Group sequential designs with negative binomial data
|
|
- Isabella Goodwin
- 6 years ago
- Views:
Transcription
1 Group sequential designs with negative binomial data Ekkehard Glimm 1 Tobias Mütze 2,3 1 Statistical Methodology, Novartis, Basel, Switzerland 2 Department of Medical Statistics, University Medical Center Göttingen 3 DZHK (German Centre for Cardiovascular Research), partner site Göttingen, Göttingen, Germany Thanks to Tim Friede and Heinz Schmidli PSI/BBS One-day meeting Basel September 13, 2016
2 1 Motivating examples 2 Fixed design 3 Group sequential designs 4 Assessing operating characteristics 5 Discussion and outlook 2 / 28
3 Motivating examples Example 1: Clinical trials in heart failure Heart failure (HF) with preserved ejection fraction (HFpEF) Primary endpoint: Number of heart failure hospitalizations (HFH) HFH can be modeled with negative binomial distribution (Rogers et al., 2014) Example: the CHARM-Preserved trial (Yusuf et al., 2003) Table: Heart failure hospitalizations in CHARM-preserved Placebo Candesartan Number of patients Total follow-up years Patients with 1 admission Total admissions Rate ratio for recurrent heart failure hospitalizations according to negative binomial model θ = / 28
4 Motivating examples Example 2: Clinical trials in relapsing-remitting multiple sclerosis Primary endpoint: number of combined unique active lesions (CULAs) CULAs are modeled using the negative binomial distribution Example: Phase II study of Siponimod (Selmaj et al., 2013) Placebo and five doses of Siponimod Equal follow-up times (in general either 3 or 6 months) Table: Monthly number of lesions (at 3 months) Placebo Siponimod 0.25 mg Siponimod 0.5 mg Number of patients Monthly CULAS / 28
5 Statistical model Fixed design Number of counts for patient i = 1,..., n j receiving treatment j = 1, 2 Follow-up per patient: t ij Gamma-mixture for the rates Y ij λ ij Pois(t ij λ ij ) λ ij Γ Marginal distribution of counts Expected value and variance ( ) 1 φ, 1 φµ j Y ij NB (t ij µ j, φ) E [Y ij ] = t ij µ j Var [Y ij ] = t ij µ j (1 + φt ij µ j ) 5 / 28
6 Hypothesis testing I Fixed design Statistical hypothesis H 0 : µ 1 µ 2 1 vs. H 1 : µ 1 µ 2 < 1. Hypothesis is tested using a Wald-type test of the maximum-likelihood estimators ˆβ j of the log-rates β j = log(µ j ) Wald-type test statistic T = ˆβ 1 ˆβ 2 1 Îβ1 + 1 Î β2 H 0 N (0, 1) asymp. 6 / 28
7 Hypothesis testing II Fixed design Fisher information of log-rates β j I βj = n j i=1 t ij exp(β j ) 1 + φt ij exp(β j ) = n j i=1 t ij µ j 1 + φt ij µ j. (Reminder: I 1 β j is the asymptotic variance of the MLE ˆβ j.) Information level I fix describes knowledge about unknown treatment effect 1 I fix = 1 I β1 + 1 = I I β1 β2 I I β1 + I β2 β2 Sample size planning by solving equation I fix! = (q 1 β q 1 α ) 2 (β 1 β 2 ) 2 7 / 28
8 Group sequential designs Group sequential designs: Overview Test the hypothesis H 0 at several interim analyses and stop the trial if H 0 can be rejected (stop for efficacy) The interim analyses are performed with the Wald-type test using all data available up to that point in time Counts of patient i in treatment j at analysis k: Y ijk NB(t ijk µ j, φ) t ijk is the follow-up time until analysis k The final analysis is performed when a prespecified information level I max is attained (maximum information trial) 8 / 28
9 Group sequential designs Type I error Type I error Critical values of the individual tests c k must be chosen such that global type I error α, i.e. α P H0 (T k < c k for at least one k = 1,..., K). Allocate global type I error α = K k=1 π k Type I error rate π k for analysis k P H0 (T 1 c 1,..., T k 1 c k 1, T k < c k ) = π k Choose π k through error spending function f : [0, ) [0, α] with f (0) = 0 and f (t) = α, t 1: π 1 = f (I 1 /I max ), π k = f (I k /I max ) f (I k 1 /I max ) k = 2, 3, / 28
10 Critical values Group sequential designs Type I error First critical value is the normal quantile c 1 = q π1 Joint distribution (T 1,..., T k ) required to calculate critical value c k Asymptotic normality of joint distribution has canonical form [Scharfstein et al., 1997] (T 1,..., T k ) N (0, Σ k ) with (Σ k ) (k1,k 2 ) = (Σ k) (k2,k 1 ) = I k1 I k2, 1 k 1 k 2 k. 10 / 28
11 Group sequential designs Practical considerations Type I error Information level depends on rates µ j, shape parameter φ, follow-up times t ijk, and sample size n j At analysis k, I k not known and is estimated by plugging in the rate and shape maximum-likelihood estimators Critical value c k is not determined prior to the trial but at the time of analysis k Î k is the estimated information level of stage k obtained with the data available at interim k 11 / 28
