Skip to main content
Grant Details

Grant Number: 7R01CA183854-05 Interpret this number
Primary Investigator: Daniels, Michael
Organization: University Of Florida
Project Title: Bayesian Approaches for Missingness and Causality in Cancer and Behavior Studies
Fiscal Year: 2017
Back to top


DESCRIPTION (provided by applicant): This proposal will develop novel Bayesian approaches to handle missingness and conduct causal inference for important problems in biomedical research with particular relevance to cancer and behavioral studies. Missing data is a major problem in clinical studies. Of late, more e ort is spent to try to minimize the amount of missingness, but it remains a problem. We will address several pressing complications in the analysis of incomplete data in clinical settings as documented in a recent National Academies of Science report, including assessing model t to the observed data, developing Bayesian approaches for auxiliary covariates, and nonparametric modeling of nonignorable missingness. The mechanisms of treatment effectiveness are of particular interest in behavioral trials. Specifically, how do different processes mediate the effect of an intervention? This can facilitate constructing future interventions. However, determining the causal effect of such 'mediators' on the outcomes is difficult. We will develop new approaches to identify these effects in complex settings with multiple mediators and longitudinal mediators for which little work has been done. Another important question is how to de ne and identify causal effects of interventions on outcomes in the setting of semi-competing risks. Semi-competing risks occur in studies where a progression endpoint may be pre-empted by death or censored due to loss to follow-up or study termination. Subjects who experience a progression event are also followed for survival, which may be censored. Data of this form has been termed semi-competing risks data. This paradigm is particularly relevant to certain brain cancer trials, where the semi-competing risks are death and cerebellar progression. For all these settings, a Bayesian approach is ideal as it allows one to appropriately characterize uncertainty about invariable assumptions (which are present in all these problems). The methods developed here will help answer numerous important clinical questions including the mechanisms of behavior change, both in weight management and smoking cessation, via the ability to appropriately assess mediation, and the joint causal effect of treatment on time to death and cerebellar progression in brain cancer. We will disseminate code for these methods (via the PI's webpage) to ensure the methods will be readily usable by investigators in their own studies. The history of the PI's collaboration with the PI's of the individual clinical studies and the statistician co- investigators will help the team produce the best science and facilitate dissemination of our clinical findings and new methods to the appropriate audience via both subject matter publications and presentations at relevant conferences.

Back to top


A note on compatibility for inference with missing data in the presence of auxiliary covariates.
Authors: Daniels M.J. , Luo X. .
Source: Statistics In Medicine, 2018-11-18 00:00:00.0; , .
EPub date: 2018-11-18 00:00:00.0.
PMID: 30450746
Related Citations

Optimizing and evaluating biomarker combinations as trial-level general surrogates.
Authors: Gabriel E.E. , Sachs M.C. , Daniels M.J. , Halloran M.E. .
Source: Statistics In Medicine, 2018-10-10 00:00:00.0; , .
EPub date: 2018-10-10 00:00:00.0.
PMID: 30306600
Related Citations

A Bayesian semiparametric latent variable approach to causal mediation.
Authors: Kim C. , Daniels M. , Li Y. , Milbury K. , Cohen L. .
Source: Statistics In Medicine, 2017-12-18 00:00:00.0; , .
EPub date: 2017-12-18 00:00:00.0.
PMID: 29250817
Related Citations

ARMA Cholesky Factor Models for the Covariance Matrix of Linear Models.
Authors: Lee K. , Baek C. , Daniels M.J. .
Source: Computational Statistics & Data Analysis, 2017 Nov; 115, p. 267-280.
EPub date: 2017-05-18 00:00:00.0.
PMID: 29109594
Related Citations

Modeling the causal effect of treatment initiation time on survival: Application to HIV/TB co-infection.
Authors: Hu L. , Hogan J.W. , Mwangi A.W. , Siika A. .
Source: Biometrics, 2017-09-28 00:00:00.0; , .
EPub date: 2017-09-28 00:00:00.0.
PMID: 28960243
Related Citations

Comparing biomarkers as trial level general surrogates.
Authors: Gabriel E.E. , Daniels M.J. , Halloran M.E. .
Source: Biometrics, 2016 Dec; 72(4), p. 1046-1054.
PMID: 27038302
Related Citations

A note on posterior predictive checks to assess model fit for incomplete data.
Authors: Xu D. , Chatterjee A. , Daniels M. .
Source: Statistics In Medicine, 2016-11-30 00:00:00.0; 35(27), p. 5029-5039.
EPub date: 2016-11-30 00:00:00.0.
PMID: 27426216
Related Citations

Inference In Randomized Trials With Death And Missingness
Authors: Wang C. , Scharfstein D.O. , Colantuoni E. , Girard T.D. , Yan Y. .
Source: Biometrics, 2016-10-17 00:00:00.0; , .
PMID: 27753071
Related Citations

