SEQUENTIAL MULTIPLE ASSIGNMENT RANDOMIZATION TRIALS WITH ENRICHMENT (SMARTER) DESIGN

Size: px
Start display at page:

Download "SEQUENTIAL MULTIPLE ASSIGNMENT RANDOMIZATION TRIALS WITH ENRICHMENT (SMARTER) DESIGN"

Transcription

1 SEQUENTIAL MULTIPLE ASSIGNMENT RANDOMIZATION TRIALS WITH ENRICHMENT (SMARTER) DESIGN Ying Liu Division of Biostatistics, Medical College of Wisconsin Yuanjia Wang Department of Biostatistics & Psychiatry, Columbia University Donglin Zeng Department of Biostatistics, University of North Carolina Duke Industry Statistics Symposium, Sep 7th, 2017

2 INTRODUCTION TO DTR AND SMART Topic of this talk: Design SMART Enrichment Trial A new design to save time and cost for SMART trial. A way to incorporate big observational data in to randomized clinical trial design:a future foresight. Reference: Liu, Ying, Yuanjia Wang, and Donglin Zeng. "Sequential multiple assignment randomization trials with enrichment design." Biometrics 73, no. 2 (2017):

3 INTRODUCTION TO DTR AND SMART MOTIVATION: MULTIPLE STAGE DECISIONS Dynamic Treatment Regimes (DTRs) are sequential decision rules, tailored at each stage by patients time-varying features and intermediate outcomes in previous stages (Lavori & Dawson 1998, Murphy et al. 2001, Lei et al. 2014). Optimizing DTR is to address the personalized medicine quest to diliver the best treatment to the right patient at the right time.

4 INTRODUCTION TO DTR AND SMART CLINICAL TRIAL DESIGN FOR INFERRING DTRS SMART: Sequential Multiple Assignment Randomized Trial (Lavori & Dawson 2000, 2004; Murphy 2005) Patients are sequentially randomized at each critical decision point. Enables efficient causal comparisons among different DTRs.

5 INTRODUCTION TO DTR AND SMART SMART EXAMPLE: ADHD TRIAL Figure: SMART Design of Adaptive Pharmacological Behavioral Treatments for Children with ADHD Trial (Pelham 2002)

6 INTRODUCTION TO DTR AND SMART RESEARCH QUESTIONS TO BE ANSWERED FROM A SMART SMART Design Powered for Comparing Effects of fixed DTRs Comparing BMOD+Intensify vs BMOD+add MED; Comparing BMOD+add MED vs MED+add BMOD; SMART variance (Murphy 2005) ( ) I(A1 = d 1 (S 1 ), A 2 = d 2 (S 1, A 1 )) Var s (Y µ(d 1, d 2 )). p(a 1 S 1 )p(a 2 S 1, A 1 )

7 INTRODUCTION TO DTR AND SMART HOWEVER, PRACTICAL CONCERNS REMAIN... SMART requires all participants to stay through multi-stage randomization and be compliant. High cost and long period. With drop-out and non-compliance, need a large sample size to achieve sufficient power for comparing DTRs. Clinical Antipsychotic Trials of Intervention and Effectiveness (CATIE, Stroup et al. 2003): 705 out of 1460 (48%) stayed for the full 18 months In ExTENd (Lei et al., 2012), there was a drop-out rate of 17% during the first-stage treatment (52 out of 302), and an additional 13% during the second stage (41 out of 302).

8 SMART WITH ENRICHMENT (SMARTER) NEW DESIGN: SMART-ENRICHMENT TRIAL (SMARTER) Main Idea: At the kth stage, (k>1), augment the original SMART with new patients randomized among the k th stage treatment options without requiring randomization of previous stage treatments. A Two stage example: Group 1. Compliant and complete the SMART trial in both stages. Group 2. Dropouts before the second stage randomization after complete the first stage. Group 3. Newly recruited enrichment sample at the second stage. They only receive randomization at the second stage, and they receive one of the stage 1 treatment by observation.

9 SMART WITH ENRICHMENT (SMARTER) NEW DESIGN: SMART-ENRICHMENT TRIAL (SMARTER) Figure: Diagram of SMART-EnRichment Trial (SMARTER)

10 SMART WITH ENRICHMENT (SMARTER) RATIONALE BEHIND SMARTER At Stage 2, the continuing participants from SMART and the enrichment participants provide unbiased prediction of Stage 2 treatment effect given history at Stage 1, due to RANDOMIZATION. This prediction provides imputed and unbiased future outcomes for the participants who drop out before Stage 2 we recover the drop-out participants. At Stage 1, the imputed and observed outcomes from SMART can be used to infer unbiased treatment effects, again due to RANDOMIZATION. Therefore, SMARTER protects against bias due to sequential randomization; SMARTER improves efficiency due to enrichment.

11 DATA COLLECTED IN SMARTER DESIGNS Notation. Stage 1: {S 1, A 1 }; Stage 2: S 2 = {(S 1, A 1 ), A 2 }; Final outcome: Y. The goal is to evaluate the expected final outcome for any given treatment strategy: a 1 = d 1 (S 1 ), a 2 = d 2 (S 2 ). Data from the SMART sample: S 1i, A 1i, Z i A 2i, Z i Y i, i = 1,..., n. (Z i : Stage 2 continuation status) Data from the enrichment sample: S 1j, A 1j, A 2j, Y j, j = 1,..., m. Note that the distributions of (S 1, A 1 ) may be different between the SMART group and the enrichment group!

12 KEY ASSUMPTIONS IN SMARTER (C.1) Stable unit treatment value assumption (SUTVA): treatment applied to one unit does not effect the outcome for another unit (C.2) Non-informative dropout: the dropout is independent of {Y (a 1, a 2 )} given (S, A 1 ) (C.3) No selection bias: the conditional distribution of Y given (A 1, S, A 2 ) in the enrichment group is the same as that in the original SMART population. (C.4) The first stage treatments of A 1 for the enrichment group is identical to the treatment A 1 in SMART population.

13 Under conditions (C.1)-(C.4), SMARTer can provide an unbiased estimation for the average potential outcome E(Y (d 1, d 2 )) under the DTR(d 1, d 2 ).

