SAMPLE SIZE RE-ESTIMATION FOR BINARY DATA VIA CONDITIONAL POWER
|
|
- Joanna Washington
- 6 years ago
- Views:
Transcription
1 SAPE SIZE RE-ESIAION FOR BINARY DAA VIA ONDIIONA POWER. Wang, D.S. Keller and K.K.G an. Wang and D.S. Keller, Pfizer Inc, Groton, K.K.G. an, Aventis Pharmaceuticals, Bridgewater, NJ Key Words: Sample size re-estimation, onditional power, Binary data, Noninferiority, ype I error rate Abstract: We extend an and rost s (997,999) conditional power approach for interim sample size re-estimation to binary data for clinical trials with a noninferiority objective. If conditional power is used to extend a trial, the α level will be inflated. On the contrary if it is used to stop a trial early to claim futility, the α level will be reduced. If inflation does not exceed deflation, then the α level will be maintained. Simulations were used to estimate probabilities of ype I error for a range of typical clinical trial situations commonly encountered in Veterinary edicine. he simulation results demonstrated that the procedure preserves ype I error rate. hroughout, hypothetical examples will be used to illustrate the procedure. his intuitive, simple and flexible procedure is recommended for use in clinical trials.. linical rial Setting/introduction onsider the following clinical trial situation. A sponsor was to test a novel compound for Veterinary edical use. A typical multi-center, double blind, randomized two -arm trial was envisioned. he clinical end point was binary success or failure of the treatment. Due to ethical concerns, a positive control was needed. Per IH Guideline and preliminary discussion with a regulatory agency, a noninferiority test of the test compound over the positive control was required. he sponsor and the regulatory agency mutually agreed ) that the minimum sample size per arm should be 00 patients, 2) that the noninferiority margin should be 5 percentage points, and 3) the significance level should be one-sided 5%. Also result of Freedom of Information, the treatment success rate of the positive control was known to be about 75%. Without sufficient early trial information, the sponsor was unsure about the efficacy of the test compound but thought it should be comparable to the positive control (75%). Under a fixed design, the trial statistician performed some sample size/power analyses for true effect sizes of the test compound up to 5% lower than the reference (able ). able. Sample Size and Power Percent Success (%) Positive Power SS** ontrol est (%)* * denotes power with 00 cases per arm, and ** denotes sample size (SS) per arm to achieve 80% of power What sample size should the sponsor use? If the efficacy was comparable to the positive control, the minimum sample size of 00 required by the agency should be sufficient to achieve a power of approximately 80%. On the other extreme, if the test compound performed 5 percentage points worse than the control, the sample size requirement increased substantially to 246. onservatively, to ensure success of the trial, a sample size of 246 would be needed. However, if the efficacy of the test was comparable to or better than the control, this would amount to a considerable waste of resources, since 00 subjects per arm would be sufficient. Fortunately, recent advances in flexible/adaptive trial design and interim analysis were used to resolve this dilemma. With concurrence from the regulatory agency, the sponsor proposed to perform an interim analysis to reassess the sample size requirement. Flexible/adaptive trial design and interim data analysis are active areas of research in recent years. Increased knowledge has contributed to greater use of these methods in clinical trials (O Neill, 994; IH E-9, 999). Gould (200) provided a comprehensive review of interim sample size re -estimation in methodology developments and their uses in practice. onditional power (P) (an et al., 982, 984; Halperin et al., 987; Proschan and Hunsberger, 995; Snapinn, 992) has been advanced as a useful tool to manage clinical trials. Its properties and uses have been elucidated in an and rost (997, 999), 362
2 ooper et al. (200), Siu and an (200), among others. In this paper, we extend this P approach (an and rost, 997, 999) to the aforementioned clinical trial situation. he proposed procedure does not require α spending or increase critical values to preserve overall α. It is well known that if a trial is extended, the α level will be inflated. On the contrary if a trial is terminated early to claim futility, the α level will be reduced. If inflation does not exceed deflation, then the α level will be maintained. he proposed procedure combines sample size reestimation with early trial termination for futility such that the nominal α level is preserved. Explicitly, the objectives of this paper are: ) to extend the an and rost s (997, 999) P approach to sample size re-estimation for binary data with a noninferiority study objective, 2) to validate the proposed procedure in terms of α level preservation using simulations under trial conditions applicable for Veterinary edicine, and 3) to illustrate the procedure using hypothetical examples. 2. Hypothesis et denote the test article and denote the positive control. Further let p and p be probabilities of treatment successes for test and control respectively. Noninferiority margin is denoted by δ (a positive number). he null hypothesis is that the test is inferior to the positive control by a noninferiority margin δ. Explicitly, the null and the alternative hypotheses are: H : p p δ H 0 A : p > p δ 3. est: One-sided Z test he Z test statistic is pˆ pˆ + δ λˆ + δ Z SE SE where pˆ pˆ n λˆ () pˆ is the estimated success rate of the test article, with n as the observed number of successful patients and as the total number of n successful patients in the test group, pˆ is the estimated success rate of the positive control, with n as the observed number of successful patients and as the total number of patients in the positive control group, and SE pˆ ( pˆ ) / + pˆ ( pˆ ) / /. Reject λ ˆ { } 2 H 0 (concluding noninferiority), if Z. Z α Equivalently, noninferiority