Harvard University Biostatistics Working Paper Series

Más-o-menos: A Simple Sign Averaging Method for Discrimination in Genomic Data Analysis

Sihai Dave Zhao et al. — Wed, 01 May 2013 09:27:17 PDT

Efficient Estimation of Risk Ratios From Clustered Binary Data

Matthew Cefalu et al. — Thu, 21 Mar 2013 07:15:25 PDT

On the Restricted Mean Event Time in Survival Analysis

Lu Tian et al. — Wed, 27 Feb 2013 07:16:04 PST

A General Regression Framework for a Secondary Outcome in Case-control Studies

Eric J. Tchetgen Tchetgen — Fri, 04 Jan 2013 09:14:55 PST

Nonparametric Inference for Meta Analysis with Fixed Unknown, Study-specific Parameters

Brian Claggett et al. — Thu, 29 Nov 2012 06:32:37 PST

Treatment Selections using Risk-benefit Profiles Based on Data from Comparative Randomized Clinical Trials with Multiple Endpoints

Brian Claggett et al. — Mon, 26 Nov 2012 07:37:54 PST

Robust Estimation of Pure/Natural Direct Effects with Mediator Measurement Error

Eric J. Tchetgen Tchetgen et al. — Wed, 05 Sep 2012 06:06:19 PDT

Locally Efficient Estimation of Marginal Treatment Effects when Outcomes are Correlated: Is the Prize Worth the Chase?

Alisa J. Stephens et al. — Thu, 02 Aug 2012 08:23:10 PDT

Flexible Covariate-adjusted Exact Tests for Randomized Studies

Alisa J. Stephens et al. — Thu, 02 Aug 2012 08:22:57 PDT

Model Averaged Double Robust Estimation

Matthew Cefalu et al. — Tue, 05 Jun 2012 09:39:27 PDT

Existing methods in causal inference do not account for the uncertainty in the selection of confounders. We propose a new class of estimators for the average causal effect, the model averaged double robust estimators, that formally account for model uncertainty in both the propensity score and outcome model through the use of Bayesian model averaging. These estimators build on the desirable double robustness property by only requiring the true propensity score model or the true outcome model be within a specified class of models to maintain consistency. We provide asymptotic results and conduct a large scale simulation study that indicates the model averaged double robust estimator has better finite sample behavior than the usual double robust estimator.

On Identification of Natural Direct Effects when a Confounder of the Mediator is Directly Affected by Exposure

Eric J. Tchetgen Tchetgen et al. — Mon, 04 Jun 2012 07:39:34 PDT

C2BAT: A Novel Method for Association Between Ge- netic Markers and Multiple Phenotypes

Melissa Naylor et al. — Mon, 02 Apr 2012 06:31:03 PDT

The purpose of this technical report is to describe a novel method developed to detect association between a genetic marker and multiple phenotypes. In order to obtain a one-degree of freedom test, a generalized principal component approach is suggested that aggregates the information about the genetic effect in the ﬁrst prin- cipal component, while the remain principal components contain only environment noise. A limited simulation study is done validating the method. For scenarios in which the genetic effect is constant across all measurements and there is no envi- ronmental correlation between the measurements, preliminary results suggest that this method has similar power to standard methods of analysis. Since such setups favor the standard approach, the new method is expected to be efﬁcient for many realistic alternative hypotheses, including those with varying genetic effect sizes across measurements and those accounting for environmental correlation.

Robustness of Measures of Interaction to Unmeasured Confounding

Eric J. Tchetgen Tchetgen et al. — Mon, 12 Mar 2012 08:36:21 PDT

On a Logistic Mixed Model Formulation of a Quadratic Exponential Model for Correlated Binary Outcomes

Eric J. Tchetgen Tchetgen — Wed, 29 Feb 2012 07:01:58 PST

Inverse Odds Ratio-Weighted Estimation for Causal Mediation Analysis

Eric J. Tchetgen Tchetgen — Mon, 13 Feb 2012 09:15:18 PST

Multiple-Robust Estimation of an Odds Ratio Interaction

Eric J. Tchetgen Tchetgen — Mon, 13 Feb 2012 07:35:59 PST

On Parametrization, Robustness and Sensitivity Analysis in a Marginal Structural Cox Proportional Hazards Model for Point Exposure

Eric J. Tchetgen Tchetgen et al. — Mon, 13 Feb 2012 07:35:58 PST

A Cautionary Note on Specification of the Correlation Structure in Inverse-Probability-Weighted Estimation for Repeated Measures

Eric J. Tchetgen Tchetgen et al. — Mon, 13 Feb 2012 07:33:46 PST

Formulae for Causal Mediation Analysis in an Odds Ratio Context Without a Normality Assumption for the Continuous Mediator

Eric J. Tchetgen Tchetgen — Mon, 13 Feb 2012 07:28:11 PST

On a Closed-form Doubly Robust Estimator of the Adjusted Odds Ratio for a Binary Exposure

Eric J. Tchetgen Tchetgen — Mon, 13 Feb 2012 07:25:31 PST