14 INFERENCE FROM SMARTER First, we estimate the predicted outcome using the Stage 2 data for Group 2 patients using Group 1 and 3. Ŷ (a 1, a 2, s) = n i=1 Z iy i I(A 1i = a 1, A 2i = a 2, S 1i = s) + m j=1 Y ji(a 1j = a 1, A 2j = a 2, S 1j = s) n i=1 Z ii(a 1i = a 1, A 2i = a 2, S 1i = s) + m j=1 I(A. 1j = a 1, A 2j = a 2, S 1j = s)

15 INFERENCE FROM SMARTER For any given treatment regimen (d 1, d 2 ), the nonparametric estimator of its value using SMARTER is a weighted average of the outcomes from the SMART participants who were assigned to treatment (d 1, d 2 ): SMART Subjects Outcome Weights Group 1:Z i = 1 Y i I(A 1i =d 1 (S 1i ),A 2i =d 2 (S 1i,A 1i )) p(a 1i S 1i )p(a 2i S 1i,A 1i ) Group 2:Z i = 0 Ŷ (A 1i, d 2 (S 1i, A 1i ), S 1i ) I(A 1i =d 1 (S 1i )) p(a 1i S 1i )

16 VARIANCE COMPUTATION FOR SMARTER For any given treatment regime (d 1, d 2 ), the variance of the value estimator depends on the continuation ratio α = n 1 /n, enrichment ratio β = m/n : ( Var smart Z I(A 1 = d 1 (S 1 ), A 2 = d 2 (S 1, A 1 )) p(a 1 S 1 )p(a 2 S 1, A 1 ) { } 1 α(a 1, S 1 ) (Y µ(d 1, d 2 )) + α(a 1, S 1 ) + βr(a 1, S 1 ) (Y E[Y A 1, A 2, S 1 ]) + (1 Z ) I(A 1 = d 1 (S 1 )) E[Y µ(d 1, d 2 ) A 1, A 2 = d 2 (S 1, A 2 ), S 1 ] p(a 1 S 1 ) ( (1 α(a1, S 1 )) (Y E[Y A 1, A 2, S 1 ]) +βvar enrichment α(a 1, S 1 ) + βr(a 1, S 1 ) I(A ) 1 = d 1 (S 1 ), A 2 = d 2 (S 1, A 1 )). p(a 1 S 1 )p(a 2 S 1, A 1 ) )

17 VARIANCE COMPUTATION FOR SMARTER When continuation ratio α = 1, enrichment ratio β = 0, reduces to SMART variance (Murphy 2005) ( ) I(A1 = d 1 (S 1 ), A 2 = d 2 (S 1, A 1 )) Var s (Y µ(d 1, d 2 )). p(a 1 S 1 )p(a 2 S 1, A 1 )

18 EFFICIENCY OF SMARTER COMPARED TO SMART Simplifications: (1) pure randomization: p 1 (S) = p 1, p 2 (S) = p 2 ; (2) drop-out completely at random : P(Z = 1 A 1, S) = α; (3) same S distribution in the enrichment and SMART populations Relative efficiency of SMARTER to SMART: ρ = Var SMART Var enrichment 1 + γ, 1 (1 α)(1 p 2 ) + γ α(1+β)2 +β(1 α) 2 (α+β) 2 γ is the ratio of the within-strata variance versus the between-strata variance. The relative efficiency depends on randomization probabilities, within- and between-strata (S) variability, drop out rate, enrichment rate.

19 RELATIVE EFFICIENCY IN SOME SIMPLE CASES ρ > 1 implies the proposed SMARTER is more efficient than a SMART without enrichment and no dropout For α = 0, all subjects drop out of the first stage. Thus, ρ (1 + γ)/(p 2 + γ/β) so β 1 leads to efficiency gain. SMARTER always more efficient if β > γ/(1 + γ p 2 ). For any 0 α < 1, if α(1 + β) 2 + β(1 α) 2 (α + β) 2, ρ > 1 implies efficiency gain. Particularly, the latter condition holds if we choose β 1.

20 CONTOUR PLOTS OF RES Figure: Relative efficiencies of SMARTER compared to SMART; γ = 2 (ratio of within and between stratum variance); β α

21 SAMPLE SIZE CONSIDERATION SMART without dropout: 8(z 0.05/2 + z 0.2 ) 2 σ 2 ( d 2 ) ( µ) 2 ; SMART with α attrition rate: 8(z 0.05/2 + z 0.2 ) 2 σ 2 ( d 2 ) α( µ) 2 ; SMARTER: 8(z 0.05/2 + z β ) 2 σ2 ( µ) 2 ρ.

22 SAMPLE SIZE CONSIDERATION Table: Sample sizes of SMARTER to achieve the same efficiency as SMART with 100 subjects α SMARTER β = 0.5 n m n m n m n m n m n m γ = γ = γ = β = 1 γ = γ = γ = β = 2 γ = γ = γ = SMART-mis NA : Sample sizes for SMARTER are to achieve same efficiency as a SMART trial with 100 patients and in an ideal case of no dropout. n is the sample size for the SMART group, m is the sample size for the enrichment group; β = m/n is the ratio of sample size between enrichment and SMART group; 1 α is dropout rate; γ is ratio of within- and between-stratum variance. : SMART-mis is the sample size for a SMART accounting for the dropout rate of 1 α in the second stage in the design, i.e., 100/α.

23 ESTIMATING OPTIMAL DTRS USING SMARTER Use Group 1 and 3 to train a model ˆf 1 to optimize A 2. Inputs are (S 1, A 1, S 2 ) and outputs are actual observed outcome Y. Use Group 1 and 2 to train a model to optimize A 1. Inputs are S 1 and outputs is the predicted optimal outcome from ˆf 1.

24 A SIMULATION STUDY FOR ESTIMATING OPTIMAL DTRS Simulation setting R 1 = 1 + A 1 S 1 + N(0, 2); R 2 = A 2 R 1 + N(0, 2). S 1 N(0, 1) plus 4 additional noise baseline covariates. In SMART group, A 1 and A 2 are purely randomized. In the enrichment group of the same size, A 1 is observational and depends on R 1 and R 2 ; only A 2 is purely randomized. We vary the drop-out rates of subjects in SMART component.