12 Group sequential designs Type I error Practical considerations continued In practice the following estimators are considered ) ˆπ 1 = f (Î1 /I max ) ) ˆπ k = f (Îk /I max f (Îk 1 /I max (ˆΣk ) (k 1,k 2 ) = Îk1 Î k2 k = 2, 3,... Estimated information might decrease if sample sizes or time between analyses is small, i.e. Î k < Î k 1 then analysis is skipped critical value c k = Locally allocated type I error preserves the global type I error K ˆπ k = α i=1 12 / 28
13 Group sequential designs Planning of group sequential trials Planning of group sequential trials Power for given set of critical values c 1,..., c K Power = 1 P H1 (T 1 c 1,..., T K c K ) For rate ratio θ in alternative, joint distribution (T 1,..., T K ) approximately normal with mean vector log(θ )( I 1,..., I K ) For planning purposes, we write I k = w k I max, k = 1,..., K, w k (0, 1] Calculate maximum information I max required to obtain power of 1 β by solving 1 P θ (T 1 c 1,..., T K c K ) = β Sample size, study duration, etc must be selected such that the maximum information is obtained 13 / 28
14 Assessing operating characteristics Simulation study - preface In the simulation, interim analysis time points are determined by theoretical information levels I k. The actual estimated information levels Î k differ from this. Use of spending functions which imitate critical values of Pocock s test and O Brien & Fleming s test Recruitment times uniform in fixed accrual period 14 / 28
15 Assessing operating characteristics Simulation scenarios - type I error Re-hospitalizations in heart failure Simulation scenarios motivated by the number of hospitalizations from Example 1 Parameter Values Type I error rate α Annual rates µ 1 = µ , 0.1, 0.12 Shape parameter φ 2, 3, 4, 5 Group sample size n 1 = n 2 600, 1000, 1400 Stages K 2, 5 Study duration 3.5 (years) Recruitment period 1.25 (years) Monte Carlo replications per scenario 15 / 28
16 Assessing operating characteristics Re-hospitalizations in heart failure Results - type I error Fix O'Brien & Fleming Pocock Maximal group specific sample size Type I error rate 16 / 28
17 Assessing operating characteristics Simulation scenarios - power Re-hospitalizations in heart failure Parameters for the Monte Carlo simulation study of the power Parameter Values Type I error rate α Annual rate µ Annual rate µ Rate ratio µ 1 /µ Group sample size n 1 = n 2 600, 650,..., 1500 Shape parameter φ 5 Stages K 2, 5 Study duration 3.5 (years) Recruitment period 1.25 (years) Monte Carlo replications per scenario 17 / 28
18 Assessing operating characteristics Re-hospitalizations in heart failure Results - power Maximum number of stages: 2 Maximum number of stages: Maximum group specific sample size n 1 Power Design Fix O'Brien & Fleming Pocock 18 / 28
19 Assessing operating characteristics Results - stopping times Re-hospitalizations in heart failure Rejections by stage (O Brien-Fleming, total power of 80%) Maximum number of stages: 2 Maximum number of stages: Rejection rate Analysis k at which the null hypothesis is rejected 19 / 28
20 Assessing operating characteristics Re-hospitalizations in heart failure Results - gains from stopping early Study times at which in theory 25%, 50%, 75%, and 100% of the maximum information level I max is attained Study duration τ Patient 20 / 28
21 Assessing operating characteristics Simulation scenarios - type I error Lesion counts in multiple sclerosis Simulation scenarios motivated by the CULAs from Example 2 Parameter Values Type I error rate α month rates µ 1 = µ 2 6, 8, 10 Shape parameter φ 2, 3, 4 Group sample size n 1 = n 2 50, 70,..., 150 Stages K 2, 3 Individual follow-up 0.5 (years) Recruitment period 1.5 (years) 18 scenarios per group sample size for group sequential designs and 9 scenarios for the fixed design Monte Carlo replications per scenario 21 / 28
22 Assessing operating characteristics Lesion counts in multiple sclerosis Results - type I error Fix O'Brien & Fleming Pocock Maximum group specific sample size Type I error rate 22 / 28
23 Assessing operating characteristics Simulation scenarios - power Lesion counts in multiple sclerosis Parameters for the Monte Carlo simulation study of the power Parameter Values Type I error rate α month rate µ month rate µ Group sample size n 1 = n 2 70, 75,..., 140 Shape parameter φ 3 Stages K 2 Individual follow-up 0.5 (years) Recruitment period 1.5 (years) Monte Carlo replications per scenario 23 / 28
24 Assessing operating characteristics Lesion counts in multiple sclerosis Results - power Maximum number of stages: 2 Maximum number of stages: Maximum group specific sample size n 1 Power Design Fix O'Brien & Fleming Pocock 24 / 28
25 Assessing operating characteristics Lesion counts in multiple sclerosis Results - analysis specific rejection rate Rate of stopping at a specific analysis at a power of 80% Maximum number of stages: 2 Maximum number of stages: Rejection rate Analysis k at which the null hypothesis is rejected 25 / 28
