PubMed PubMed Central
20. Javanmard, A, Montanari, A. Confidence intervals and hypothesis testing for high-dimensional regression. J Mach Learn Res 2014;15:2869–909.Search in Google Scholar
21. Van de Geer, S, Bühlmann, P, Ritov, Y, Dezeure, R. On asymptotically optimal confidence regions and tests for high-dimensional models. Ann Stat 2014;42:1166–202. https://doi.org/10.1214/14-aos1221.Search in Google Scholar
22. Zhang, CH, Zhang, SS. Confidence intervals for low dimensional parameters in high dimensional linear models. J Roy Stat Soc B Stat Methodol 2014;76:217–42. https://doi.org/10.1111/rssb.12026.Search in Google Scholar
23. Sun, T, Zhang, CH. Scaled sparse linear regression. Biometrika 2012;99:879–98. https://doi.org/10.1093/biomet/ass043.Search in Google Scholar
24. Sun, T. Scalreg: scaled sparse linear regression, 2019. R package version 1.0.1.Search in Google Scholar
25. Gaunt, RE. The basic distributional theory for the product of zero mean correlated normal random variables. Stat Neerl 2022;76:450–70.10.1111/stan.12267Search in Google Scholar
26. Sobel, ME. Asymptotic confidence intervals for indirect effects in structural equation models. Socio Methodol 1982;13:290–312. https://doi.org/10.2307/270723.Search in Google Scholar
27. Barfield, R, Shen, J, Just, AC, Vokonas, PS, Schwartz, J, Baccarelli, AA, et al.. Testing for the indirect effect under the null for genome-wide mediation analyses. Genet Epidemiol 2017;41:824–33. https://doi.org/10.1002/gepi.22084.Search in Google Scholar PubMed PubMed Central
28. Zeilinger, S, Kühnel, B, Klopp, N, Baurecht, H, Kleinschmidt, A, Gieger, C, et al.. Tobacco smoking leads to extensive genome-wide changes in DNA methylation. PLoS One 2013;8:e63812. https://doi.org/10.1371/journal.pone.0063812.Search in Google Scholar PubMed PubMed Central
29. Huang, YT. Variance component tests of multivariate mediation effects under composite null hypotheses. Biometrics 2019;75:1191–204. https://doi.org/10.1111/biom.13073.Search in Google Scholar PubMed
30. Liu, Y, Xie, J. Cauchy combination test: a powerful test with analytic p-value calculation under arbitrary dependency structures. J Am Stat Assoc 2020;115:393–402. https://doi.org/10.1080/01621459.2018.1554485.Search in Google Scholar PubMed PubMed Central
31. Wang, X, Parast, L, Tian, L, Cai, T. Model-free approach to quantifying the proportion of treatment effect explained by a surrogate marker. Biometrika 2020;107:107–22. https://doi.org/10.1093/biomet/asz065.Search in Google Scholar PubMed PubMed Central
Supplementary Material
This article contains supplementary material (https://doi.org/10.1515/ijb-2022-0106).
© 2023 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Research Articles
- Survival analysis using deep learning with medical imaging
- Using a population-based Kalman estimator to model the COVID-19 epidemic in France: estimating associations between disease transmission and non-pharmaceutical interventions
- Approximate reciprocal relationship between two cause-specific hazard ratios in COVID-19 data with mutually exclusive events
- Sensitivity of estimands in clinical trials with imperfect compliance
- Highly robust causal semiparametric U-statistic with applications in biomedical studies
- Hierarchical Bayesian bootstrap for heterogeneous treatment effect estimation
- Penalized logistic regression with prior information for microarray gene expression classification
- Bayesian learners in gradient boosting for linear mixed models
- Unequal allocation of sample/event sizes with considerations of sampling cost for testing equality, non-inferiority/superiority, and equivalence of two Poisson rates
- HiPerMAb: a tool for judging the potential of small sample size biomarker pilot studies
- Heterogeneity in meta-analysis: a comprehensive overview
- On stochastic dynamic modeling of incidence data
- Power of testing for exposure effects under incomplete mediation
- Exact correction factor for estimating the OR in the presence of sparse data with a zero cell in 2 × 2 tables
- Right-censored partially linear regression model with error in variables: application with carotid endarterectomy dataset
- Assessing HIV-infected patient retention in a program of differentiated care in sub-Saharan Africa: a G-estimation approach
- Prediction-based variable selection for component-wise gradient boosting
Articles in the same Issue
- Frontmatter
- Research Articles
- Survival analysis using deep learning with medical imaging
- Using a population-based Kalman estimator to model the COVID-19 epidemic in France: estimating associations between disease transmission and non-pharmaceutical interventions
- Approximate reciprocal relationship between two cause-specific hazard ratios in COVID-19 data with mutually exclusive events
- Sensitivity of estimands in clinical trials with imperfect compliance
- Highly robust causal semiparametric U-statistic with applications in biomedical studies
- Hierarchical Bayesian bootstrap for heterogeneous treatment effect estimation
- Penalized logistic regression with prior information for microarray gene expression classification
- Bayesian learners in gradient boosting for linear mixed models
- Unequal allocation of sample/event sizes with considerations of sampling cost for testing equality, non-inferiority/superiority, and equivalence of two Poisson rates
- HiPerMAb: a tool for judging the potential of small sample size biomarker pilot studies
- Heterogeneity in meta-analysis: a comprehensive overview
- On stochastic dynamic modeling of incidence data
- Power of testing for exposure effects under incomplete mediation
- Exact correction factor for estimating the OR in the presence of sparse data with a zero cell in 2 × 2 tables
- Right-censored partially linear regression model with error in variables: application with carotid endarterectomy dataset
- Assessing HIV-infected patient retention in a program of differentiated care in sub-Saharan Africa: a G-estimation approach
- Prediction-based variable selection for component-wise gradient boosting