25 SIMULATIONS FOR EXPLORING OPTIMAL DTRS Emipirical Value Super(Analysis 1) SMART(group1) dropout proportion at stage 1 Figure: Estimates of the value functions using the complete SMART subjects (yellow) and the SMARTER (blue)

26 SIMULATIONS FOR EXPLORING OPTIMAL DTRS Results: Scenario 2 Emipirical Value Super(Analysis 1) SMART(group1) dropout proportion at stage 1 Figure: Mean Value Functions in Scenario 2

27 DISCUSSION DISCUSSION SMARTER advantages: SMARTER supplements SMART to improve efficiency to salvage potential high drop-out in SMART. By enrichment, it ensures sufficient sample size at each stage.

28 DISCUSSION DISCUSSION A more radical departure from SMART: All subjects in SMART sample have dropped out after the first stage treatment. SMARTER essentially synthesizes two independent trials: Trial 1 on Stage 1 and Trial 2 on Stage 2. Key information: Stage 1 treatment and tailoring variables for Trial 2 participants are available. Key assumptions: the two trial populations should be the same; tailoring variables S 1 and S 2 are measured in Trial 1, and S 2 measured in Trial 2

29 DISCUSSION DISCUSSION Concerns of SMARTER: Quality of the first stage (naturalistic) treatment delivery in the enrichment sample: When the first stage treatment includes some common treatment. SMARTER can be used to improve efficiency, if one option of A 1 can be found in naturalistic treatment delivery, despite the other treatments are novel and cannot be found in observational data sets. Recruiting similar enrichment population with the SMART population: A future forsight for the big medical data set to improve its precision.

Lecture 9: Learning Optimal Dynamic Treatment Regimes. Donglin Zeng, Department of Biostatistics, University of North Carolina

Lecture 9: Learning Optimal Dynamic Treatment Regimes. Donglin Zeng, Department of Biostatistics, University of North Carolina Lecture 9: Learning Optimal Dynamic Treatment Regimes Introduction Refresh: Dynamic Treatment Regimes (DTRs) DTRs: sequential decision rules, tailored at each stage by patients time-varying features and

More information

Estimation of Optimal Treatment Regimes Via Machine Learning. Marie Davidian

Estimation of Optimal Treatment Regimes Via Machine Learning. Marie Davidian Estimation of Optimal Treatment Regimes Via Machine Learning Marie Davidian Department of Statistics North Carolina State University Triangle Machine Learning Day April 3, 2018 1/28 Optimal DTRs Via ML

More information

Lecture 2: Constant Treatment Strategies. Donglin Zeng, Department of Biostatistics, University of North Carolina

Lecture 2: Constant Treatment Strategies. Donglin Zeng, Department of Biostatistics, University of North Carolina Lecture 2: Constant Treatment Strategies Introduction Motivation We will focus on evaluating constant treatment strategies in this lecture. We will discuss using randomized or observational study for these

More information

Estimating Causal Effects of Organ Transplantation Treatment Regimes

Estimating Causal Effects of Organ Transplantation Treatment Regimes Estimating Causal Effects of Organ Transplantation Treatment Regimes David M. Vock, Jeffrey A. Verdoliva Boatman Division of Biostatistics University of Minnesota July 31, 2018 1 / 27 Hot off the Press

More information

Robustifying Trial-Derived Treatment Rules to a Target Population

Robustifying Trial-Derived Treatment Rules to a Target Population 1/ 39 Robustifying Trial-Derived Treatment Rules to a Target Population Yingqi Zhao Public Health Sciences Division Fred Hutchinson Cancer Research Center Workshop on Perspectives and Analysis for Personalized

More information

Randomization-Based Inference With Complex Data Need Not Be Complex!

Randomization-Based Inference With Complex Data Need Not Be Complex! Randomization-Based Inference With Complex Data Need Not Be Complex! JITAIs JITAIs Susan Murphy 07.18.17 HeartSteps JITAI JITAIs Sequential Decision Making Use data to inform science and construct decision

More information

Estimating Optimal Dynamic Treatment Regimes from Clustered Data

Estimating Optimal Dynamic Treatment Regimes from Clustered Data Estimating Optimal Dynamic Treatment Regimes from Clustered Data Bibhas Chakraborty Department of Biostatistics, Columbia University bc2425@columbia.edu Society for Clinical Trials Annual Meetings Boston,

More information

arxiv: v1 [stat.ap] 17 Mar 2018

arxiv: v1 [stat.ap] 17 Mar 2018 Power Analysis in a SMART Design: Sample Size Estimation for Determining the Best Dynamic Treatment Regime arxiv:1804.04587v1 [stat.ap] 17 Mar 2018 William J. Artman Department of Biostatistics and Computational

More information

Set-valued dynamic treatment regimes for competing outcomes

Set-valued dynamic treatment regimes for competing outcomes Set-valued dynamic treatment regimes for competing outcomes Eric B. Laber Department of Statistics, North Carolina State University JSM, Montreal, QC, August 5, 2013 Acknowledgments Zhiqiang Tan Jamie

More information

Comparing Adaptive Interventions Using Data Arising from a SMART: With Application to Autism, ADHD, and Mood Disorders

Comparing Adaptive Interventions Using Data Arising from a SMART: With Application to Autism, ADHD, and Mood Disorders Comparing Adaptive Interventions Using Data Arising from a SMART: With Application to Autism, ADHD, and Mood Disorders Daniel Almirall, Xi Lu, Connie Kasari, Inbal N-Shani, Univ. of Michigan, Univ. of

More information

A Sampling of IMPACT Research:

A Sampling of IMPACT Research: A Sampling of IMPACT Research: Methods for Analysis with Dropout and Identifying Optimal Treatment Regimes Marie Davidian Department of Statistics North Carolina State University http://www.stat.ncsu.edu/

More information

Structural Nested Mean Models for Assessing Time-Varying Effect Moderation. Daniel Almirall

Structural Nested Mean Models for Assessing Time-Varying Effect Moderation. Daniel Almirall 1 Structural Nested Mean Models for Assessing Time-Varying Effect Moderation Daniel Almirall Center for Health Services Research, Durham VAMC & Dept. of Biostatistics, Duke University Medical Joint work

More information

Bounds on Causal Effects in Three-Arm Trials with Non-compliance. Jing Cheng Dylan Small

Bounds on Causal Effects in Three-Arm Trials with Non-compliance. Jing Cheng Dylan Small Bounds on Causal Effects in Three-Arm Trials with Non-compliance Jing Cheng Dylan Small Department of Biostatistics and Department of Statistics University of Pennsylvania June 20, 2005 A Three-Arm Randomized