26 Assessing operating characteristics Results - gains from stopping early Lesion counts in multiple sclerosis Study times at which in theory 25%, 50%, 75%, and 100% of the maximum information level I max is attained 90 Patient Study duration τ 26 / 28
27 Discussion and outlook Discussion and outlook Maximum-likelihood theory for negative binomial data results asymptotically in canonical form of joint distribution of test statistic Information level depends on rates, shape parameter, follow-up times, and sample size Future research on group sequential with negative binomial endpoints Blinded information monitoring Adaptive group sequential designs Optimal designs Extend approach to quasi-poisson models in the future 27 / 28
28 Bibliography Discussion and outlook DO. Scharfstein, AA. Tsiatis, JM. Robins (1997). Semiparametric efficiency and its implication on the design and analysis of group-sequential studies. Journal of the American Statistical Association, 92: S. Yusuf et al. (2003) Effects of candesartan in patients with chronic heart failure and preserved left-ventricular ejection fraction: the CHARM-Preserved Trial. The Lancet, 362: JK. Rogers, SJ. Pocock, JJV. McMurray, CB. Granger, EL. Michelson, J. Östergren, MA. Pfeffer, SD. Solomon, K. Swedberg, S. Yusuf (2014) Analysing recurrent hospitalizations in heart failure: a review of statistical methodology, with application to CHARM-Preserved. European Journal of Heart Failure, 16: K. Selmaj, SKB. Li, HP. Hartung, B. Hemmer, L. Kappos, MS. Freedman, O. Stüve, P. Rieckmann, X. Montalban, T. Ziemssen (2013) Siponimod for patients with relapsing-remitting multiple sclerosis (BOLD): an adaptive, dose-ranging, randomised, phase 2 study. The Lancet Neurology, 12: / 28
Group sequential designs for negative binomial outcomes
Group sequential designs for negative binomial outcomes Tobias Mütze a, Ekkehard Glimm b,c, Heinz Schmidli b, and Tim Friede a,d a Department of Medical Statistics, University Medical Center Göttingen,
More informationBlinded sample size reestimation with count data
Blinded sample size reestimation with count data Tim Friede 1 and Heinz Schmidli 2 1 Universtiy Medical Center Göttingen, Germany 2 Novartis Pharma AG, Basel, Switzerland BBS Early Spring Conference 2010
More informationAdaptive designs beyond p-value combination methods. Ekkehard Glimm, Novartis Pharma EAST user group meeting Basel, 31 May 2013
Adaptive designs beyond p-value combination methods Ekkehard Glimm, Novartis Pharma EAST user group meeting Basel, 31 May 2013 Outline Introduction Combination-p-value method and conditional error function
More informationPower assessment in group sequential design with multiple biomarker subgroups for multiplicity problem
Power assessment in group sequential design with multiple biomarker subgroups for multiplicity problem Lei Yang, Ph.D. Statistical Scientist, Roche (China) Holding Ltd. Aug 30 th 2018, Shanghai Jiao Tong
More informationInterim Monitoring of Clinical Trials: Decision Theory, Dynamic Programming. and Optimal Stopping
Interim Monitoring of Clinical Trials: Decision Theory, Dynamic Programming and Optimal Stopping Christopher Jennison Department of Mathematical Sciences, University of Bath, UK http://people.bath.ac.uk/mascj
More informationMultiple Testing in Group Sequential Clinical Trials
Multiple Testing in Group Sequential Clinical Trials Tian Zhao Supervisor: Michael Baron Department of Mathematical Sciences University of Texas at Dallas txz122@utdallas.edu 7/2/213 1 Sequential statistics
More informationOptimising Group Sequential Designs. Decision Theory, Dynamic Programming. and Optimal Stopping
: Decision Theory, Dynamic Programming and Optimal Stopping Christopher Jennison Department of Mathematical Sciences, University of Bath, UK http://people.bath.ac.uk/mascj InSPiRe Conference on Methodology
More informationThe Design of a Survival Study
The Design of a Survival Study The design of survival studies are usually based on the logrank test, and sometimes assumes the exponential distribution. As in standard designs, the power depends on The
More informationType I error rate control in adaptive designs for confirmatory clinical trials with treatment selection at interim
Type I error rate control in adaptive designs for confirmatory clinical trials with treatment selection at interim Frank Bretz Statistical Methodology, Novartis Joint work with Martin Posch (Medical University
More informationTesting 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 informationGroup 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 informationSample size re-estimation in clinical trials. Dealing with those unknowns. Chris Jennison. University of Kyoto, January 2018
