Issue 3 January 2025 newsletter

Welcome to the third newsletter for the Cochrane Statistical Methods Group

Issue 3 January 2025

Convenors

We have recently had a change of convenors and we sadly say goodbye to Catrin Tudur Smith. We are very grateful to Catrin for her contributions to the work of the SMG over the past decade.

RevMan updates

In September 2022, Cochrane endorsed the implementation of new statistical methods for random-effects meta-analysis. These methods have now been finalized, and the updated version of RevMan was released on January 23, 2025. In addition to the previously available implementations, the new RevMan version introduces the following features:

  • the Hartung-Knapp-Sidik-Jonkman (HKSJ) method for calculating the confidence interval of the summary effect.

  • the restricted maximum likelihood (REML) method (default option) for estimating the heterogeneity parameter.

  • the Q-profile method for calculating the confidence interval of the heterogeneity estimate. 

  • calculation of the I-square statistic using a new formula based on the heterogeneity estimate. 

  • methods for calculating prediction intervals.

Updates in Cochrane Handbook’s Chapter 10

The 2024 update of the Cochrane Intervention Handbook provides detailed guidance on the newly available random-effects meta-analysis options in RevMan and includes updates to several existing recommendations (see Chapter 10 [1]). Briefly, compared to previous versions of Chapter 10, the updated chapter now recommends:

  • using the REML method as the default option for estimating heterogeneity (see section 10.10.4.4).

  • using the HKSJ method based on the t-distribution (with k-1 degrees of freedom) when the heterogeneity estimate is greater than 0 and the number of study results is greater than 2 (see section 10.10.4.4).

  • calculating a confidence interval for the heterogeneity parameter estimate using the Q-profile method (see section 10.10.4.4), when there are sufficient studies to do so.

  • a new formula for calculating the I-square statistic based on the heterogeneity estimate used (see section 10.10.4.4).

  • calculating prediction intervals based on the t-distribution with k-1 degrees of freedom, rather than k-2 as previously recommended. This recommendation is also implemented in RevMan. (see section 10.10.4.3).

For more details, we refer to the updated Chapter 10 of the Cochrane Intervention Handbook [1].

  1. Deeks JJ, Higgins JPT, Altman DG, McKenzie JE, Veroniki AA (editors). Chapter 10: Chapter 10: Analysing data and undertaking meta-analyses [last updated November 2024]. In: Higgins JPT, Thomas J, Chandler J, Cumpston M, Li T, Page MJ, Welch VA (editors). Cochrane Handbook for Systematic Reviews of Interventions version 6.5. Cochrane, 2024. Available from www.training.cochrane.org/handbook.

SMG participation in GES

The 2nd Global Evidence Summit (GES) took place from the 10th to the 13th of September 2024 in Prague, Czech Republic. The convenors of SMG contributed to GES by in both workshops and oral presentations:

  • Jo Mckenzie and Lizzie Korevaar presented a workshop titled "Introduction to analysis and meta-analysis of interrupted time series studies with continuous outcomes”.

  • Jo McKenzie co-facilitated a workshop titled “Introducing the PRISMA 2020 adherence assessment form: a standardized approach for assessing completeness of reporting of systematic reviews”.

  • Theodoros Evrenoglou presented a workshop titled "Advanced Meta-Analysis 2: Performing Meta-Analysis in the Presence of rare events".

  • Lizzie Korevaar delivered an oral presentation titled "Checklist to help peer reviewers detect errors in meta-analyses in systematic reviews of interventions: results from the development process”. 

  • Areti Angeliki Veroniki delivered an oral contribution with title “Update of PRISMA guidelines for network meta-analyses”.

In addition, the SMG convenors participated as co-authors in several other GES contributions. The full abstract book is available here.