More information

A Bayesian Machine Learning Approach for Optimizing Dynamic Treatment Regimes

A Bayesian Machine Learning Approach for Optimizing Dynamic Treatment Regimes A Bayesian Machine Learning Approach for Optimizing Dynamic Treatment Regimes Thomas A. Murray, (tamurray@mdanderson.org), Ying Yuan, (yyuan@mdanderson.org), and Peter F. Thall (rex@mdanderson.org) Department

More information

Q learning. A data analysis method for constructing adaptive interventions

Q learning. A data analysis method for constructing adaptive interventions Q learning A data analysis method for constructing adaptive interventions SMART First stage intervention options coded as 1(M) and 1(B) Second stage intervention options coded as 1(M) and 1(B) O1 A1 O2

More information

An Introduction to Causal Analysis on Observational Data using Propensity Scores

An Introduction to Causal Analysis on Observational Data using Propensity Scores An Introduction to Causal Analysis on Observational Data using Propensity Scores Margie Rosenberg*, PhD, FSA Brian Hartman**, PhD, ASA Shannon Lane* *University of Wisconsin Madison **University of Connecticut

More information

Core Courses for Students Who Enrolled Prior to Fall 2018

Core Courses for Students Who Enrolled Prior to Fall 2018 Biostatistics and Applied Data Analysis Students must take one of the following two sequences: Sequence 1 Biostatistics and Data Analysis I (PHP 2507) This course, the first in a year long, two-course

More information

Improving Efficiency of Inferences in Randomized Clinical Trials Using Auxiliary Covariates

Improving Efficiency of Inferences in Randomized Clinical Trials Using Auxiliary Covariates Improving Efficiency of Inferences in Randomized Clinical Trials Using Auxiliary Covariates Anastasios (Butch) Tsiatis Department of Statistics North Carolina State University http://www.stat.ncsu.edu/

More information

Implementing Precision Medicine: Optimal Treatment Regimes and SMARTs. Anastasios (Butch) Tsiatis and Marie Davidian

Implementing Precision Medicine: Optimal Treatment Regimes and SMARTs. Anastasios (Butch) Tsiatis and Marie Davidian Implementing Precision Medicine: Optimal Treatment Regimes and SMARTs Anastasios (Butch) Tsiatis and Marie Davidian Department of Statistics North Carolina State University http://www4.stat.ncsu.edu/~davidian

More information

The Supervised Learning Approach To Estimating Heterogeneous Causal Regime Effects

The Supervised Learning Approach To Estimating Heterogeneous Causal Regime Effects The Supervised Learning Approach To Estimating Heterogeneous Causal Regime Effects Thai T. Pham Stanford Graduate School of Business thaipham@stanford.edu May, 2016 Introduction Observations Many sequential

More information

Empirical Likelihood Methods for Two-sample Problems with Data Missing-by-Design

Empirical Likelihood Methods for Two-sample Problems with Data Missing-by-Design 1 / 32 Empirical Likelihood Methods for Two-sample Problems with Data Missing-by-Design Changbao Wu Department of Statistics and Actuarial Science University of Waterloo (Joint work with Min Chen and Mary

More information

Testing a secondary endpoint after a group sequential test. Chris Jennison. 9th Annual Adaptive Designs in Clinical Trials

Testing a secondary endpoint after a group sequential test. Chris Jennison. 9th Annual Adaptive Designs in Clinical Trials Testing a secondary endpoint after a group sequential test Christopher Jennison Department of Mathematical Sciences, University of Bath, UK http://people.bath.ac.uk/mascj 9th Annual Adaptive Designs in

More information

Causal modelling in Medical Research

Causal modelling in Medical Research Causal modelling in Medical Research Debashis Ghosh Department of Biostatistics and Informatics, Colorado School of Public Health Biostatistics Workshop Series Goals for today Introduction to Potential

More information

Estimating the Dynamic Effects of a Job Training Program with M. Program with Multiple Alternatives

Estimating the Dynamic Effects of a Job Training Program with M. Program with Multiple Alternatives Estimating the Dynamic Effects of a Job Training Program with Multiple Alternatives Kai Liu 1, Antonio Dalla-Zuanna 2 1 University of Cambridge 2 Norwegian School of Economics June 19, 2018 Introduction

More information

Rerandomization to Balance Covariates

Rerandomization to Balance Covariates Rerandomization to Balance Covariates Kari Lock Morgan Department of Statistics Penn State University Joint work with Don Rubin University of Minnesota Biostatistics 4/27/16 The Gold Standard Randomized

More information

Extending causal inferences from a randomized trial to a target population

Extending causal inferences from a randomized trial to a target population Extending causal inferences from a randomized trial to a target population Issa Dahabreh Center for Evidence Synthesis in Health, Brown University issa dahabreh@brown.edu January 16, 2019 Issa Dahabreh

More information

Personalized Treatment Selection Based on Randomized Clinical Trials. Tianxi Cai Department of Biostatistics Harvard School of Public Health

Personalized Treatment Selection Based on Randomized Clinical Trials. Tianxi Cai Department of Biostatistics Harvard School of Public Health Personalized Treatment Selection Based on Randomized Clinical Trials Tianxi Cai Department of Biostatistics Harvard School of Public Health Outline Motivation A systematic approach to separating subpopulations

More information

A Unified Approach to the Statistical Evaluation of Differential Vaccine Efficacy

A Unified Approach to the Statistical Evaluation of Differential Vaccine Efficacy A Unified Approach to the Statistical Evaluation of Differential Vaccine Efficacy Erin E Gabriel Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden Dean Follmann

More information

Matching. Quiz 2. Matching. Quiz 2. Exact Matching. Estimand 2/25/14

Matching. Quiz 2. Matching. Quiz 2. Exact Matching. Estimand 2/25/14 STA 320 Design and Analysis of Causal Studies Dr. Kari Lock Morgan and Dr. Fan Li Department of Statistical Science Duke University Frequency 0 2 4 6 8 Quiz 2 Histogram of Quiz2 10 12 14 16 18 20 Quiz2

More information

BIOS 6649: Handout Exercise Solution

BIOS 6649: Handout Exercise Solution BIOS 6649: Handout Exercise Solution NOTE: I encourage you to work together, but the work you submit must be your own. Any plagiarism will result in loss of all marks. This assignment is based on weight-loss