Sample Size Re-estimation in Clinical Trials: Dealing with those unknowns Christopher Jennison Department of Mathematical Sciences, University of Bath, UK http://people.bath.ac.uk/mascj University of Kyoto,
More informationGroup sequential designs for Clinical Trials with multiple treatment arms
Group sequential designs for Clinical Trials with multiple treatment arms Susanne Urach, Martin Posch Cologne, June 26, 2015 This project has received funding from the European Union s Seventh Framework
More informationGroup 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 informationOverrunning in Clinical Trials: a Methodological Review
Overrunning in Clinical Trials: a Methodological Review Dario Gregori Unit of Biostatistics, Epidemiology and Public Health Department of Cardiac, Thoracic and Vascular Sciences dario.gregori@unipd.it
More informationPubh 8482: Sequential Analysis
Pubh 8482: Sequential Analysis Joseph S. Koopmeiners Division of Biostatistics University of Minnesota Week 8 P-values When reporting results, we usually report p-values in place of reporting whether or
More informationSAS/STAT 15.1 User s Guide The SEQDESIGN Procedure
SAS/STAT 15.1 User s Guide The SEQDESIGN Procedure This document is an individual chapter from SAS/STAT 15.1 User s Guide. The correct bibliographic citation for this manual is as follows: SAS Institute
More informationCHL 5225H Advanced Statistical Methods for Clinical Trials: Multiplicity
CHL 5225H Advanced Statistical Methods for Clinical Trials: Multiplicity Prof. Kevin E. Thorpe Dept. of Public Health Sciences University of Toronto Objectives 1. Be able to distinguish among the various
More informationMonitoring 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 informationAdaptive Extensions of a Two-Stage Group Sequential Procedure for Testing a Primary and a Secondary Endpoint (II): Sample Size Re-estimation
Research Article Received XXXX (www.interscience.wiley.com) DOI: 10.100/sim.0000 Adaptive Extensions of a Two-Stage Group Sequential Procedure for Testing a Primary and a Secondary Endpoint (II): Sample
More informationAn Adaptive Futility Monitoring Method with Time-Varying Conditional Power Boundary
An Adaptive Futility Monitoring Method with Time-Varying Conditional Power Boundary Ying Zhang and William R. Clarke Department of Biostatistics, University of Iowa 200 Hawkins Dr. C-22 GH, Iowa City,
More informationAdaptive, graph based multiple testing procedures and a uniform improvement of Bonferroni type tests.
1/35 Adaptive, graph based multiple testing procedures and a uniform improvement of Bonferroni type tests. Martin Posch Center for Medical Statistics, Informatics and Intelligent Systems Medical University
More informationThe SEQDESIGN Procedure
SAS/STAT 9.2 User s Guide, Second Edition The SEQDESIGN Procedure (Book Excerpt) This document is an individual chapter from the SAS/STAT 9.2 User s Guide, Second Edition. The correct bibliographic citation
More informationThe Design of Group Sequential Clinical Trials that Test Multiple Endpoints
The Design of Group Sequential Clinical Trials that Test Multiple Endpoints Christopher Jennison Department of Mathematical Sciences, University of Bath, UK http://people.bath.ac.uk/mascj Bruce Turnbull
More informationDivision of Pharmacoepidemiology And Pharmacoeconomics Technical Report Series
Division of Pharmacoepidemiology And Pharmacoeconomics Technical Report Series Year: 2013 #006 The Expected Value of Information in Prospective Drug Safety Monitoring Jessica M. Franklin a, Amanda R. Patrick
More informationPubh 8482: Sequential Analysis
Pubh 8482: Sequential Analysis Joseph S. Koopmeiners Division of Biostatistics University of Minnesota Week 7 Course Summary To this point, we have discussed group sequential testing focusing on Maintaining
More informationPublished online: 10 Apr 2012.
This article was downloaded by: Columbia University] On: 23 March 215, At: 12:7 Publisher: Taylor & Francis Informa Ltd Registered in England and Wales Registered Number: 172954 Registered office: Mortimer
More informationHigh-Throughput Sequencing Course
High-Throughput Sequencing Course DESeq Model for RNA-Seq Biostatistics and Bioinformatics Summer 2017 Outline Review: Standard linear regression model (e.g., to model gene expression as function of an
More informationDesigns for Clinical Trials
Designs for Clinical Trials Chapter 5 Reading Instructions 5.: Introduction 5.: Parallel Group Designs (read) 5.3: Cluster Randomized Designs (less important) 5.4: Crossover Designs (read+copies) 5.5:
More informationEvidence synthesis for a single randomized controlled trial and observational data in small populations
Evidence synthesis for a single randomized controlled trial and observational data in small populations Steffen Unkel, Christian Röver and Tim Friede Department of Medical Statistics University Medical
More informationAdaptive Designs: Why, How and When?
