Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Optimal sample size determination in adaptive seamless phase II/III design

Xu, Zhongying (2016) Optimal sample size determination in adaptive seamless phase II/III design. Master's Thesis, University of Pittsburgh. (Unpublished)

[img]
Preview
PDF
Submitted Version

Download (300kB)

Abstract

The adaptive seamless phase II/III design combines the conventional separate phases II and III trials into a single trial, and it allows for adaptations (e.g. sample size reassessment and early stopping for futility or success) after the interim analysis. In this study, we propose a simulation-based method to determine the optimal sample size for the adaptive seamless phase II/III design. We assume that a power law relationship exists between the overall sample size and statistical power of the final test. The optimal sample size is defined as the minimum sample size that provides adequate power with overall type I error rate under control. To find the optimal size, we also take correlations between the early and the final outcomes into consideration. The methodology is applied to determining sample sizes in a study for a candidate treatment that can avoid renal damage during cardiac operations while the most effective dose of the treatment will be selected at the interim analysis.

PUBLIC HEALTH SIGNIFICANCE
Adaptive seamless phase II/III design eliminates the time between the traditional separate trials and better utilizes the data collected before the interim analysis, thus will result in faster clinical trials. Treatment effect can be confirmed at the final test if adequate power is achieved and the overall type I error rate is under control. Using these faster clinical trials, effective treatment can be approved sooner to benefit more patients. In addition, in an adaptive seamless phase II/III design more patients will be allocated to the more effective treatment than they would in conventional clinical trials.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Xu, Zhongyingzhx17@pitt.eduZHX17
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Thesis AdvisorChang, Chung-Chou H.changj@pitt.eduCHANGJ
Committee CoChairMarsh, Gary M.gmarsh@pitt.eduGMARSH
Committee MemberKellum, John A.kellumja@upmc.edu
Date: 29 June 2016
Date Type: Publication
Defense Date: 13 April 2016
Approval Date: 29 June 2016
Submission Date: 31 March 2016
Access Restriction: 2 year -- Restrict access to University of Pittsburgh for a period of 2 years.
Number of Pages: 36
Institution: University of Pittsburgh
Schools and Programs: Graduate School of Public Health > Biostatistics
Degree: MS - Master of Science
Thesis Type: Master's Thesis
Refereed: Yes
Uncontrolled Keywords: adaptive seamless design; closed testing principle; combination test; sample size determination; treatment selection
Date Deposited: 29 Jun 2016 20:48
Last Modified: 01 May 2018 05:15
URI: http://d-scholarship.pitt.edu/id/eprint/27481

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item