More information

Evaluation of Viable Dynamic Treatment Regimes in a Sequentially Randomized Trial of Advanced Prostate Cancer

Evaluation of Viable Dynamic Treatment Regimes in a Sequentially Randomized Trial of Advanced Prostate Cancer Evaluation of Viable Dynamic Treatment Regimes in a Sequentially Randomized Trial of Advanced Prostate Cancer Lu Wang, Andrea Rotnitzky, Xihong Lin, Randall E. Millikan, and Peter F. Thall Abstract We

More information

Lecture 1 January 18

Lecture 1 January 18 STAT 263/363: Experimental Design Winter 2016/17 Lecture 1 January 18 Lecturer: Art B. Owen Scribe: Julie Zhu Overview Experiments are powerful because you can conclude causality from the results. In most

More information

Propensity Score Methods for Causal Inference

Propensity Score Methods for Causal Inference John Pura BIOS790 October 2, 2015 Causal inference Philosophical problem, statistical solution Important in various disciplines (e.g. Koch s postulates, Bradford Hill criteria, Granger causality) Good

More information

Assessing Time-Varying Causal Effect. Moderation

Assessing Time-Varying Causal Effect. Moderation Assessing Time-Varying Causal Effect JITAIs Moderation HeartSteps JITAI JITAIs Susan Murphy 11.07.16 JITAIs Outline Introduction to mobile health Causal Treatment Effects (aka Causal Excursions) (A wonderfully

More information

Causal Inference Basics

Causal Inference Basics Causal Inference Basics Sam Lendle October 09, 2013 Observed data, question, counterfactuals Observed data: n i.i.d copies of baseline covariates W, treatment A {0, 1}, and outcome Y. O i = (W i, A i,

More information

Adaptive Trial Designs

Adaptive Trial Designs Adaptive Trial Designs Wenjing Zheng, Ph.D. Methods Core Seminar Center for AIDS Prevention Studies University of California, San Francisco Nov. 17 th, 2015 Trial Design! Ethical:!eg.! Safety!! Efficacy!

More information

Structural Nested Mean Models for Assessing Time-Varying Effect Moderation. Daniel Almirall

Structural Nested Mean Models for Assessing Time-Varying Effect Moderation. Daniel Almirall 1 Structural Nested Mean Models for Assessing Time-Varying Effect Moderation Daniel Almirall Center for Health Services Research, Durham VAMC & Duke University Medical, Dept. of Biostatistics Joint work

More information

Causal Inference for Mediation Effects

Causal Inference for Mediation Effects Causal Inference for Mediation Effects by Jing Zhang B.S., University of Science and Technology of China, 2006 M.S., Brown University, 2008 A Dissertation Submitted in Partial Fulfillment of the Requirements

More information

Nonrespondent subsample multiple imputation in two-phase random sampling for nonresponse

Nonrespondent subsample multiple imputation in two-phase random sampling for nonresponse Nonrespondent subsample multiple imputation in two-phase random sampling for nonresponse Nanhua Zhang Division of Biostatistics & Epidemiology Cincinnati Children s Hospital Medical Center (Joint work

More information

Comparative effectiveness of dynamic treatment regimes

Comparative effectiveness of dynamic treatment regimes Comparative effectiveness of dynamic treatment regimes An application of the parametric g- formula Miguel Hernán Departments of Epidemiology and Biostatistics Harvard School of Public Health www.hsph.harvard.edu/causal

More information

Estimating Post-Treatment Effect Modification With Generalized Structural Mean Models

Estimating Post-Treatment Effect Modification With Generalized Structural Mean Models Estimating Post-Treatment Effect Modification With Generalized Structural Mean Models Alisa Stephens Luke Keele Marshall Joffe December 5, 2013 Abstract In randomized controlled trials, the evaluation

More information

Three-Level Modeling for Factorial Experiments With Experimentally Induced Clustering

Three-Level Modeling for Factorial Experiments With Experimentally Induced Clustering Three-Level Modeling for Factorial Experiments With Experimentally Induced Clustering John J. Dziak The Pennsylvania State University Inbal Nahum-Shani The University of Michigan Copyright 016, Penn State.

More information

Latent Variable Model for Weight Gain Prevention Data with Informative Intermittent Missingness

Latent Variable Model for Weight Gain Prevention Data with Informative Intermittent Missingness Journal of Modern Applied Statistical Methods Volume 15 Issue 2 Article 36 11-1-2016 Latent Variable Model for Weight Gain Prevention Data with Informative Intermittent Missingness Li Qin Yale University,

More information

BIOSTATISTICAL METHODS

BIOSTATISTICAL METHODS BIOSTATISTICAL METHODS FOR TRANSLATIONAL & CLINICAL RESEARCH Cross-over Designs #: DESIGNING CLINICAL RESEARCH The subtraction of measurements from the same subject will mostly cancel or minimize effects

More information

Potential Outcomes Model (POM)

Potential Outcomes Model (POM) Potential Outcomes Model (POM) Relationship Between Counterfactual States Causality Empirical Strategies in Labor Economics, Angrist Krueger (1999): The most challenging empirical questions in economics

More information

Nonparametric meta-analysis for diagnostic accuracy studies Antonia Zapf

Nonparametric meta-analysis for diagnostic accuracy studies Antonia Zapf Nonparametric meta-analysis for diagnostic accuracy studies Antonia Zapf joint work with A. Hoyer, K. Kramer, and O. Kuss Table of contents Motivation Nonparametric approach Simulation study Application

More information

Combining Non-probability and Probability Survey Samples Through Mass Imputation

Combining Non-probability and Probability Survey Samples Through Mass Imputation Combining Non-probability and Probability Survey Samples Through Mass Imputation Jae-Kwang Kim 1 Iowa State University & KAIST October 27, 2018 1 Joint work with Seho Park, Yilin Chen, and Changbao Wu

More information

Discussion of Identifiability and Estimation of Causal Effects in Randomized. Trials with Noncompliance and Completely Non-ignorable Missing Data

Discussion of Identifiability and Estimation of Causal Effects in Randomized. Trials with Noncompliance and Completely Non-ignorable Missing Data Biometrics 000, 000 000 DOI: 000 000 0000 Discussion of Identifiability and Estimation of Causal Effects in Randomized Trials with Noncompliance and Completely Non-ignorable Missing Data Dylan S. Small

More information

Comparing Adaptive Designs and the. Classical Group Sequential Approach. to Clinical Trial Design