Adaptive Designs: Why, How and When? Christopher Jennison Department of Mathematical Sciences, University of Bath, UK http://people.bath.ac.uk/mascj ISBS Conference Shanghai, July 2008 1 Adaptive designs:
More informationIndependent Increments in Group Sequential Tests: A Review
Independent Increments in Group Sequential Tests: A Review KyungMann Kim kmkim@biostat.wisc.edu University of Wisconsin-Madison, Madison, WI, USA July 13, 2013 Outline Early Sequential Analysis Independent
More informationTesting a Primary and a Secondary Endpoint in a Confirmatory Group Sequential Clinical Trial
Testing a Primary and a Secondary Endpoint in a Confirmatory Group Sequential Clinical Trial ExL Pharma Workshop 2010 Rockville, MD Cyrus R. Mehta President, Cytel Corporation January 26, 2010 email: mehta@cytel.com
More informationApproximating mixture distributions using finite numbers of components
Approximating mixture distributions using finite numbers of components Christian Röver and Tim Friede Department of Medical Statistics University Medical Center Göttingen March 17, 2016 This project has
More informationTwo-stage Adaptive Randomization for Delayed Response in Clinical Trials
Two-stage Adaptive Randomization for Delayed Response in Clinical Trials Guosheng Yin Department of Statistics and Actuarial Science The University of Hong Kong Joint work with J. Xu PSI and RSS Journal
More informationModels for Multivariate Panel Count Data
Semiparametric Models for Multivariate Panel Count Data KyungMann Kim University of Wisconsin-Madison kmkim@biostat.wisc.edu 2 April 2015 Outline 1 Introduction 2 3 4 Panel Count Data Motivation Previous
More informationAdaptive clinical trials with subgroup selection
Adaptive clinical trials with subgroup selection Nigel Stallard 1, Tim Friede 2, Nick Parsons 1 1 Warwick Medical School, University of Warwick, Coventry, UK 2 University Medical Center Göttingen, Göttingen,
More informationFinding Critical Values with Prefixed Early. Stopping Boundaries and Controlled Type I. Error for A Two-Stage Adaptive Design
Finding Critical Values with Prefixed Early Stopping Boundaries and Controlled Type I Error for A Two-Stage Adaptive Design Jingjing Chen 1, Sanat K. Sarkar 2, and Frank Bretz 3 September 27, 2009 1 ClinForce-GSK
More informationBios 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 informationSAMPLE SIZE RE-ESTIMATION FOR ADAPTIVE SEQUENTIAL DESIGN IN CLINICAL TRIALS
Journal of Biopharmaceutical Statistics, 18: 1184 1196, 2008 Copyright Taylor & Francis Group, LLC ISSN: 1054-3406 print/1520-5711 online DOI: 10.1080/10543400802369053 SAMPLE SIZE RE-ESTIMATION FOR ADAPTIVE
More informationGroup Sequential Methods. for Clinical Trials. Christopher Jennison, Dept of Mathematical Sciences, University of Bath, UK
Group Sequential Methods for Clinical Trials Christopher Jennison, Dept of Mathematical Sciences, University of Bath, UK http://wwwbathacuk/ mascj University of Malaysia, Kuala Lumpur March 2004 1 Plan
More informationPubh 8482: Sequential Analysis
Pubh 8482: Sequential Analysis Joseph S. Koopmeiners Division of Biostatistics University of Minnesota Week 5 Course Summary So far, we have discussed Group sequential procedures for two-sided tests Group
More informationAnswer Key for STAT 200B HW No. 7
Answer Key for STAT 200B HW No. 7 May 5, 2007 Problem 2.2 p. 649 Assuming binomial 2-sample model ˆπ =.75, ˆπ 2 =.6. a ˆτ = ˆπ 2 ˆπ =.5. From Ex. 2.5a on page 644: ˆπ ˆπ + ˆπ 2 ˆπ 2.75.25.6.4 = + =.087;
More informationPubh 8482: Sequential Analysis
Pubh 8482: Sequential Analysis Joseph S. Koopmeiners Division of Biostatistics University of Minnesota Week 10 Class Summary Last time... We began our discussion of adaptive clinical trials Specifically,
More informationGeneralizing the MCPMod methodology beyond normal, independent data
Generalizing the MCPMod methodology beyond normal, independent data José Pinheiro Joint work with Frank Bretz and Björn Bornkamp Novartis AG Trends and Innovations in Clinical Trial Statistics Conference
More informationA Gatekeeping Test on a Primary and a Secondary Endpoint in a Group Sequential Design with Multiple Interim Looks
A Gatekeeping Test in a Group Sequential Design 1 A Gatekeeping Test on a Primary and a Secondary Endpoint in a Group Sequential Design with Multiple Interim Looks Ajit C. Tamhane Department of Industrial
More informationEstimation in Flexible Adaptive Designs
Estimation in Flexible Adaptive Designs Werner Brannath Section of Medical Statistics Core Unit for Medical Statistics and Informatics Medical University of Vienna BBS and EFSPI Scientific Seminar on Adaptive
More informationGroup Sequential Tests for Delayed Responses
Group Sequential Tests for Delayed Responses Lisa Hampson Department of Mathematics and Statistics, Lancaster University, UK Chris Jennison Department of Mathematical Sciences, University of Bath, UK Read
More informationasymptotic normality of nonparametric M-estimators with applications to hypothesis testing for panel count data
asymptotic normality of nonparametric M-estimators with applications to hypothesis testing for panel count data Xingqiu Zhao and Ying Zhang The Hong Kong Polytechnic University and Indiana University Abstract:
More informationA Generalized Global Rank Test for Multiple, Possibly Censored, Outcomes
A Generalized Global Rank Test for Multiple, Possibly Censored, Outcomes Ritesh Ramchandani Harvard School of Public Health August 5, 2014 Ritesh Ramchandani (HSPH) Global Rank Test for Multiple Outcomes
More informationHarvard University. Robust alternatives to ANCOVA for estimating the treatment effect via a randomized comparative study
Harvard University Harvard University Biostatistics Working Paper Series Year 2016 Paper 209 Robust alternatives to ANCOVA for estimating the treatment effect via a randomized comparative study Fei Jiang
More informationWhat is Experimental Design?