will be concluded if the one-sided lower limit of the difference between the estimated success rates is greater than or equal to the negative of the noninferiority margin δ, i.e., if ( pˆ pˆ ) Z SE δ. 4. B-value 0.95 pˆ pˆ Without loss of generality, let be the total sample size per group, and r be the number of patients per group at the interim check. he information fraction is defined as r /. (2) he Z value at, denoted by Z can be calculated as in () using the available patients (total number of patients 2r). he B value calculated at the information fraction (an and Wittes, 988) is: B Z. (3) 5. onditional power he conditional power to declare noninferiority given the currently observed data, a total sample size of per treatment and the treatment effect is calculated as (an and Wittes, 988): P P[B Z, θ] B E(B Z P[ V(B α α V(B E(B, θ] Z α E(B P[N(0,) ] (4) where E(B B + ( θ is the mean and ), θ) V(B is the variance of the conditional normal distribution, with E (B ) Z (βype II error). θ α + Z β Assume the current treatment trend continues, then θ B / and E(B, θ ) B, so Eq. (4) becomes Z P P[ N(0,) α B / / ]. (5) 3622
3 6. Sample size required to achieve a certain level of conditional power From (4), we have Z α E(B, θ) ZP (6) with P Φ(Z ), and Φ Z ) the cumulative P ( P standard normal distribution evaluated at Z P. Assume the current treatment trend continues, Eq. (6) becomes Z α B / ZP (7) with defined in (2) and B defined in (3). Eq. (7) can be expressed as r ZP + Z Z α 0 (8) r he total sample size () required to achieve conditional power of P is obtained by solving Eq. (8). 7. An example calculation of P and sample size For illustration purposes, we provide example calculations for the following conditions: δ 0.5, r 50, 200, r / 50 / , pˆ 0.70, estimated at, and SE pˆ 0.75, estimated at. { pˆ ( pˆ ) / r + pˆ ( pˆ ) / r} / 2 λ ˆ he Z vale at is: pˆ ˆ pˆ + δ λ + δ Z SE SE pˆ pˆ he B vale at is: B Z For our case, α.05, Z λˆ he conditional power to declare noninferiority given the observed data, a total scheduled sample size of 200 patients per treatment, and the current treatment trend, is P P[B , θ ] B P[ ] P[N(0,) ] with the current treatment trend, θ B / / , and E(B B + ( ) θ ( 0.25) he total sample size required per group to achieve a certain level of conditional power is obtained by solving Eq. (8). For P80%, Z P , the equation becomes he solution is Interim sample size re-estimation procedure he procedure consists of the following steps and decision rules: With an interim sample size r, calculate success rates by treatment group. If the estimated success rate of the test is d (d>0) less than that of the positive control (i.e., pˆ pˆ ) d ), then stop ( the trial and fail to demonstrate noninferiority. If not, calculate Z as in Eq. (). Solve Eq. (8) for to achieve P c U (where c U is the desirable P for the trial) assuming the treatment trend estimated at the interim continues. If < min reset min, where min is the minimum sample size required; If > reset, where is the imum sample size affordable. alculate P as in Eq. (5) given assuming the treatment trend estimated at the interim continues. If P < c then stop the trial and fail to demonstrate noninferiority, where c is the minimu m acceptable P for continuing the trial. If P c then continue the trial with a sample size of min. Reject H 0 if Z Z α. 3623
4 For the hypothetical trial introduced in Section, we set d 0.3, c 0.3, c 0. 8, r50, min 00 and 250. U 9. ype I error rate evaluation for the proposed interim sample size re-estimation procedure using simulation he question is: does the procedure proposed in Section 8 preserve ype I error rate? Due to flexibility of the procedure, no attempt was made to evaluate this property analytically. Instead, simulations were conducted to evaluate the ype I error rates of the procedure for the following conditions under the null hypothesis that test is inferior to the positive control by an noninferiority margin of 0.5 in terms of success rate: One-sided significance level: 5% inimum sample size required per group: 00 aximum sample size affordable per group: 250 Noninferiority margin: 0.5 Sample size per group at the interim check: 50 inimum estimated success rate difference at the interim check to stop the trial early to claim futility: d 0., 0.2, and 0.3. inimum conditional power at the interim check to continue the trial: c 0.2, 0.3, and 0. 4 Desirable conditional power at the interim check: c U 0.8 rue success rates for the positive control ( p ): 0.75, 0.8, 0.85, 0.9, and Under null hypothesis, the corresponding true success rates for the test article ( p ): 0.60, 0.65, 0.70, 0.75, and he above parameter specifications resulted in a total of 45 combinations. Each simulation combination was replicated,000,000 times. Probabilities of ype I error were estimated. For example, the estimated probability of ype I error was for d 0.3, c 0. 3 and p able 2 summarizes estimated probabilities of ype I error for all the selected simulated combinations. able 2. Estimated probabilities of ype I error for selected combinations d rue Success Rate for Positive ontrol (est) c.75 (.60).80 (.65).85 (.70).90 (.75).95 (.80) he results in able 2 demonstrated that under a wide range of use conditions, the proposed interim sample size re-estimation procedure preserves the overall α level. Given d 0.3 and c 0. 3 with the true success rates for the positive control between.75 and.90, the estimated probabilities of ype I error were less than or equal to the nominal level of 5%. 0. Example uses able 3 provides 8 hypothetical trials, and their interim results and impact on decision making under the following conditions specified a priori: α5%, δ0.5, d 0.3, c 0. 3, c U 0. 8, r50, min 00 and 250. For trials and 2, a total of 00 subjects per arm will provide a P of 97% and 87%, respectively, assuming the current treatment trend continues. So the interim decisions are to continue the trials. For trials 3 and 4, extending the trials to 9 (trial 3) and 227 (rial 4) subjects per arm will reach the desired P of 80%, so the trials will be continued. With 250 subjects per arm, rial 5 will yield a P of 65%. Should the trial be continued? It is up to the sponsor to decide to continue the trial or not with P65%. However, it is not proper to extend the trial beyond 250 subjects per arm to reach a P of 80%, because 3624