Comparing Adaptive Designs and the. Classical Group Sequential Approach. to Clinical Trial Design Comparing Adaptive Designs and the Classical Group Sequential Approach to Clinical Trial Design Christopher Jennison Department of Mathematical Sciences, University of Bath, UK http://people.bath.ac.uk/mascj

More information

Combining Experimental and Non-Experimental Design in Causal Inference

Combining Experimental and Non-Experimental Design in Causal Inference Combining Experimental and Non-Experimental Design in Causal Inference Kari Lock Morgan Department of Statistics Penn State University Rao Prize Conference May 12 th, 2017 A Tribute to Don Design trumps

More information

Marginal versus conditional effects: does it make a difference? Mireille Schnitzer, PhD Université de Montréal

Marginal versus conditional effects: does it make a difference? Mireille Schnitzer, PhD Université de Montréal Marginal versus conditional effects: does it make a difference? Mireille Schnitzer, PhD Université de Montréal Overview In observational and experimental studies, the goal may be to estimate the effect

More information

Group Sequential Tests for Delayed Responses. Christopher Jennison. Lisa Hampson. Workshop on Special Topics on Sequential Methodology

Group Sequential Tests for Delayed Responses. Christopher Jennison. Lisa Hampson. Workshop on Special Topics on Sequential Methodology Group Sequential Tests for Delayed Responses Christopher Jennison Department of Mathematical Sciences, University of Bath, UK http://people.bath.ac.uk/mascj Lisa Hampson Department of Mathematics and Statistics,

More information

Robust covariance estimator for small-sample adjustment in the generalized estimating equations: A simulation study

Robust covariance estimator for small-sample adjustment in the generalized estimating equations: A simulation study Science Journal of Applied Mathematics and Statistics 2014; 2(1): 20-25 Published online February 20, 2014 (http://www.sciencepublishinggroup.com/j/sjams) doi: 10.11648/j.sjams.20140201.13 Robust covariance

More information

Time-Varying Causal. Treatment Effects

Time-Varying Causal. Treatment Effects Time-Varying Causal JOOLHEALTH Treatment Effects Bar-Fit Susan A Murphy 12.14.17 HeartSteps SARA Sense 2 Stop Disclosures Consulted with Sanofi on mobile health engagement and adherence. 2 Outline Introduction

More information

Estimating the Mean Response of Treatment Duration Regimes in an Observational Study. Anastasios A. Tsiatis.

Estimating the Mean Response of Treatment Duration Regimes in an Observational Study. Anastasios A. Tsiatis. Estimating the Mean Response of Treatment Duration Regimes in an Observational Study Anastasios A. Tsiatis http://www.stat.ncsu.edu/ tsiatis/ Introduction to Dynamic Treatment Regimes 1 Outline Description

More information

Sample Size and Power Considerations for Longitudinal Studies

Sample Size and Power Considerations for Longitudinal Studies Sample Size and Power Considerations for Longitudinal Studies Outline Quantities required to determine the sample size in longitudinal studies Review of type I error, type II error, and power For continuous

More information

ANALYSIS OF CORRELATED DATA SAMPLING FROM CLUSTERS CLUSTER-RANDOMIZED TRIALS

ANALYSIS OF CORRELATED DATA SAMPLING FROM CLUSTERS CLUSTER-RANDOMIZED TRIALS ANALYSIS OF CORRELATED DATA SAMPLING FROM CLUSTERS CLUSTER-RANDOMIZED TRIALS Background Independent observations: Short review of well-known facts Comparison of two groups continuous response Control group:

More information

RANDOMIZATIONN METHODS THAT

RANDOMIZATIONN METHODS THAT RANDOMIZATIONN METHODS THAT DEPEND ON THE COVARIATES WORK BY ALESSANDRO BALDI ANTOGNINI MAROUSSA ZAGORAIOU ALESSANDRA G GIOVAGNOLI (*) 1 DEPARTMENT OF STATISTICAL SCIENCES UNIVERSITY OF BOLOGNA, ITALY

More information

Introduction to Empirical Processes and Semiparametric Inference Lecture 01: Introduction and Overview

Introduction to Empirical Processes and Semiparametric Inference Lecture 01: Introduction and Overview Introduction to Empirical Processes and Semiparametric Inference Lecture 01: Introduction and Overview Michael R. Kosorok, Ph.D. Professor and Chair of Biostatistics Professor of Statistics and Operations

More information

Modelling Dropouts by Conditional Distribution, a Copula-Based Approach

Modelling Dropouts by Conditional Distribution, a Copula-Based Approach The 8th Tartu Conference on MULTIVARIATE STATISTICS, The 6th Conference on MULTIVARIATE DISTRIBUTIONS with Fixed Marginals Modelling Dropouts by Conditional Distribution, a Copula-Based Approach Ene Käärik

More information

Using Instrumental Variables to Find Causal Effects in Public Health

Using Instrumental Variables to Find Causal Effects in Public Health 1 Using Instrumental Variables to Find Causal Effects in Public Health Antonio Trujillo, PhD John Hopkins Bloomberg School of Public Health Department of International Health Health Systems Program October

More information

Statistical Analysis of Causal Mechanisms

Statistical Analysis of Causal Mechanisms Statistical Analysis of Causal Mechanisms Kosuke Imai Princeton University November 17, 2008 Joint work with Luke Keele (Ohio State) and Teppei Yamamoto (Princeton) Kosuke Imai (Princeton) Causal Mechanisms

More information

Shu Yang and Jae Kwang Kim. Harvard University and Iowa State University

Shu Yang and Jae Kwang Kim. Harvard University and Iowa State University Statistica Sinica 27 (2017), 000-000 doi:https://doi.org/10.5705/ss.202016.0155 DISCUSSION: DISSECTING MULTIPLE IMPUTATION FROM A MULTI-PHASE INFERENCE PERSPECTIVE: WHAT HAPPENS WHEN GOD S, IMPUTER S AND

More information

Compare Predicted Counts between Groups of Zero Truncated Poisson Regression Model based on Recycled Predictions Method

Compare Predicted Counts between Groups of Zero Truncated Poisson Regression Model based on Recycled Predictions Method Compare Predicted Counts between Groups of Zero Truncated Poisson Regression Model based on Recycled Predictions Method Yan Wang 1, Michael Ong 2, Honghu Liu 1,2,3 1 Department of Biostatistics, UCLA School

