Meta-analysis: Learn It, Teach It, See the Elephant
In the parable of the blind men and the elephant, each felt only a bit of the elephant and argued over which perception was correct.
In science we sometimes get lots of views of a phenomenon through small studies and observations. Sometimes these are inconclusive and sometimes they are contradictory. Meta-analysis is an analytical means by which we can sort through reports and attempt to combine the information to get at the big picture -- a clear, in-focus, view of that elephant.
Systematic reviews and meta-analyses are common reading for any clinical staff or faculty member looking for an "evidence-based" practice, so it's not uncommon for statisticians in health sciences to get a request to teach, review, or conduct a meta-analysis.
In a short-course and round-table combo, TSHS is bringing professional development and teacher training on meta-analysis to JSM 2018. Read on for details. Then be sure to scroll to the bottom to leave your favorite meta-analysis teaching example or activity in the comments.
CONTINUING EDUCATION COURSE
What: "Meta-analysis for Biopharmaceutical and Public Health Research Using SAS"*
When: Mon, 7/30/2018, 8:00 AM - 12:00 PM
Where: JSM 2018, Vancouver; CC-East 2/3
Fee: $270
Instructor(s): Michael LaValley, Boston University School of Public Health, Ludovic Trinquart, Boston University School of Public Health
Who is the target audience?
The target audience includes biostatisticians, data analysts, and quantitative researchers from academia, the pharmaceutical industry, the FDA and other government institutions with a basic knowledge of study design and regression modeling.
What benefit will TSHS members will gain from this event? Instructors who teach meta-analysis topics could gain more insight from this short course. Additionally, this is a nice introduction for health science researchers who are interested conducting meta analyses.
Abstract: Meta-analysis is the gold standard statistical approach to combine the results of multiple studies and to examine sources of heterogeneity and potential biases. This course will review fixed-effect and random-effects models, including the newly-recommended approaches, that underlie the combination of study results in meta-analysis; the use of study-level predictors in meta-regression; novel limit meta-analysis models to adjust for small-study effects and related reporting biases; and the synthesis of individual participant data. Throughout the course, participants will apply each model by using the SAS/STAT software and produce high-quality graphs, with original macros developed by the instructors. The target audience includes biostatisticians, data analysts, and quantitative researchers from academia, the pharmaceutical industry, the FDA and other government institutions with a basic knowledge of study design and regression modeling.
* Co-sponsored with the Biopharmaceutical Section
ROUND-TABLE DISCUSSION
What: "Teaching Meta-analysis for Health Scientists"
When: Tuesday, July 31, 2018 : 7:00 AM to 8:15 AM
Where: JSM 2018, Vancouver; CC-West Ballroom D
Fee: $25
Discussion Lead: Laila Poisson
Who is the target audience?
TSHS members or friends who do or want to teach meta analysis to their clinical learners
What benefit will TSHS members will gain from this event?
Practical ideas for introducing meta analysis to a clinical audience
Discussion of breadth and depth of material
Activities, articles, etc that might be helpful.
Abstract: Meta-analysis is a common technique used in medical literature, but it is not generally a topic covered in basic statistics courses. Clinicians are motivated to learn about meta-analysis either as consumers of, or collaborators in the generation of, topical reviews. As a follow-up to the continuing education session** on "Meta-analysis for biopharmaceutical and public health research using SAS," this round-table discussion will look at resources for teaching meta-analysis to health scientists. From formal seminars to in-the-moment opportunities, let's discuss best practices and brainstorm new ideas for conveying the concepts, assumptions and limitations of meta-analysis.
**Attendance at the CE event is not required for participation in this round-table.