Mediation analysis for survival data using semiparametric probit models

Causal mediation modeling has become a popular approach for studying the effect of an exposure on an outcome through mediators. Currently, the literature on mediation analyses with survival outcomes largely focused on settings with a single mediator and quantified the mediation effects on the hazard, log hazard and log survival time (Lange and Hansen 2011; VanderWeele 2011). In this article, we propose a multi-mediator model for survival data by employing a flexible semiparametric probit model. We characterize path-specific effects (PSEs) of the exposure on the outcome mediated through specific mediators. We derive closed form expressions for PSEs on a transformed survival time and the survival probabilities. Statistical inference on the PSEs is developed using a nonparametric maximum likelihood estimator under the semiparametric probit model and the functional Delta method. Results from simulation studies suggest that our proposed methods perform well in finite sample. We illustrate the utility of our method in a genomic study of glioblastoma multiforme survival.

[1]  R. Pazdur,et al.  Approval Summary: Azacitidine for Treatment of Myelodysplastic Syndrome Subtypes , 2005, Clinical Cancer Research.

[2]  James M. Robins,et al.  Effect decomposition in the presence of an exposure-induced mediator-outcome confounder. , 2014, Epidemiology.

[3]  Judea Pearl,et al.  Direct and Indirect Effects , 2001, UAI.

[4]  Mohamed F Ghalwash,et al.  DNA methylation differences at growth related genes correlate with birth weight: a molecular signature linked to developmental origins of adult disease? , 2012, BMC Medical Genomics.

[5]  Hiromu Suzuki,et al.  DNA methylation and microRNA dysregulation in cancer , 2012, Molecular oncology.

[6]  J. Kalbfleisch,et al.  The Statistical Analysis of Failure Time Data: Kalbfleisch/The Statistical , 2002 .

[7]  J. Kalbfleisch,et al.  The Statistical Analysis of Failure Time Data , 1980 .

[8]  L. Thygesen,et al.  Assessing natural direct and indirect effects through multiple pathways. , 2014, American journal of epidemiology.

[9]  R. Gill,et al.  Cox's regression model for counting processes: a large sample study : (preprint) , 1982 .

[10]  J. Issa,et al.  Phase II study of low-dose decitabine in patients with chronic myelogenous leukemia resistant to imatinib mesylate. , 2005, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[11]  Thomas Brox,et al.  Maximum Likelihood Estimation , 2019, Time Series Analysis.

[12]  H. Zou,et al.  Regularized rank-based estimation of high-dimensional nonparanormal graphical models , 2012, 1302.3082.

[13]  David R. Cox,et al.  Regression models and life tables (with discussion , 1972 .

[14]  Donglin Zeng,et al.  Maximum likelihood estimation in semiparametric regression models with censored data , 2007, Statistica Sinica.

[15]  Eric J. Tchetgen Tchetgen,et al.  On causal mediation analysis with a survival outcome. , 2011 .

[16]  Jeffrey M Albert,et al.  Generalized Causal Mediation Analysis , 2011, Biometrics.

[17]  T J VanderWeele,et al.  Mediation Analysis with Multiple Mediators , 2014, Epidemiologic methods.

[18]  Joel L. Horowitz,et al.  Semiparametric Estimation of a Regression Model with an Unknown Transformation of the Dependent Variable , 1996 .

[19]  Tyler J VanderWeele,et al.  Causal Mediation Analysis With Survival Data , 2011, Epidemiology.

[20]  J. Klein,et al.  Statistical Models Based On Counting Process , 1994 .

[21]  P. Jia,et al.  SZGR: a comprehensive schizophrenia gene resource , 2009, Molecular Psychiatry.

[22]  J. Seoane,et al.  Glioblastoma Multiforme: A Look Inside Its Heterogeneous Nature , 2014, Cancers.

[23]  Yen-Tsung Huang,et al.  Integrative modeling of multi‐platform genomic data under the framework of mediation analysis , 2015, Statistics in medicine.

[24]  J. Pearl,et al.  Title Identifiability of Path-Specific Effects Permalink , 2005 .

[25]  Cheng Li,et al.  Adjusting batch effects in microarray expression data using empirical Bayes methods. , 2007, Biostatistics.

[26]  Theis Lange,et al.  Direct and Indirect Effects in a Survival Context , 2011, Epidemiology.

[27]  Yi Li,et al.  Semiparametric transformation models for semicompeting survival data , 2014, Biometrics.

[28]  Xiaoyan Lin,et al.  A semiparametric probit model for case 2 interval‐censored failure time data , 2010, Statistics in medicine.

[29]  L. Keele,et al.  Identification, Inference and Sensitivity Analysis for Causal Mediation Effects , 2010, 1011.1079.

[30]  John K Wiencke,et al.  A novel approach to the discovery of survival biomarkers in glioblastoma using a joint analysis of DNA methylation and gene expression , 2014, Epigenetics.

[31]  Roger W. Klein,et al.  Shift Restrictions and Semiparametric Estimation in Ordered Response Models , 2002 .

[32]  John D. Kalbfleisch,et al.  The Statistical Analysis of Failure Data , 1986, IEEE Transactions on Reliability.

[33]  S. Bennett,et al.  Analysis of survival data by the proportional odds model. , 1983, Statistics in medicine.

[34]  J. Robins,et al.  Identifiability and Exchangeability for Direct and Indirect Effects , 1992, Epidemiology.

[35]  D. A. Kenny,et al.  The moderator-mediator variable distinction in social psychological research: conceptual, strategic, and statistical considerations. , 1986, Journal of personality and social psychology.