5 the a priori imum sample size was set at 250. For rial 6, according to the a priori specifications, the sponsor has an option to continue the trial to 250 subjects per arm, realizing the P is only 32%. It is more likely that the sponsor would terminate the trial early for futility owing to such a low P. his will have an effect of further deflating the α. In realistic trial situations, c can be raised further to a higher level, say 0.5. How likely would a sponsor continue a trial given a 50% of P? learly, rials 7 and 8 will be terminated early for futility due to low Ps (<c 0.3) for both trials and low efficacy of the test group ( pˆ pˆ ) 0.3 d ) for trial 8. ( able 3. Examples of interim sample size reestimation and decision making rial pˆ pˆ P (%) Interim Decision ontinue ontinue ontinue ontinue Pending Pending erminate erminate. Discussion We have proposed an interim sample size reestimation procedure via conditional power for binary data in clinical trials with a noninferiority objective. he procedure is an extension of an and rost (997, 999). he essence of the procedure is that if a trial is extended, the α level will be inflated and that on the contrary if a trial is stopped early to claim futility, the α level will be reduced. If inflation does not exceed deflation, then the α level will be maintained. he simulations demonstrated that the procedure preserves the nominal α under a wide range of trial conditions commonly encountered in Veterinary edicine clinical trials. Other trial situations can be simulated accordingly. As such, the procedure does not require α spending or increase critical values of the statistical test. he procedure is flexible to handle realistic trial conditions. In our settings, the procedure incorporated minimum, imum sample size requirements, imum efficacy deficiency of the test compound to the control for continuing the trial, minimum and desirable P to extend the trial. Any other trial conditions can be accommodated. Due to its flexibility, no analytical proof of α preservation was attempted. Rather, it is recommended to conduct simulations for each trial situation to demonstrate α preservation. onditions under which α will be maintained are easy to find. For example, increasing the lower limit of P (c ) will have a dramatic effect on α deflation. he procedure has been investigated to compare two means and two survival curves (an and rost, 997, 999; Siu and an, 200) for superiority testings. We extended the procedure to binary data for sample size re -estimation with a noninferiority objective. With a modification to the test statistics, the procedure is applicable to superiority and equivalence test situations as well. he procedure can be easily extended to multi-stages of interim sample size re-estimation. he P approach does require unblinding the data at interim. his raises the issue of interim data integrity, scope of information sharing, potential for introduction of operational bias and trial management. With proper planning and management, these concerns can be addressed satisfactorily. It is anticipated that with more understanding of the procedure and better trial and data management, this intuitive, simple and flexible procedure will find more use in clinical trials. 2. References ooper, J., K. Anderson and. akshminarayanan (200) Evaluation of sample size re -estimation using group sequential design and conditional power. American Statistical Association, Proceedings of the Biopharmaceutical Section, 200. Gould, A.. (200) Sample size re-estimation: recent developments and practical considerations. Statistics in edicine 20: Halperin,., K.K.G. an, E.. Wright and.a. Foulkes (987) Stochastic curtailing for comparison of slopes in longitudinal studies. ontrolled linical rials 8: IH E-9 Expert Working Group (999) Statistical principles for clinical trials (IH Harmonized ripartite Guideline E-9). Statistics in edicine 8: an, K.K.G., R. Simon and. Halperin (982) Stochastically curtailed tests in long term 3625
6 clinical trials. ommunications in Statistics- Sequential Analysis : an, K.K.G., D.. Deets and. Halperin (984) ore flexible sequential and non-sequential designs in long-term clinial trials. ommunications in Statistics, Part A heory and ethods 3: an, K.K.G. and J. Wittes (988) he B-value: a tool for monitoring data. Biometrics 44: an, K.K.G and D.. rost (997) Estimation of parameters and sample size re-estimation. American Statistical Association, Proceedings of the Biopharmaceutical Section 997: an, K.K.G. and D.. rost (999) he use of conditional power in interim analysis. Pfizer echnical Report pages. O Neill, R.. (994) Interim Analysis. A regulatory perspective on data mo nitoring and interim analysis. Statistics in the pharmaceutical industry. Edited by. Ralph Buncher, Jia- Yeong say. Second Edition. arcel Dekker, Inc. New York. Proschan,.A. and S.A. Hunsberger (995) Designed extension of studies based on conditional power. Biometrics 5: Siu,.O. and K.K.G. an (200) Flexible interim analysis method for sample size re -estimation and early stopping: a conditional power approach. American Statistical Association, Proceedings of the Biopharmaceutical Section, 200. Snapinn, S.. (992) onitoring clinical trials with a conditional probability stopping rule. Statistics in edicine :
Adaptive Design for Clinical Trials
Adaptive Design for Clinical Trials Mark Chang Millennium Pharmaceuticals, Inc., Cambridge, MA 02139,USA (e-mail: Mark.Chang@Statisticians.org) Abstract. Adaptive design is a trial design that allows modifications
More informationAdaptive Design for Medical Device Development
Adaptive Design for Medical Device Development A guide to accelerate clinical development and enhance portfolio value Executive Summary In May 2015, the FDA released a draft guidance document regarding
More informationINTERNAL PILOT DESIGNS FOR CLUSTER SAMPLES
