Agenda » Learning objectives
Course learning objectives
Basic course
The objective of this course is to introduce students to the logic of a basic meta-analysis and teach them how to perform a meta-analysis, critique a meta-analysis, and avoid common mistakes in meta-analysis. By the end of the course students will understand
- The goals of a meta-analysis
- How to choose a statistical model
- How to choose an effect-size index
- How to enter data for a simple meta-analysis
- How to estimate the mean effect size
- How to quantify and understand heterogeneity in effects
- How to report the results of the analysis
- How to create forest plots
- How to create plots that show the distribution of true effects
- How to avoid common mistakes in all these areas
Advanced course
The objective of this course is to teach students advanced issues in meta-analysis. By the end of the course the student will understand
- How to use subgroup analyses to compare the impact of a treatment in sets of studies that enrolled different populations or employed different variants of an intervention (analogous to ANOVA in a primary study)
- How to use meta-regression to assess the unique impact of continuous or categorical covariates on the effect size (analogous to multiple-regression in a primary study)
- How to assess the potential impact of publication bias on the analysis
- What to do when there are only a small number of studies in the analysis
- How to avoid common mistakes in all these areas
Testimonials
"This is an excellent course, well presented, step-by-step and easy to follow. Great to have all the case studies in paper and soft copy. Michael is extremely knowledgeable and an excellent teacher. I liked the stories, real life examples and openness to answer questions. He was able to make a dry topic very interesting. Also appreciated a grounded clinical perspective of what meta-analysis results infer."
Sharon Carey - Royal Prince Alfred Hospital - Sydney 2020
"The meta-analysis seminar was extremely clear, informative, and helpful. We were especially pleased that it was at an appropriate level for the faculty and researchers who were from various areas of specialization in health and medical sciences at our University of Medicine and Dentistry of New Jersey. Thank you."
Syed S. Haque, PhD - Professor and Chairman, Department of Health Informatics, Director of Graduate Programs in Biomedical Informatics