One Factor ANOVA What is Experimental Design? A designed experiment is a test in which purposeful changes are made to the input variables (x) so that we may observe and identify the reasons for change
More informationGeneralizing the MCPMod methodology beyond normal, independent data
Generalizing the MCPMod methodology beyond normal, independent data José Pinheiro Joint work with Frank Bretz and Björn Bornkamp Novartis AG ASA NJ Chapter 35 th Annual Spring Symposium June 06, 2014 Outline
More informationDuke University. Duke Biostatistics and Bioinformatics (B&B) Working Paper Series. Randomized Phase II Clinical Trials using Fisher s Exact Test
Duke University Duke Biostatistics and Bioinformatics (B&B) Working Paper Series Year 2010 Paper 7 Randomized Phase II Clinical Trials using Fisher s Exact Test Sin-Ho Jung sinho.jung@duke.edu This working
More informationclinical trials Abstract Multi-arm multi-stage (MAMS) trials can improve the efficiency of the drug
A multi-stage drop-the-losers design for multi-arm clinical trials James Wason 1, Nigel Stallard 2, Jack Bowden 1, and Christopher Jennison 3 1 MRC Biostatistics Unit, Cambridge 2 Warwick Medical School,
More informationComparing 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 informationBayesian inference for a principal stratum estimand to assess the treatment effect in a subgroup characterized by post-randomization events
arxiv:1809.03741v1 [stat.ap] 11 Sep 2018 Bayesian inference for a principal stratum estimand to assess the treatment effect in a subgroup characterized by post-randomization events Baldur P. Magnusson
More informationStatistics and Probability Letters. Using randomization tests to preserve type I error with response adaptive and covariate adaptive randomization
Statistics and Probability Letters ( ) Contents lists available at ScienceDirect Statistics and Probability Letters journal homepage: wwwelseviercom/locate/stapro Using randomization tests to preserve
More informationTwo-stage k-sample designs for the ordered alternative problem
Two-stage k-sample designs for the ordered alternative problem Guogen Shan, Alan D. Hutson, and Gregory E. Wilding Department of Biostatistics,University at Buffalo, Buffalo, NY 14214, USA July 18, 2011
More informationGroup Sequential Methods. for Clinical Trials. Christopher Jennison, Dept of Mathematical Sciences, University of Bath, UK
Group Sequential Methods for Clinical Trials Christopher Jennison, Dept of Mathematical Sciences, University of Bath, UK http://www.bath.ac.uk/οmascj PSI, London, 22 October 2003 1 Plan of talk 1. Why
More informationGroup-Sequential Tests for One Proportion in a Fleming Design
Chapter 126 Group-Sequential Tests for One Proportion in a Fleming Design Introduction This procedure computes power and sample size for the single-arm group-sequential (multiple-stage) designs of Fleming
More informationTECHNICAL REPORT # 59 MAY Interim sample size recalculation for linear and logistic regression models: a comprehensive Monte-Carlo study
TECHNICAL REPORT # 59 MAY 2013 Interim sample size recalculation for linear and logistic regression models: a comprehensive Monte-Carlo study Sergey Tarima, Peng He, Tao Wang, Aniko Szabo Division of Biostatistics,
More informationParametric Modelling of Over-dispersed Count Data. Part III / MMath (Applied Statistics) 1
Parametric Modelling of Over-dispersed Count Data Part III / MMath (Applied Statistics) 1 Introduction Poisson regression is the de facto approach for handling count data What happens then when Poisson
More informationNATIONAL UNIVERSITY OF SINGAPORE EXAMINATION (SOLUTIONS) ST3241 Categorical Data Analysis. (Semester II: )
NATIONAL UNIVERSITY OF SINGAPORE EXAMINATION (SOLUTIONS) Categorical Data Analysis (Semester II: 2010 2011) April/May, 2011 Time Allowed : 2 Hours Matriculation No: Seat No: Grade Table Question 1 2 3
More informationComparing two independent samples
In many applications it is necessary to compare two competing methods (for example, to compare treatment effects of a standard drug and an experimental drug). To compare two methods from statistical point
More informationc Copyright 2014 Navneet R. Hakhu
c Copyright 04 Navneet R. Hakhu Unconditional Exact Tests for Binomial Proportions in the Group Sequential Setting Navneet R. Hakhu A thesis submitted in partial fulfillment of the requirements for the
More informationAdaptive Enrichment Designs for Randomized Trials with Delayed Endpoints, using Locally Efficient Estimators to Improve Precision
Adaptive Enrichment Designs for Randomized Trials with Delayed Endpoints, using Locally Efficient Estimators to Improve Precision MICHAEL ROSENBLUM, TIANCHEN QIAN, YU DU, and HUITONG QIU Department of
More informationSTAT 526 Spring Final Exam. Thursday May 5, 2011
STAT 526 Spring 2011 Final Exam Thursday May 5, 2011 Time: 2 hours Name (please print): Show all your work and calculations. Partial credit will be given for work that is partially correct. Points will
More information1 One-way analysis of variance
LIST OF FORMULAS (Version from 21. November 2014) STK2120 1 One-way analysis of variance Assume X ij = µ+α i +ɛ ij ; j = 1, 2,..., J i ; i = 1, 2,..., I ; where ɛ ij -s are independent and N(0, σ 2 ) distributed.