More information

University of Michigan School of Public Health

University of Michigan School of Public Health University of Michigan School of Public Health The University of Michigan Department of Biostatistics Working Paper Series Year 003 Paper Weighting Adustments for Unit Nonresponse with Multiple Outcome

More information

Final Exam Details. J. Parman (UC-Davis) Analysis of Economic Data, Winter 2011 March 8, / 24

Final Exam Details. J. Parman (UC-Davis) Analysis of Economic Data, Winter 2011 March 8, / 24 Final Exam Details The final is Thursday, March 17 from 10:30am to 12:30pm in the regular lecture room The final is cumulative (multiple choice will be a roughly 50/50 split between material since the

More information

IsoLATEing: Identifying Heterogeneous Effects of Multiple Treatments

IsoLATEing: Identifying Heterogeneous Effects of Multiple Treatments IsoLATEing: Identifying Heterogeneous Effects of Multiple Treatments Peter Hull December 2014 PRELIMINARY: Please do not cite or distribute without permission. Please see www.mit.edu/~hull/research.html

More information

MISSING or INCOMPLETE DATA

MISSING or INCOMPLETE DATA MISSING or INCOMPLETE DATA A (fairly) complete review of basic practice Don McLeish and Cyntha Struthers University of Waterloo Dec 5, 2015 Structure of the Workshop Session 1 Common methods for dealing

More information

Group Sequential Designs: Theory, Computation and Optimisation

Group Sequential Designs: Theory, Computation and Optimisation Group Sequential Designs: Theory, Computation and Optimisation Christopher Jennison Department of Mathematical Sciences, University of Bath, UK http://people.bath.ac.uk/mascj 8th International Conference

More information

Mantel-Haenszel Test Statistics. for Correlated Binary Data. Department of Statistics, North Carolina State University. Raleigh, NC

Mantel-Haenszel Test Statistics. for Correlated Binary Data. Department of Statistics, North Carolina State University. Raleigh, NC Mantel-Haenszel Test Statistics for Correlated Binary Data by Jie Zhang and Dennis D. Boos Department of Statistics, North Carolina State University Raleigh, NC 27695-8203 tel: (919) 515-1918 fax: (919)

More information

Recent Advances in Outcome Weighted Learning for Precision Medicine

Recent Advances in Outcome Weighted Learning for Precision Medicine Recent Advances in Outcome Weighted Learning for Precision Medicine Michael R. Kosorok Department of Biostatistics Department of Statistics and Operations Research University of North Carolina at Chapel

More information

University of California, Berkeley

University of California, Berkeley University of California, Berkeley U.C. Berkeley Division of Biostatistics Working Paper Series Year 2010 Paper 259 Targeted Maximum Likelihood Based Causal Inference Mark J. van der Laan University of

More information

Whether to use MMRM as primary estimand.

Whether to use MMRM as primary estimand. Whether to use MMRM as primary estimand. James Roger London School of Hygiene & Tropical Medicine, London. PSI/EFSPI European Statistical Meeting on Estimands. Stevenage, UK: 28 September 2015. 1 / 38

More information

Package Rsurrogate. October 20, 2016

Package Rsurrogate. October 20, 2016 Type Package Package Rsurrogate October 20, 2016 Title Robust Estimation of the Proportion of Treatment Effect Explained by Surrogate Marker Information Version 2.0 Date 2016-10-19 Author Layla Parast

More information

Optimal Blocking by Minimizing the Maximum Within-Block Distance

Optimal Blocking by Minimizing the Maximum Within-Block Distance Optimal Blocking by Minimizing the Maximum Within-Block Distance Michael J. Higgins Jasjeet Sekhon Princeton University University of California at Berkeley November 14, 2013 For the Kansas State University

More information

Pubh 8482: Sequential Analysis

Pubh 8482: Sequential Analysis Pubh 8482: Sequential Analysis Joseph S. Koopmeiners Division of Biostatistics University of Minnesota Week 12 Review So far... We have discussed the role of phase III clinical trials in drug development

More information

Balancing Covariates via Propensity Score Weighting

Balancing Covariates via Propensity Score Weighting Balancing Covariates via Propensity Score Weighting Kari Lock Morgan Department of Statistics Penn State University klm47@psu.edu Stochastic Modeling and Computational Statistics Seminar October 17, 2014

More information

Phase I design for locating schedule-specific maximum tolerated doses

Phase I design for locating schedule-specific maximum tolerated doses Phase I design for locating schedule-specific maximum tolerated doses Nolan A. Wages, Ph.D. University of Virginia Division of Translational Research & Applied Statistics Department of Public Health Sciences

More information

University of California, Berkeley

University of California, Berkeley University of California, Berkeley U.C. Berkeley Division of Biostatistics Working Paper Series Year 2010 Paper 267 Optimizing Randomized Trial Designs to Distinguish which Subpopulations Benefit from

More information

Auxiliary-variable-enriched Biomarker Stratified Design

Auxiliary-variable-enriched Biomarker Stratified Design Auxiliary-variable-enriched Biomarker Stratified Design Ting Wang University of North Carolina at Chapel Hill tingwang@live.unc.edu 8th May, 2017 A joint work with Xiaofei Wang, Haibo Zhou, Jianwen Cai

More information

Analysis of Longitudinal Data. Patrick J. Heagerty PhD Department of Biostatistics University of Washington

Analysis of Longitudinal Data. Patrick J. Heagerty PhD Department of Biostatistics University of Washington Analsis of Longitudinal Data Patrick J. Heagert PhD Department of Biostatistics Universit of Washington 1 Auckland 2008 Session Three Outline Role of correlation Impact proper standard errors Used to weight

More information

arxiv: v2 [stat.me] 31 Dec 2012

arxiv: v2 [stat.me] 31 Dec 2012 1 arxiv:1109.1070v2 [stat.me] 31 Dec 2012 1 Mediation Analysis Without Sequential Ignorability: Using Baseline Covariates Interacted with Random Assignment as Instrumental Variables Dylan S. Small University

More information

A Bayesian Nonparametric Approach to Monotone Missing Data in Longitudinal Studies with Informative Missingness

A Bayesian Nonparametric Approach to Monotone Missing Data in Longitudinal Studies with Informative Missingness A Bayesian Nonparametric Approach to Monotone Missing Data in Longitudinal Studies with Informative Missingness A. Linero and M. Daniels UF, UT-Austin SRC 2014, Galveston, TX 1 Background 2 Working model