INTERNAL PILOT DESIGNS FOR CLUSTER SAMPLES CHRISTOPHER S. COFFEY University of Alabama at Birmingham email: ccoffey@uab.edu website: www.soph.uab.edu/coffey MATTHEW J. GURKA University of Virginia KEITH
More informationA sequential test procedure for monitoring a singular safety and efficacy outcome
Tropical Journal of Pharmaceutical Research, December 2003; 2 (2): 97-206 Pharmacotherapy Group, Faculty of Pharmacy, University of Benin, Benin City, Nigeria. All rights reserved. Available online at
More informationDisclaimer This presentation expresses my personal views on this topic and must not be interpreted as the regulatory views or the policy of the FDA
On multiplicity problems related to multiple endpoints of controlled clinical trials Mohammad F. Huque, Ph.D. Div of Biometrics IV, Office of Biostatistics OTS, CDER/FDA JSM, Vancouver, August 2010 Disclaimer
More informationNovel multiple testing procedures for structured study objectives and families of hypotheses a case study
Novel multiple testing procedures for structured study objectives and families of hypotheses a case study Guenther Mueller-Velten Novartis Pharma AG EMA Workshop on Multiplicity Issues in Clinical Trials
More informationThe Promise and Challenge of Adaptive Design in Oncology Trials
THE POWER OFx Experts. Experience. Execution. The Promise and Challenge of Adaptive Design in Oncology Trials Clinical oncology trials are more complex and time consuming than those in any other therapeutic
More informationShort Course: Adaptive Clinical Trials
Short Course: Adaptive Clinical Trials Presented at the 2 Annual Meeting of the Society for Clinical Trials Vancouver, Canada Roger J. Lewis, MD, PhD Department of Emergency Medicine Harbor-UCLA Medical
More informationDOI: /CIRCULATIONAHA
Optimizing Trial Design: Sequential, Adaptive, and Enrichment Strategies Cyrus Mehta, Ping Gao, Deepak L. Bhatt, Robert A. Harrington, Simona Skerjanec and James H. Ware Circulation 2009;119;597-605 DOI:
More informationTwenty-five years of confirmatory adaptive designs: opportunities and pitfalls
Featured Article Received 2 September 2014, Accepted 19 February 2015 Published online in Wiley Online Library (wileyonlinelibrary.com) DOI: 10.1002/sim.6472 Twenty-five years of confirmatory adaptive
More informationDMC membership experience. P.Bauer Basel May 2016
DMC membership experience P.Bauer Basel May 2016 EMA GUIDELINE ON DATA MONITORING COMMITTEES Clinical trials frequently extend over a long period of time. Thus, for ethical reasons it is desirable to ensure
More informationComments from the FDA Working Group on SUBGROUP ANALYSES. Estelle Russek-Cohen, Ph.D. U.S. Food and Drug Administration Center for Biologics
Comments from the FDA Working Group on SUBGROUP ANALYSES Estelle Russek-Cohen, Ph.D. U.S. Food and Drug Administration Center for Biologics 1 Outline An intro to FDA EMA and FDA on subgroups Companion
More informationThe Role of Adaptive Designs in Clinical Development Program*
The Role of Adaptive Designs in Clinical Development Program* Sue-Jane Wang, Ph.D. Associate Director, Adaptive Design and Pharmacogenomics Office of Biostatistics, Office of Translational Sciences Center
More informationImplementing type I & type II error spending for two-sided group sequential designs
Available online at www.sciencedirect.com Contemporary Clinical Trials 29 (2008) 351 358 www.elsevier.com/locate/conclintrial Implementing type I & type II error spending for two-sided group sequential
More informationAn Overview of Bayesian Adaptive Clinical Trial Design
An Overview of Bayesian Adaptive Clinical Trial Design Roger J. Lewis, MD, PhD Department of Emergency Medicine Harbor-UCLA Medical Center David Geffen School of Medicine at UCLA Los Angeles Biomedical
More informationResponse Adjusted for Duration of Antibiotic Risk (RADAR) Scott Evans, Ph.D., M.S. Harvard University
Response Adjusted for Duration of Antibiotic Risk (RADAR) Scott Evans, Ph.D., M.S. Harvard University CTTI Statistical Think Tank Expert Meeting November 19, 2014 Special Thank You Kunal Merchant Dan Rubin
More informationMRC Biostatistics Unit
MRC Biostatistics Unit Adrian Mander MRC Biostatistics Unit Hub for Trials Methodology Research Cambridge June 2014 Adrian Mander June 2014 1/12 MRC Biostatistics Unit The 4 themes DART Design and Analysis
More informationDesign Consideration for Simultaneous Global Drug Development Program (SGDDP)*
Design Consideration for Simultaneous Global Drug Development Program (SGDDP)* Qin Huang 1 ( 黄钦 ),Gang Chen 2 ( 陈刚 ) DIA China, May 18, 2011 1. Office of Biostatistics, Center for Drug Evaluation, SFDA,
More informationSample Size and Power. Objectives. Take Away Message
Sample Size and Power Laura Lee Johnson, Ph.D. Statistician National Center for Complementary and Alternative Medicine johnslau@mail.nih.gov Fall 2011 Objectives Calculate changes in sample size based
More informationPOPULATION ENRICHMENT DESIGNS FOR ADAPTIVE CLINICAL TRIALS. An Aptiv Solutions White Paper
FOR ADAPTIVE CLINICAL TRIALS An Aptiv Solutions White Paper EXECUTIVE SUMMARY The increasing pressure on governments caused by the spiraling healthcare costs is leading to a growing demand by payers for
More informationClinical Trial Optimization via Simulations. Thursday November 9, 2017
Clinical Trial Optimization via Simulations Thursday November 9, 2017 Clinical Trial Optimization via Simulations Today s Forum is hosted by the MassBio Biostatistics/Statistical Programming/Data Management/Clinical
More informationGuidance on Data Monitoring Committee: Regulatory Perspective in Japan
Austria-Japan Joint Statistics Workshop Data monitoring committees in clinical trials Guidance on Data Monitoring Committee: Regulatory Perspective in Japan Yuki Ando Senior Scientist for Biostatics Pharmaceuticals
More informationThe rheumatoid arthritis drug development model: a case study in Bayesian clinical trial simulation
The rheumatoid arthritis drug development model: a case study in Bayesian clinical trial simulation Richard Nixon, Modeling and Simulation, Novartis PSI journal club, 2010 March 24 1 Bayesian clinical
More informationFDA Drug Approval Process Vicki Seyfert-Margolis, Ph.D.
