Clinical Trials - Cluster

Resize the browser window to see the effect.




Sample Size and Power-Analysis for Cluster-Randomized and

Multi-Site Studies

taught by Michael Borenstein

Aim of Course:

This online course, "Sample Size and Power-Analysis for Cluster-Randomized and Multi-Site Studies" covers the methods for calculating power and sample size for cluster-randomized studies, and for determining optimal study designs.

Typical methods and software for calculating power and sample size are for simple random sampling designs.  Many study designs, though, are multi-level (clustered) -- select a school/classroom/student, or a region/hospital/patient, terrain/region/core sample, etc.  How do you calculate sample size and power for a multi-level study?

More importantly, how do you design a cost-effective study?  In simple randomized studies the only sample size we can manipulate is the number of subjects.  In a multi-level study, we can select the number of schools, classes, etc.  Different combinations might yield similar power, but some might cost two or three times as much as others.

This course covers the methods needed to determine sample size (given specified power) for multi-level trials, and also how to arrive at an optimal design.

Please note: For the most part, the software used in this class is, as of Sep 2012, the only program that can compute power for three-level and four-level designs. Therefore, a large part of the class will be dedicated to this software. Software is supplied to registered students for the duration of the course. In order to apply the knowledge acquired in this course after it is over, you will need to obtain or have available a regular commercial copy of the program.

Course Program:

 WEEK 1: Cluster Randomized Studies and Power Analysis

  • Basic issues in power analysis
  • How cluster-randomized studies pose unique problems for power analysis

WEEK 2: Hierarchical Designs in Cluster Randomized Studies

  • Hierarchical designs (HD) two level, three level, four level
  • Understanding the ICC, and how to specify it in the analysis
  • Working with means and with proportions in HD designs
  • Finding the most cost-effective ratio of subjects to clusters

WEEK 3: Randomized Block Designs in Cluster Randomized Studies

  • Randomized block designs (RB) two level, three level, four level
  • Understanding Tau-squared, and how to specify it in the analysis
  • Working with means and with proportions in RB designs
  • Finding the most cost-effective ratio of subjects to clusters

WEEK 4:Interpreting Output

  • Finding the minimum detectable effect size
  • Creating graphs showing power and cost as a function of design factors
  • Creating reports detailing assumptions and computations


HOMEWORK:

Homework in this course consists of guided data analysis problems using software and guided data modeling problems using software.

In addition to assigned readings, this course also has an end of course data modeling project.


Sample Size and Power-Analysis for Cluster-Randomized and Multi-Site Studies

Who Should Take This Course:

Researchers involved in the planning design, implementation, management or analsis of cluster-randomized clinical trials.

Level:

intermediate/advanced


Organization of the Course:

This course takes place online at the Institute for 4 weeks. During each course week, you participate at times of your own choosing - there are no set times when you must be online. Course participants will be given access to a private discussion board. In class discussions led by the instructor, you can post questions, seek clarification, and interact with your fellow students and the instructor.

At the beginning of each week, you receive the relevant material, in addition to answers to exercises from the previous session. During the week, you are expected to go over the course materials, work through exercises, and submit answers. Discussion among participants is encouraged. The instructor will provide answers and comments, and at the end of the week, you will receive individual feedback on your homework answers.

Time Requirement:
About 15 hours per week, at times of  your choosing.

Credit:
Students come to the Institute for a variety of reasons. As you begin the course, you will be asked to specify your category:

  1. You may be interested only in learning the material presented, and not be concerned with grades or a record of completion.
  2. You may be enrolled in PASS (Programs in Analytics and Statistical Studies) that requires demonstration of proficiency in the subject, in which case your work will be assessed for a grade.
  3. You may require a "Record of Course Completion," along with professional development credit in the form of Continuing Education Units (CEU's).  For those successfully completing the course,  CEU's and a record of course completion will be issued by The Institute, upon request.


Course Text:

All required materials will be provided in the course. The course will be taught by Michael Borenstein, the co-developer (with Larry Hedges) of CRT Power, a computer program to compute power for cluster-randomized trials.

Software:

Participants will have free access to the software CRT Power for the duration of the course, and will learn how to use this program to conduct advanced analyses.

Please note: For the most part, the software used in this class is, as of Sep 2012, the only program that can compute power for three-level and four-level designs. Therefore, a large part of the class will be dedicated to this software. Software is supplied to registered students for the duration of the course. In order to apply the knowledge acquired in this course after it is over, you will need to obtain or have available a regular commercial copy of the program.


Sample Size and Power-Analysis for Cluster-Randomized and Multi-Site Studies

Instructor(s):
Dates:
To be scheduled

Course Fee: $589