More informationPSI Journal Club March 10 th, 2016
PSI Journal Club March 1 th, 1 The analysis of incontinence episodes and other count data in patients with Overactive Bladder (OAB) by Poisson and negative binomial regression Martina R, Kay R, van Maanen
More informationMETHODS OF EVALUATION OF PERFORMANCE OF ADAPTIVE DESIGNS ON TREATMENT EFFECT INTERVALS AND METHODS OF
METHODS OF EVALUATION OF PERFORMANCE OF ADAPTIVE DESIGNS ON TREATMENT EFFECT INTERVALS AND METHODS OF DESIGNING TWO-STAGE WINNER DESIGNS WITH SURVIVAL OUTCOMES BY FANG FANG A dissertation submitted to
More informationImpact 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 informationRepeated confidence intervals for adaptive group sequential trials
STATISTICS IN MEDICINE Statist. Med. 2007; 26:5422 5433 Published online 4 October 2007 in Wiley InterScience (www.interscience.wiley.com).3062 Repeated confidence intervals for adaptive group sequential
More informationPoisson Regression. Ryan Godwin. ECON University of Manitoba
Poisson Regression Ryan Godwin ECON 7010 - University of Manitoba Abstract. These lecture notes introduce Maximum Likelihood Estimation (MLE) of a Poisson regression model. 1 Motivating the Poisson Regression
More information9 Generalized Linear Models
9 Generalized Linear Models The Generalized Linear Model (GLM) is a model which has been built to include a wide range of different models you already know, e.g. ANOVA and multiple linear regression models
More informationPower and Sample Size Calculations with the Additive Hazards Model
Journal of Data Science 10(2012), 143-155 Power and Sample Size Calculations with the Additive Hazards Model Ling Chen, Chengjie Xiong, J. Philip Miller and Feng Gao Washington University School of Medicine
More informationCase Study in the Use of Bayesian Hierarchical Modeling and Simulation for Design and Analysis of a Clinical Trial
Case Study in the Use of Bayesian Hierarchical Modeling and Simulation for Design and Analysis of a Clinical Trial William R. Gillespie Pharsight Corporation Cary, North Carolina, USA PAGE 2003 Verona,
More informationA Type of Sample Size Planning for Mean Comparison in Clinical Trials
Journal of Data Science 13(2015), 115-126 A Type of Sample Size Planning for Mean Comparison in Clinical Trials Junfeng Liu 1 and Dipak K. Dey 2 1 GCE Solutions, Inc. 2 Department of Statistics, University
More informationMonitoring clinical trial outcomes with delayed response: Incorporating pipeline data in group sequential and adaptive designs. Christopher Jennison
Monitoring clinical trial outcomes with delayed response: Incorporating pipeline data in group sequential and adaptive designs Christopher Jennison Department of Mathematical Sciences, University of Bath,
More informationPoisson regression 1/15
Poisson regression 1/15 2/15 Counts data Examples of counts data: Number of hospitalizations over a period of time Number of passengers in a bus station Blood cells number in a blood sample Number of typos
More informationFall 2017 STAT 532 Homework Peter Hoff. 1. Let P be a probability measure on a collection of sets A.