Speaker Comparing The Effectiveness Of New Drugs: Should The FDA Be Asking 'Does It Work' Or 'Does It Work Better'? Vicki L. Seyfert-Margolis, PhD Senior Advisor, Science Innovation and Policy U.S. Food
More informationSome key multiplicity questions on primary and secondary endpoints of RCCTs and possible answers
Some key multiplicity questions on primary and secondary endpoints of RCCTs and possible answers Mohammad F. Huque, Ph.D. Div of Biometrics IV, Office of Biostatistics OTS, CDER/FDA Basel Statistical Society,
More informationA Bayesian Design for Phase II Clinical Trials with Delayed Responses Based on Multiple Imputation
Research Article A Bayesian Design for Phase II Clinical Trials with Delayed Responses Based on Multiple Imputation Chunyan Cai a, Suyu Liu b and Ying Yuan b Interim monitoring is routinely conducted in
More informationData and Safety Monitoring Boards
Data and Safety Monitoring Boards Purposes, Roles and Challenges IACCT2017 Nov 29, 2017, Tel Aviv, Israel Arthur Weinstein, MD, FACP, FRCP, MACR Attending Rheumatologist Emeritus, MedStar Washington Hospital
More informationAlternative Trial Designs
Alternative Trial Designs STATS 773: DESIGN AND ANALYSIS OF CLINICAL TRIALS Dr Yannan Jiang Department of Statistics May 16 th 01, Wednesday, 08:30-10:00 Standard Design of RCT Individual subject is randomly
More informationAdaptive Dose Ranging Studies:
Adaptive Dose Ranging Studies: Flexible, Adaptive Dose-Finding Designs Frank Bretz and José Pinheiro Novartis Pharmaceuticals Tokyo University of Science, July 28, 2006 Outline Background and motivation
More informationNon-Inferiority Trials: What are they and why are they so difficult?
Non-Inferiority Trials: What are they and why are they so difficult? David J. Cohen, M.D., M.Sc. Director of Cardiovascular Research Saint-Luke Luke s s Mid America Heart Institute Professor of Medicine
More informationTECHNICAL WORKING PARTY ON AUTOMATION AND COMPUTER PROGRAMS. Twenty-Sixth Session Jeju, Republic of Korea, September 2 to 5, 2008
ORIGINAL: English DATE: August 21, 2008 INTERNATIONAL UNION FOR THE PROTECTION OF NEW VARIETIES OF PLANTS GENEVA E TECHNICAL WORKING PARTY ON AUTOMATION AND COMPUTER PROGRAMS Twenty-Sixth Session Jeju,
More informationCase studies in the design, analysis and interpretation of non-inferiority trials
Case studies in the design, analysis and interpretation of non-inferiority trials Krishan Singh, Ph.D. GlaxoSmithKline EFSPI Verona, Nov '08 1 Outline Introduction & Background Case Studies Altabax a topical
More informationPredictive Modelling of Recruitment and Drug Supply in Multicenter Clinical Trials
Biopharmaceutical Section JSM 009 Predictive Modelling of Recruitment and Drug Supply in Multicenter Clinical Trials Vladimir Anisimov Abstract Patient recruitment and drug supply planning are the biggest
More informationDecoding Phase II Clinical Trial Terminations
Decoding Phase II Clinical Trial Terminations Why Phase II trials are terminated and what can be done to improve Phase II success rates - the most critical inflection point for clinical development Subha
More informationChoosing an equivalence limit for noninferiority or equivalence studies
Controlled Clinical Trials 23 (2002) 2 14 Choosing an equivalence limit for noninferiority or equivalence studies Brian L. Wiens, Ph.D.* Department of Biostatistics, Amgen Inc., Manuscript received February
More informationEquipment and preparation required for one group (2-4 students) to complete the workshop
Your career today is a Pharmaceutical Statistician Leaders notes Do not give to the students Red text in italics denotes comments for leaders and example answers Equipment and preparation required for
More informationDynamic Probit models for panel data: A comparison of three methods of estimation
Dynamic Probit models for panel data: A comparison of three methods of estimation Alfonso Miranda Keele University and IZA (A.Miranda@econ.keele.ac.uk) 2007 UK Stata Users Group meeting September 10. In
More informationEnhancement of the Adaptive Signature Design (ASD) for Learning and Confirming in a Single Pivotal Trial
Enhancement of the Adaptive Signature Design (ASD) for Learning and Confirming in a Single Pivotal Trial Gu Mi, Ph.D. Global Statistical Sciences Eli Lilly and Company, Indianapolis, IN 46285 mi_gu@lilly.com
More informationInjectable modified release products
Guideline on the pharmacokinetic and clinical evaluation of modified release dosage forms (EMA/CPMP/EWP/280/96 Corr1) Injectable modified release products Dr Sotiris Michaleas, National Expert for the
More informationAdaptive Trials. Raphaël Porcher. CRESS, Inserm UMR-S 1153, Université Paris Descartes
Adaptive Trials Raphaël Porcher CRESS, Inserm UMR-S 1153, Université Paris Descartes Modélisation et simulation d essais cliniques Toulouse 9 10 avril 2015 R. Porcher (CRESS U1153) 1 / 69 Outline Outline
More informationData and safety monitoring boards of randomized trials: evolving principles and practical suggestions
Review: Clinical Trial Methodology Data and safety monitoring boards of randomized trials: evolving principles and practical suggestions Clin. Invest. (2011) 1(1), 53 57 Randomized trials designed a priori
More informationProject 2 - β-endorphin Levels as a Response to Stress: Statistical Power
Score: Name: Due Wednesday, April 10th in class. β-endorphins are neurotransmitters whose activity has been linked to the reduction of pain in the body. Elite runners often report a runners high during
More informationExperience with Adaptive Dose-Ranging Studies in Early Clinical Development
Experience with Adaptive Dose-Ranging Studies in Early Clinical Development Judith Quinlan MSc Vice President Adaptive Trials Cytel Inc. judith.quinlan@cytel.com Thanks to members of the PhRMA Adaptive
More informationPharmaSUG Paper SP03
PharmaSUG 2014 - Paper SP03 ABSTRACT Defining Non-Inferiority Margins for Skin Adhesion Studies Marina Komaroff, Noven Pharmaceuticals, New York, NY Sailaja Bhaskar, Noven Pharmaceuticals, New York, NY
More information13-5 The Kruskal-Wallis Test
13-5 The Kruskal-Wallis Test luman, hapter 13 1 1 13-5 The Kruskal-Wallis Test The NOV uses the F test to compare the means of three or more populations. The assumptions for the NOV test are that the populations
More informationCorrecting Sample Bias in Oversampled Logistic Modeling. Building Stable Models from Data with Very Low event Count
Correcting Sample Bias in Oversampled Logistic Modeling Building Stable Models from Data with Very Low event Count ABSTRACT In binary outcome regression models with very few bads or minority events, it
More informationDesign and inference in phase II/III clinical trials incorporating monitoring of multiple endpoints.
