Our new website is now live at https://t.co/n1Cc1Jlu9m! 💥 This hub facilitates discussions on Bayesian Meta-Analysis. We're integrating codes from our book and methodological resources over the summer, structured as an interactive blog where practitioners can engage.

In summary, this chapter reviews the foundations of statistical inference, preparing the reader for the modelling concepts central to Bayesian meta-analysis by framing inference as a process that relies on probability models, not merely on weighted averages.

• 𝗕𝗲𝘆𝗼𝗻𝗱 𝘁𝗵𝗲 𝗻𝘂𝗺𝗯𝗲𝗿𝘀. Considerations like intention-to-treat vs per-protocol analysis (we’ll soon add on the strategies as defined in the ICH E9(R1) addendum on estimands), and cautions about extrapolating to populations not represented in the studies.

across hypothetical replications (standard error). • 𝗜𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝗳𝗼𝗿 𝗰𝗼𝗻𝘁𝗶𝗻𝘂𝗼𝘂𝘀 𝗮𝗻𝗱 𝗯𝗶𝗻𝗮𝗿𝘆 𝗱𝗮𝘁𝗮. From estimating a mean with the t-distribution to comparing groups, odds, odds ratios, and the logit.

Key concepts include: • 𝗧𝗵𝗲 𝗻𝗮𝘁𝘂𝗿𝗲 𝗼𝗳 𝗶𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲. What it means to generalise beyond the data at hand. • 𝗗𝗮𝘁𝗮 𝘃𝘀. 𝘀𝗮𝗺𝗽𝗹𝗶𝗻𝗴 𝗱𝗶𝘀𝘁𝗿𝗶𝗯𝘂𝘁𝗶𝗼𝗻𝘀. Why the spread of measurements (standard deviation) differs from the spread of statistics

We revisit the key principles, terminology, and notation that underpin later chapters on Bayesian meta-analysis, making the material accessible even if you haven’t studied statistics in a while.

𝗖𝗵𝗮𝗽𝘁𝗲𝗿 𝟭 – 𝗔 𝗦𝘁𝗮𝘁𝗶𝘀𝘁𝗶𝗰𝗮𝗹 𝗜𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝗣𝗿𝗶𝗺𝗲𝗿 How do we move from raw data to meaningful conclusions? That’s the essence of statistical inference, and the foundation we lay in the opening chapter of our book.

Starting this week, we’ll be sharing a chapter-by-chapter introduction to our book, “𝗕𝗮𝘆𝗲𝘀𝗶𝗮𝗻 𝗠𝗲𝘁𝗮-𝗔𝗻𝗮𝗹𝘆𝘀𝗶𝘀: 𝗔 𝗣𝗿𝗮𝗰𝘁𝗶𝗰𝗮𝗹 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻”, available here:

Call for paper on Methods for Systematic Reviews of Health Economic Evaluations, PharmacoEconomics https://t.co/Dme4tTGiGZ #healtheconomics

We launched a call for papers in @ph_economics on methods for Systematic Reviews of health economics evaluations

Please reach out to with suggestions for content (papers incl. preprints, webinars, events, blog posts) that would benefit our growing community!

We finally extended robust Bayesian meta-analysis to multilevel settings. Now, you can fit 3-level publication bias-adjusted model-averaged meta-regression models in R (and in about a week in JASP too!)

Any #Cluster Randomised #Trial in your Meta-Analysis? I am pleased to share our latest paper in BMC Med Res Met "Warnings on the inclusion of cluster randomized trials (CRTs) in meta-analysis: results of a simulation study" https://t.co/iZYCzBAUfj

We have tried to show its implementation across various computational frameworks including: BUGS JAGS Stan Stata JASP R packages such as bayesmeta and brms Beginning this week, I'll be sharing weekly insights from specific chapters

This book addresses a critical methodological gap in the evidence synthesis landscape, offering a systematic approach to Bayesian meta-analytic techniques accessible to researchers across disciplines.

I'm delighted to present the cover of the book Robert Grant and I wrote titled "Bayesian Meta-Analysis: A Practical Introduction" which will be released by CRC Press in June 2025!

I've been really enjoying the Past, Present, Future series on revolutions, and then I was asked to be in one myself! So here I am discussing the Bayesian revolution - 250 years old and still going strong

This series on risk by Lucy Easthope seems rather good (and not just because I feature). Recommended listening

We learn more from reading on paper than on screens. 54 studies, 171k people: we process print more deeply than digital content—as long as it's informational rather than purely narrative. The paper advantage holds across ages and has grown over time. Long live physical books.

Results of our GMRx2 trial has been published today in @TheLancet ! We showed how a novel low-dose triple single-pill combination led to clinically meaningful blood pressure reductions compared to dual combinations and was well tolerated. https://t.co/8Y0E0ji83Q