1. Let P be a probability measure on a collection of sets A. (a) For each n N, let H n be a set in A such that H n H n+1. Show that P (H n ) monotonically converges to P ( k=1 H k) as n. (b) For each n
More informationThe assessment of non-inferiority in a gold standard design with censored, exponentially distributed endpoints
The assessment of non-inferiority in a gold standard design with censored, exponentially distributed endpoints M. Mielke Department of Mathematical Stochastics, University Göttingen e-mail: mmielke@math.uni-goettingen.de
More informationOn the efficiency of two-stage adaptive designs
On the efficiency of two-stage adaptive designs Björn Bornkamp (Novartis Pharma AG) Based on: Dette, H., Bornkamp, B. and Bretz F. (2010): On the efficiency of adaptive designs www.statistik.tu-dortmund.de/sfb823-dp2010.html
More informationSession 3 The proportional odds model and the Mann-Whitney test
Session 3 The proportional odds model and the Mann-Whitney test 3.1 A unified approach to inference 3.2 Analysis via dichotomisation 3.3 Proportional odds 3.4 Relationship with the Mann-Whitney test Session
More informationSequential Testing in Reliability and Validity Studies With Repeated Measurements per Subject
http://ijsp.ccsenet.org International Journal of Statistics and Probability Vol. 8, No. 1; 019 Sequential Testing in Reliability and Validity Studies With Repeated Measurements per Subject Steven B. Kim
More informationA Gate-keeping Approach for Selecting Adaptive Interventions under General SMART Designs
1 / 32 A Gate-keeping Approach for Selecting Adaptive Interventions under General SMART Designs Tony Zhong, DrPH Icahn School of Medicine at Mount Sinai (Feb 20, 2019) Workshop on Design of mhealth Intervention
More informationOn the Inefficiency of the Adaptive Design for Monitoring Clinical Trials
On the Inefficiency of the Adaptive Design for Monitoring Clinical Trials Anastasios A. Tsiatis and Cyrus Mehta http://www.stat.ncsu.edu/ tsiatis/ Inefficiency of Adaptive Designs 1 OUTLINE OF TOPICS Hypothesis
More informationTESTING FOR HOMOGENEITY IN COMBINING OF TWO-ARMED TRIALS WITH NORMALLY DISTRIBUTED RESPONSES
Sankhyā : The Indian Journal of Statistics 2001, Volume 63, Series B, Pt. 3, pp 298-310 TESTING FOR HOMOGENEITY IN COMBINING OF TWO-ARMED TRIALS WITH NORMALLY DISTRIBUTED RESPONSES By JOACHIM HARTUNG and
More informationModeling the scale parameter ϕ A note on modeling correlation of binary responses Using marginal odds ratios to model association for binary responses
Outline Marginal model Examples of marginal model GEE1 Augmented GEE GEE1.5 GEE2 Modeling the scale parameter ϕ A note on modeling correlation of binary responses Using marginal odds ratios to model association
More informationPrecision of maximum likelihood estimation in adaptive designs
Research Article Received 12 January 2015, Accepted 24 September 2015 Published online 12 October 2015 in Wiley Online Library (wileyonlinelibrary.com) DOI: 10.1002/sim.6761 Precision of maximum likelihood
More informationInterim Monitoring of. Clinical Trials. Christopher Jennison, Dept of Mathematical Sciences, University of Bath, UK
Interim Monitoring of Clinical Trials Christopher Jennison, Dept of Mathematical Sciences, University of Bath, UK http://www.bath.ac.uk/οmascj Magdeburg, 1 October 2003 1 Plan of talk 1. Why sequential
More informationMasters Comprehensive Examination Department of Statistics, University of Florida
Masters Comprehensive Examination Department of Statistics, University of Florida May 6, 003, 8:00 am - :00 noon Instructions: You have four hours to answer questions in this examination You must show
More informationAnalysis of Time-to-Event Data: Chapter 4 - Parametric regression models
Analysis of Time-to-Event Data: Chapter 4 - Parametric regression models Steffen Unkel Department of Medical Statistics University Medical Center Göttingen, Germany Winter term 2018/19 1/25 Right censored
More informationSample Size and Power I: Binary Outcomes. James Ware, PhD Harvard School of Public Health Boston, MA
Sample Size and Power I: Binary Outcomes James Ware, PhD Harvard School of Public Health Boston, MA Sample Size and Power Principles: Sample size calculations are an essential part of study design Consider
More informationBayesian Spatial Point Process Modeling of Neuroimaging Data
Bayesian Spatial Point Process Modeling of Neuroimaging Data Timothy D. Johnson Department of Biostatistics University of Michigan Johnson (University of Michigan) June 14, 2012 1 / 17 Outline 1 Acknowledgements
More informationREGRESSION ANALYSIS FOR TIME-TO-EVENT DATA THE PROPORTIONAL HAZARDS (COX) MODEL ST520
REGRESSION ANALYSIS FOR TIME-TO-EVENT DATA THE PROPORTIONAL HAZARDS (COX) MODEL ST520 Department of Statistics North Carolina State University Presented by: Butch Tsiatis, Department of Statistics, NCSU
More informationSTAC51: Categorical data Analysis
STAC51: Categorical data Analysis Mahinda Samarakoon January 26, 2016 Mahinda Samarakoon STAC51: Categorical data Analysis 1 / 32 Table of contents Contingency Tables 1 Contingency Tables Mahinda Samarakoon
More informationTUTORIAL 8 SOLUTIONS #
TUTORIAL 8 SOLUTIONS #9.11.21 Suppose that a single observation X is taken from a uniform density on [0,θ], and consider testing H 0 : θ = 1 versus H 1 : θ =2. (a) Find a test that has significance level
More informationDose-response modeling with bivariate binary data under model uncertainty
Dose-response modeling with bivariate binary data under model uncertainty Bernhard Klingenberg 1 1 Department of Mathematics and Statistics, Williams College, Williamstown, MA, 01267 and Institute of Statistics,
More informationSecondary Progressive Multiple Sclerosis
Secondary Progressive Multiple Sclerosis A Detailed Overview Pharmascroll A Pharmascroll Publication This publication is meant to be used only for Pharmascroll clients post subscription. Table of Contents
More information