University of Louisville ThinkIR: The University of Louisville's Institutional Repository Electronic Theses and Dissertations 8-211 Design and inference in phase II/III clinical trials incorporating monitoring
More information1102-Microeconomics. I (6 Questions 12,5 points)
1102-Microeconomics First Mid-Term Fall 2012/2013 I (6 Questions 12,5 points) Toni has 200 available to spend in Tickets for Soccer Matches (S) and aviar (). His preferences can be represented by and the
More informationPharmaSUG 2017 Paper 47
PharmaSUG 2017 Paper 47 Visualization & interactive application in design and analysis by using R Shiny Baoyue LI, Eli Lilly & Company, Shanghai, China Boyao SHAN, Eli Lilly & Company, Shanghai, China
More informationThe Role of a Clinical Statistician in Drug Development By: Jackie Reisner
The Role of a Clinical Statistician in Drug Development By: Jackie Reisner Types of studies within clinical development Phase I Phase II Phase III Phase IV Phase I First Human Dose (FHD) Young healthy
More informationBargaining in technology markets: An empirical study of biotechnology alliances
Bargaining in technology markets: An empirical study of biotechnology alliances Shinya Kinukawa Komazawa University Kazuyuki Motohashi University of Tokyo September 7, 2009 Abstract The division of innovative
More informationSWOG ONCOLOGY RESEARCH PROFESSIONAL (ORP) MANUAL STUDY PROTOCOL CHAPTER 14 REVISED: OCTOBER 2015
THE STUDY PROTOCOL The study protocol is a written document detailing how a clinical trial is conducted. The elements of a protocol include: 1. Trial design and organization; 2. Study objectives; 3. Background
More informationA study of cartel stability: the Joint Executive Committee, Paper by: Robert H. Porter
A study of cartel stability: the Joint Executive Committee, 1880-1886 Paper by: Robert H. Porter Joint Executive Committee Cartels can increase profits by restricting output from competitive levels. However,
More informationReinforced Concrete Tilt-Up Wall Panel Analysis and Design (ACI 551)
Reinforced Concrete Tilt-Up Wall Panel Analysis and Design (ACI 551) Reinforced Concrete Tilt-Up Wall Panel Analysis and Design (ACI 551) Tilt-up is form of construction with increasing popularity owing
More informationEnd-to-End Management of Clinical Trials Data
End-to-End Management of Clinical Trials Data A Revolutionary Step Toward Supporting Clinical Trials Analysis Over the Next Decades of Clinical Research WHITE PAPER SAS White Paper Table of Contents Introduction....
More informationThree Methods for Phase I/II Clinical Trials, with Application to Allogeneic
Three Methods for Phase I/II Clinical Trials, with Application to Allogeneic Stem Cell Transplantation Peter F. Thall, PhD Biostatistics Department M.D. Anderson Cancer Center Workshop on Clinical Trial
More informationRegulatory Requirements
Regulatory Requirements CTTI Quality by Design Workshop 28-29 Jan 2013 Rockville, MD Fergus Sweeney, Head, Compliance and Inspections, European Medicines Agency An agency of the European Union Disclaimer
More informationThe Collaborative and Methodologic Research
The Collaborative and Methodologic Research of Dr. Stewart Anderson Associate Professor of Biostatistics University of Pittsburgh Graduate School of Public Health 18 February 2005 Dissertation Problems
More informationWINDOWS, MINITAB, AND INFERENCE
DEPARTMENT OF POLITICAL SCIENCE AND INTERNATIONAL RELATIONS Posc/Uapp 816 WINDOWS, MINITAB, AND INFERENCE I. AGENDA: A. An example with a simple (but) real data set to illustrate 1. Windows 2. The importance
More informationPrecast Concrete Bearing Wall Panel Design (Alternative Analysis Method) (Using ACI )
Precast Concrete Bearing Wall Panel Design (Alternative Analysis ethod) (Using ACI 318-14) Precast Concrete Bearing Wall Panel Design (Alternative Analysis ethod) (Using ACI 318-14) A structural precast
More informationFDA S DRAFT GUIDANCE ON MULTIPLE ENDPOINTS IN CLINICAL TRIALS: OVERVIEW, RECEPTION AND NEXT STEPS. John Scott, Ph.D. FDA/CBER 5 October 2017
FDA S DRAFT GUIDANCE ON MULTIPLE ENDPOINTS IN CLINICAL TRIALS: OVERVIEW, RECEPTION AND NEXT STEPS John Scott, Ph.D. FDA/CBER 5 October 2017 Disclaimer 2 This presentation reflects the views of the author
More informationStatistical Evaluation Of Stability Data
Reprinted from FDA s website by #219 GUIDANCE FOR INDUSTRY Statistical Evaluation Of Stability Data VICH GL51 DRAFT GUIDANCE This guidance document is being distributed for comment purposes only Submit
More informationLECTURE 13 THE NEOCLASSICAL OR WALRASIAN EQUILIBRIUM INTRODUCTION
LECTURE 13 THE NEOCLASSICAL OR WALRASIAN EQUILIBRIUM INTRODUCTION JACOB T. SCHWARTZ EDITED BY KENNETH R. DRIESSEL Abstract. Our model is like that of Arrow and Debreu, but with linear Leontief-like features,
More informationDoes Working for a Better Boss Improve Ratings of Subordinate Performance? A Longitudinal, Quasi-Experimental Study
Does Working for a Better Boss Improve Ratings of Subordinate Performance? A Longitudinal, Quasi-Experimental Study Stephanie Sloan The Home Depot North Carolina State University Robert B. Kaiser Kaplan
More informationDesigning a Disease-Specific Master Protocol