A Framework For Bayesian Nonparametric Inference For Causal Effects Of Mediation
Authors: Kim C. , Daniels M.J. , Marcus B.H. , Roy J.A. .
Source: Biometrics, 2016-08-01 00:00:00.0; , .
PMID: 27479682
Related Citations

Sequential BART for imputation of missing covariates.
Authors: Xu D. , Daniels M.J. , Winterstein A.G. .
Source: Biostatistics (oxford, England), 2016 Jul; 17(3), p. 589-602.
PMID: 26980459
Related Citations

A Bayesian Nonparametric Approach To Marginal Structural Models For Point Treatments And A Continuous Or Survival Outcome
Authors: Roy J. , Lum K.J. , Daniels M.J. .
Source: Biostatistics (oxford, England), 2016-06-26 00:00:00.0; , .
PMID: 27345532
Related Citations

Covariance Partition Priors: A Bayesian Approach to Simultaneous Covariance Estimation for Longitudinal Data.
Authors: Gaskins J.T. , Daniels M.J. .
Source: Journal Of Computational And Graphical Statistics : A Joint Publication Of American Statistical Association, Institute Of Mathematical Statistics, Interface Foundation Of North America, 2016-01-02 00:00:00.0; 25(1), p. 167-186.
EPub date: 2016-01-02 00:00:00.0.
PMID: 27175055
Related Citations

Quantile regression in the presence of monotone missingness with sensitivity analysis.
Authors: Liu M. , Daniels M.J. , Perri M.G. .
Source: Biostatistics (oxford, England), 2016 Jan; 17(1), p. 108-21.
PMID: 26041008
Related Citations

Causal inference with longitudinal outcomes and non-ignorable drop-out: Estimating the effect of living alone on cognitive decline.
Authors: Josefsson M. , de Luna X. , Daniels M.J. , Nyberg L. .
Source: Journal Of The Royal Statistical Society. Series C, Applied Statistics, 2016-01-01 00:00:00.0; 65(1), p. 131-144.
EPub date: 2016-01-01 00:00:00.0.
PMID: 26839439
Related Citations

A General Framework For Considering Selection Bias In Ehr-based Studies: What Data Are Observed And Why?
Authors: Haneuse S. , Daniels M. .
Source: Egems (washington, Dc), 2016; 4(1), p. 1203.
PMID: 27668265
Related Citations

Bayesian Nonparametric Estimation For Dynamic Treatment Regimes With Sequential Transition Times
Authors: Xu Y. , Müller P. , Wahed A.S. , Thall P.F. .
Source: Journal Of The American Statistical Association, 2016; 111(515), p. 921-935.
PMID: 28018015
Related Citations

Bayesian methods for nonignorable dropout in joint models in smoking cessation studies.
Authors: Gaskins J.T. , Daniels M.J. , Marcus B.H. .
Source: Journal Of The American Statistical Association, 2016; 111(516), p. 1454-1465.
EPub date: 2017-01-05 00:00:00.0.
PMID: 29104333
Related Citations

Pattern mixture models for the analysis of repeated attempt designs.
Authors: Daniels M.J. , Jackson D. , Feng W. , White I.R. .
Source: Biometrics, 2015 Dec; 71(4), p. 1160-7.
PMID: 26149119
Related Citations

Are all biases missing data problems?
Authors: Howe C.J. , Cain L.E. , Hogan J.W. .
Source: Current Epidemiology Reports, 2015-09-01 00:00:00.0; 2(3), p. 162-171.
EPub date: 2015-09-01 00:00:00.0.
PMID: 26576336
Related Citations

Bayesian modeling of the covariance structure for irregular longitudinal data using the partial autocorrelation function.
Authors: Su L. , Daniels M.J. .
Source: Statistics In Medicine, 2015-05-30 00:00:00.0; 34(12), p. 2004-18.
EPub date: 2015-05-30 00:00:00.0.
PMID: 25762065
Related Citations

A Flexible Bayesian Approach to Monotone Missing Data in Longitudinal Studies with Nonignorable Missingness with Application to an Acute Schizophrenia Clinical Trial.
Authors: Linero A.R. , Daniels M.J. .
Source: Journal Of The American Statistical Association, 2015 Mar; 110(509), p. 45-55.
PMID: 26236060
Related Citations

A Bayesian nonparametric approach to causal inference on quantiles.
Authors: Xu D. , Daniels M.J. , Winterstein A.G. .
Source: Biometrics, 2018 09; 74(3), p. 986-996.
EPub date: 2018-02-25 00:00:00.0.
PMID: 29478267
Related Citations

Back to Top