More information

Missing Data Issues in the Studies of Neurodegenerative Disorders: the Methodology

Missing Data Issues in the Studies of Neurodegenerative Disorders: the Methodology Missing Data Issues in the Studies of Neurodegenerative Disorders: the Methodology Sheng Luo, PhD Associate Professor Department of Biostatistics & Bioinformatics Duke University Medical Center sheng.luo@duke.edu

More information

Monitoring clinical trial outcomes with delayed response: incorporating pipeline data in group sequential designs. Christopher Jennison

Monitoring clinical trial outcomes with delayed response: incorporating pipeline data in group sequential designs. Christopher Jennison Monitoring clinical trial outcomes with delayed response: incorporating pipeline data in group sequential designs Christopher Jennison Department of Mathematical Sciences, University of Bath http://people.bath.ac.uk/mascj

More information

Targeted Group Sequential Adaptive Designs

Targeted Group Sequential Adaptive Designs Targeted Group Sequential Adaptive Designs Mark van der Laan Department of Biostatistics, University of California, Berkeley School of Public Health Liver Forum, May 10, 2017 Targeted Group Sequential

More information

Accounting for Baseline Observations in Randomized Clinical Trials

Accounting for Baseline Observations in Randomized Clinical Trials Accounting for Baseline Observations in Randomized Clinical Trials Scott S Emerson, MD, PhD Department of Biostatistics, University of Washington, Seattle, WA 9895, USA August 5, 0 Abstract In clinical

More information

Analyzing Pilot Studies with Missing Observations

Analyzing Pilot Studies with Missing Observations Analyzing Pilot Studies with Missing Observations Monnie McGee mmcgee@smu.edu. Department of Statistical Science Southern Methodist University, Dallas, Texas Co-authored with N. Bergasa (SUNY Downstate

More information

Welcome! Webinar Biostatistics: sample size & power. Thursday, April 26, 12:30 1:30 pm (NDT)

Welcome! Webinar Biostatistics: sample size & power. Thursday, April 26, 12:30 1:30 pm (NDT) . Welcome! Webinar Biostatistics: sample size & power Thursday, April 26, 12:30 1:30 pm (NDT) Get started now: Please check if your speakers are working and mute your audio. Please use the chat box to

More information

Approximate analysis of covariance in trials in rare diseases, in particular rare cancers

Approximate analysis of covariance in trials in rare diseases, in particular rare cancers Approximate analysis of covariance in trials in rare diseases, in particular rare cancers Stephen Senn (c) Stephen Senn 1 Acknowledgements This work is partly supported by the European Union s 7th Framework

More information

Data Integration for Big Data Analysis for finite population inference

Data Integration for Big Data Analysis for finite population inference for Big Data Analysis for finite population inference Jae-kwang Kim ISU January 23, 2018 1 / 36 What is big data? 2 / 36 Data do not speak for themselves Knowledge Reproducibility Information Intepretation

More information

Prerequisite: STATS 7 or STATS 8 or AP90 or (STATS 120A and STATS 120B and STATS 120C). AP90 with a minimum score of 3

Prerequisite: STATS 7 or STATS 8 or AP90 or (STATS 120A and STATS 120B and STATS 120C). AP90 with a minimum score of 3 University of California, Irvine 2017-2018 1 Statistics (STATS) Courses STATS 5. Seminar in Data Science. 1 Unit. An introduction to the field of Data Science; intended for entering freshman and transfers.

More information

Probabilistic Index Models

Probabilistic Index Models Probabilistic Index Models Jan De Neve Department of Data Analysis Ghent University M3 Storrs, Conneticut, USA May 23, 2017 Jan.DeNeve@UGent.be 1 / 37 Introduction 2 / 37 Introduction to Probabilistic

More information

A weighted simulation-based estimator for incomplete longitudinal data models

A weighted simulation-based estimator for incomplete longitudinal data models To appear in Statistics and Probability Letters, 113 (2016), 16-22. doi 10.1016/j.spl.2016.02.004 A weighted simulation-based estimator for incomplete longitudinal data models Daniel H. Li 1 and Liqun

More information

Variable selection and machine learning methods in causal inference

Variable selection and machine learning methods in causal inference Variable selection and machine learning methods in causal inference Debashis Ghosh Department of Biostatistics and Informatics Colorado School of Public Health Joint work with Yeying Zhu, University of

More information

Bios 6649: Clinical Trials - Statistical Design and Monitoring

Bios 6649: Clinical Trials - Statistical Design and Monitoring Bios 6649: Clinical Trials - Statistical Design and Monitoring Spring Semester 2015 John M. Kittelson Department of Biostatistics & Informatics Colorado School of Public Health University of Colorado Denver

More information

ASSESSING THE EFFECT OF TREATMENT REGIMES ON LONGITUDINAL OUTCOME DATA: APPLICATION TO REVAMP STUDY OF DEPRESSION

ASSESSING THE EFFECT OF TREATMENT REGIMES ON LONGITUDINAL OUTCOME DATA: APPLICATION TO REVAMP STUDY OF DEPRESSION Journal of Statistical Research 2012, Vol. 46, No. 2, pp. 233-254 ISSN 0256-422 X ASSESSING THE EFFECT OF TREATMENT REGIMES ON LONGITUDINAL OUTCOME DATA: APPLICATION TO REVAMP STUDY OF DEPRESSION SACHIKO

More information

Propensity Score Weighting with Multilevel Data

Propensity Score Weighting with Multilevel Data Propensity Score Weighting with Multilevel Data Fan Li Department of Statistical Science Duke University October 25, 2012 Joint work with Alan Zaslavsky and Mary Beth Landrum Introduction In comparative

More information

Causal Inference with Big Data Sets

Causal Inference with Big Data Sets Causal Inference with Big Data Sets Marcelo Coca Perraillon University of Colorado AMC November 2016 1 / 1 Outlone Outline Big data Causal inference in economics and statistics Regression discontinuity

More information

Impact of Stratified Randomization in Clinical Trials

Impact of Stratified Randomization in Clinical Trials Impact of Stratified Randomization in Clinical Trials Vladimir V. Anisimov Abstract This paper deals with the analysis of randomization effects in clinical trials. The two randomization schemes most often

More information