Designing a Disease-Specific Master Protocol Lisa M. LaVange, PhD Director, Office of Biostatistics OTS/CDER/FDA Pediatric Master Protocols Workshop September 23, 2016 FDA, White Oak Campus Acknowledgments
More information8. Clinical Trial Assessment Phase II
8. Clinical Trial Assessment Phase II Junko Sato, PhD Office of New Drug I, PMDA Disclaimer: The information within this presentation is based on the presenter s expertise and experience, and represents
More informationOnline Model Evaluation in a Large-Scale Computational Advertising Platform
Online Model Evaluation in a Large-Scale Computational Advertising Platform Shahriar Shariat Turn Inc. Redwood City, CA Email: sshariat@turn.com Burkay Orten Turn Inc. Redwood City, CA Email: borten@turn.com
More informationIntegrating Aggregate-Data and Individual-Patient-Data in Meta-Analysis: An Empirical Assessment and an Alternative Method for the Two-Stage Approach
Modern Applied Science; Vol. 9, No. 13; 2015 ISSN 1913-1844 E-ISSN 1913-1852 Published by Canadian Center of Science and Education Integrating Aggregate-Data and Individual-Patient-Data in Meta-Analysis:
More informationData Quality and Integrity: From Clinical Monitoring to Marketing Approval
Data Quality and Integrity: From Clinical Monitoring to Marketing Approval Nancy Detich, Ph.D., C.C.R.P. Senior Scientist, Clinical Strategy 18 November 2010 1 Objectives Identify the importance of accuracy,
More informationRational Approach in Applying Reliability Theory to Pavement Structural Design
TRANSPORTATION RESEARCH RECORD 1449 13 Rational Approach in Applying Reliability Theory to Pavement Structural Design RAM B. KULKARNI A rigorous yet practical methodology for evaluating pavement design
More informationGUIDELINES ON MEDICAL DEVICES
EUROPEAN COMMISSION DIRECTORATE GENERAL for HEALTH and CONSUMERS Consumer Affairs Cosmetics and Medical Devices MEDDEV 2.7/4 December 2010 GUIDELINES ON MEDICAL DEVICES GUIDELINES ON CLINICAL INVESTIGATION:
More informationEVALUATION FOR STABILITY DATA
INTERNATIONAL CONFERENCE ON HARMONISATION OF TECHNICAL REQUIREMENTS FOR REGISTRATION OF PHARMACEUTICALS FOR HUMAN USE ICH HARMONISED TRIPARTITE GUIDELINE EVALUATION FOR STABILITY DATA Q1E Recommended for
More informationSecure Interim Analysis Data Access. Management with ACES. Eric J. Silva, Cytel, Inc. Steven Ketchum, Ph.D., Sunesis Pharmaceuticals
Secure Interim Analysis Data Access and Automated DMC/DSMB Management with ACES Eric J. Silva, Cytel, Inc. Steven Ketchum, Ph.D., Sunesis Pharmaceuticals Introductions: Today s Speakers Eric J. Silva Manager,
More informationResponse Modeling Marketing Engineering Technical Note 1
Response Modeling Marketing Engineering Technical Note 1 Table of Contents Introduction Some Simple Market Response Models Linear model Power series model Fractional root model Semilog model Exponential
More informationA SIMULATION STUDY OF THE ROBUSTNESS OF THE LEAST MEDIAN OF SQUARES ESTIMATOR OF SLOPE IN A REGRESSION THROUGH THE ORIGIN MODEL
A SIMULATION STUDY OF THE ROBUSTNESS OF THE LEAST MEDIAN OF SQUARES ESTIMATOR OF SLOPE IN A REGRESSION THROUGH THE ORIGIN MODEL by THILANKA DILRUWANI PARANAGAMA B.Sc., University of Colombo, Sri Lanka,
More informationJMP JMP Pro JMP Genomics JMP Clinical JMP Add-Ins
JMP FAMILY OF PRODUCTS: SOFTWARE FOR LIFE SCIENTISTS JMP JMP Pro JMP Genomics JMP Clinical JMP Add-Ins CLINICAL TRIAL DATA REVIEWS Randomized clinical trial remains the gold standard for evaluating efficacy
More informationSECTION 11 ACUTE TOXICITY DATA ANALYSIS
SECTION 11 ACUTE TOXICITY DATA ANALYSIS 11.1 INTRODUCTION 11.1.1 The objective of acute toxicity tests with effluents and receiving waters is to identify discharges of toxic effluents in acutely toxic
More informationSubmitted on 23/12/2014 Article ID: Stella Ma, Elizabeth A. Stasny, James A. Tackett, and Douglas A. Wolfe
Journal of Contemporary Management Submitted on 3//04 Article ID: 99-08-05-0-0-7 Stella Ma, Elizabeth A. Stasny, James A. Tacett, and Douglas A. Wolfe Confidence Intervals and Hypothesis Tests for a Population
More information155S9.4_3 Inferences from Dependent Samples. April 11, Key Concept. Chapter 9 Inferences from Two Samples. Key Concept
MAT 155 Statistical Analysis Dr. Claude Moore Cape Fear Community College Chapter 9 Inferences from Two Samples 9 1 Review and Preview 9 2 Inferences About Two Proportions 9 3 Inferences About Two Means:
More information( ) + ( γh pω h + θ h π px h
Handout 3 Externality Theory And Policy (starting directly from Handout 1) A. Introduce an unpriced good; call it z. z is net production of z by firm z h is consumption of z by household h. B. Supply/demand
More informationInternational Transfers of Personal Data at sanofi-aventis R & D
International Transfers of Personal Data at sanofi-aventis R & D Pierre-Yves Lastic, PhD Senior Director, Standards Management & Data Privacy Sanofi-aventis R&D CONFERENCE ON INTERNATIONAL TRANSFERS OF
More informationLOW R&D EFFICIENCY IN LARGE PHARMACEUTICAL COMPANIES
American Journal of Medical Research 3(2), 2016 pp. 141 151, ISSN 2334-4814, eissn 2376-4481 LOW R&D EFFICIENCY IN LARGE PHARMACEUTICAL COMPANIES ERIK STRØJER MADSEN Ema@econ.au.dk Department of Economics
