Thank you to all who attended or livestreamed the Advance-CTR Statistical Methods in Translational Science Symposium on June 29, 2018. A recording of the Symposium, along with information about each of the presentations, is below. 

 

Presentations: 

“Lightning Introduction to Causal Inference”
Roee Gutman, PhD
Assistant Professor of Biostatistics
Brown University School of Public Health

--

Tao Liu, PhD
Associate Professor of Biostatistics
Brown University School of Public Health
"Causal Mediation Analysis: Application for Alcohol Behavioral Intervention Research"
This presentation will focus on causal mediation modeling based on the counterfactual (potential outcomes) framework. Emphasis will be placed on conceptual illustration of natural indirect and direct effects and estimation methods. Application to studies related to HIV and alcohol research will be discussed.

--

Roee Gutman, PhD
Assistant Professor of Biostatistics
Brown University School of Public Health
"Estimating the Effects of Health and Medical Interventions using Multiple Imputations and File Linking Techniques"
Estimating the effects of health and medical interventions in observational studies is difficult because differences in outcomes may be attributable to differences in baseline characteristics. Assuming that the assignment to treatment depends only on observed covariates, we describe multiple imputation procedures that predicts patients’ outcomes under the treatment that they did not receive. This assumption requires a large set of covariates that is not always available in one dataset and requires linking datasets that do not always share unique identifiers. The proposed methods allow to link separate data sources without unique identifiers, and they enable estimation of patient specific and population level causal effects. We demonstrate these method with two examples. The first example examines the effects of administering opioids vs. NSAIDS after car accidents, and the second example examines the effects of receiving home-delivered meals on healthcare utilizations.

--

Issa Dahabreh, MD
Assistant Professor of Health Services, Policy and Practice
Assistant Professor of Epidemiology
"Transporting the Results of a Clinical Trial to a New Target Population"
Clinical trials often select participants on the basis of covariates that are also determinants of the outcome and modifiers of the treatment effect. Consequently, the average treatment effect estimated in a trial is not the same as the average effect in other populations in which the trial’s interventions may be applied. In this talk, we consider methods for transporting the results from a completed trial to a new target population. Specifically, we show how a composite dataset, formed by appending data from a completed trial to a sample from the target population, can be used to estimate the average treatment effect in the target population. We examine methods that use the treatment, outcome, and baseline covariate information from the trial, but only baseline covariate data from the sample of the target population. We explain how these “transportability” methods can complement randomized trials as well as “conventional” observational comparative effectiveness analyses.