More informationUtilizing Innovative Statistical Methods. Discussion Guide
Utilizing Innovative Statistical Methods and Trial Designs in Rare Disease Settings Discussion Guide Background Rare diseases are a complex and diverse set of conditions which, when taken together, affect
More informationAnalysis of Clinical Trials with Multiple Objectives
Analysis of Clinical Trials with Multiple Objectives Alex Dmitrienko (Mediana Inc) Regulatory Industry Statistics Workshop September 2017 Outline Regulatory guidelines FDA and EMA draft guidance documents
More informationEstablishing Case Quality Metrics The Sciformix experience
Whitepaper Establishing Case Quality Metrics The Sciformix experience Introduction Measurement of case quality in pharmacovigilance is a relatively new development. Before pharmaceutical companies began
More informationPrinciples of Verification, Validation, Quality Assurance, and Certification of M&S Applications
Introduction to Modeling and Simulation Principles of Verification, Validation, Quality Assurance, and Certification of M&S Applications OSMAN BALCI Professor Copyright Osman Balci Department of Computer
More informationDRUG DEVELOPMENT TARGET PRODUCT PROFILE
DRUG DEVELOPMENT TARGET PRODUCT PROFILE Template This template provides suggested considerations that may assist biopharmaceutical companies in their decisions as to whether to proceed with a drug development
More informationContents. Research target and questions
Deregulation, Prices and Search Costs in the Italian OtC Retail Market Leopoldo Trieste Sant Anna School of Advanced Studies l.trieste@sssup.it Volterra, June 9th 2008 Research target and questions Contents
More informationChapter 10: Phase Diagrams
hapter 10: Phase Diagrams Show figures 10-1 and 10-3, and discuss the difference between a component and a phase. A component is a distinct chemical entity, such as u, Ni, NiO or MgO. A phase is a chemically
More informationBasic Opamp Design and Compensation. Transistor Model Summary
Basic Opamp Design and Compensation David Johns and Ken Martin (johns@eecg.toronto.edu) (martin@eecg.toronto.edu) slide of 37 General Constants Transistor charge Boltzman constant Transistor Model Summary
More informationArchives of Scientific Psychology Reporting Questionnaire for Manuscripts Describing Primary Data Collections
(Based on APA Journal Article Reporting Standards JARS Questionnaire) 1 Archives of Scientific Psychology Reporting Questionnaire for Manuscripts Describing Primary Data Collections JARS: ALL: These questions
More informationOfficial Letter from the DOH
Issued Date 2009/04/02 Issued by DOH Ref. No 0980316268 RE The DOH issued an official letter to announce the implementation of the Guideline for BA/BE Studies on April 2, 2009 (Ref. No. 0980316265). Please
More informationOne-way optional crossover: biases and analysis approaches. Leen Slaets Jan Bogaerts EORTC
One-way optional crossover: biases and analysis approaches Leen Slaets Jan Bogaerts EORTC Overview The issue A famous example Framework, analysis methods, parameters at play A simulation study Concluding
More informationCompetitive Analysis of Incentive Compatible On-line Auctions
Competitive Analysis of Incentive Compatible On-line Auctions Ron Lavi and Noam Nisan Theoretical Computer Science, 310 (2004) 159-180 Presented by Xi LI Apr 2006 COMP670O HKUST Outline The On-line Auction
More informationCrowe Critical Appraisal Tool (CCAT) User Guide
Crowe Critical Appraisal Tool (CCAT) User Guide Version 1.4 (19 November 2013) Use with the CCAT Form version 1.4 only Michael Crowe, PhD michael.crowe@my.jcu.edu.au This work is licensed under the Creative
More informationLONG RUN AGGREGATE SUPPLY
The Digital Economist Lecture 8 -- Aggregate Supply and Price Level Determination LONG RUN AGGREGATE SUPPLY Aggregate Supply represents the ability of an economy to produce goods and services. In the Long
More informationGuidance for Industry and FDA Staff Procedures for Handling Post-Approval Studies Imposed by PMA Order
Guidance for Industry and FDA Staff Procedures for Handling Post-Approval Studies Imposed by PMA Order Document issued on: [Level 2, June 15, 2009] This guidance supersedes the document issued under this
More informationMODELING AND SIMULATION OF A LEAN SYSTEM. CASE STUDY OF A PAINT LINE IN A FURNITURE COMPANY
MODELING AND SIMULATION OF A LEAN SYSTEM. CASE STUDY OF A PAINT LINE IN A FURNITURE COMPANY Quynh-Lam Ngoc LE 1, Ngoc-Hien DO 2, Ki-Chan NAM 3 1 Ho Chi Minh City University of Technology, 268 Ly Thuong
More informationThe Kruskal-Wallis Test with Excel In 3 Simple Steps. Kilem L. Gwet, Ph.D.
The Kruskal-Wallis Test with Excel 2007 In 3 Simple Steps Kilem L. Gwet, Ph.D. Copyright c 2011 by Kilem Li Gwet, Ph.D. All rights reserved. Published by Advanced Analytics, LLC A single copy of this document
More informationPharmabiotics: a Regulatory Hurdle in Europe
Pharmabiotics: a Regulatory Hurdle in Europe Dr. Magali Cordaillat-Simmons PRI Executive Scientist Raleigh, NC, USA September 8th, 2014 PHARMABIOTICS: A REGULATORY HURDLE IN EUROPE I. Introduction to Pharmabiotics
More information