Publications

  • McKenzie JE, Veroniki AA. A brief note on the random-effects meta-analysis model and its relationship to other models. J Clin Epidemiol. 2024 Aug 2;174:111492

  • Veroniki AA, McKenzie JE. A brief note on the common (fixed)-effect meta-analysis model. J Clin Epidemiol. 2024 May; 169:111281.

  • Simmonds M, Chaimani A, McKenzie J, Tudur-Smith C, Veroniki AA, Cochrane Statistical Methods Group co-convenors. A method was developed for correcting the bias in the usual study weights in meta-analyses: comment on Walter and Balakrishnan. J Clin Epidemiol. 2024 Jul;171:111357
  • Veroniki AA, Florez I, Hutton B, Straus SE, Tricco AC. Two decades of network meta-analysis: Roadmap to their applications and challenges. Res Synth Methods. 2024 Jul 31
  • Florez ID, De La Cruz-Mena JE, Veroniki AA. Network meta-analysis: a powerful tool for clinicians, decision-makers, and methodologists. J Clin Epidemiol. 2024 Sep 20;176:111537.
  • Lunny C, Veroniki AA, Higgins JPT, Dias S, Hutton B, Wright JM, White IR, Whiting P, Tricco AC. Methodological review of NMA bias concepts provides groundwork for the development of a list of concepts for potential inclusion in a new risk of bias tool for network meta-analysis (RoB NMA Tool). Syst Rev. 2024 Jan 12;13(1):25.
  • Hooper R, Tovey D, Tricco AC, Veroniki AA. What advice can we offer to authors? Reflections from the statisticians' bench. J Clin Epidemiol. 2024 Nov;175:111579.
  • Lunny C, Whtielaw S, Reid E, Chi Y, Ferri N, Jiahe J, Peiper D, Kanji S, Veroniki AA, Shea B, Dourka J, Ardern C, Pham B, Bagheri E, Tricco AC. Exploring Decision Makers' Challenges and Strategies when Selecting Multiple Systematic Reviews: Insights for AI Decision Support Tools in Healthcare. BMJ Open. 2024 Jul 5;14(7):e084124.
  • Løvsletten PO, Wang X, Pitre T, Ødegaard M, Veroniki AA, Lunny C, Tricco AC, Agoritsas T, Vandvik PO. A systematic survey of 200 systematic reviews with network meta-analysis (published 2020 - 2021) reveals that few reviews report structured evidence summaries. J Clin Epidemiol. 2024 Jun 26;173:111445.

Webinars for LMICs

The convenors of the SMG Group will soon launch a series of monthly webinars on the fundamentals of statistical analysis in systematic reviews. These webinars are primarily designed for authors and trainers from low- and middle-income countries (LMICs). However, there will be no restrictions on the total number of attendees. The webinars are scheduled to take place between May and December 2025. The exact dates, along with the detailed content of each session, will be announced soon.

Webinar series

Upcoming seminars:

Register for the live event here. A full recording will be provided.

Past seminars:

Please do send us suggestions of presenters and topics for future learning live events.

SMG presence on social media

We are happy to announce that SMG Group has launched new pages on LinkedIn (https://www.linkedin.com/groups/14581838/) and Bluesky (https://bsky.app/profile/cochranesmg.bsky.social). These platforms will serve as our primary channels for sharing updates. As part of our transition, we have decided to discontinue our account on X (formerly Twitter). This account will no longer be updated.

Contact us

Convenors: 

Joanne McKenzie, Australia
Catrin Tudur Smith, UK
Mark Simmonds, UK
Areti Angeliki (Argie) Veroniki, Canada 

Theodoros Evrenoglou, Germany

Joseph Santos, Switzerland

Lizzie Korevaar, Australia

For details about how to post to the SMGlist, or how to unsubscribe from the list, please go to: https://lists.cochrane.org/mailman/listinfo/smglist

To read the archives of messages posted to the SMGlist, please go to: https://lists.cochrane.org/pipermail/smglist/ or use the link above to obtain your password and access the archives from there.

Please follow us @CochraneStats and tag us in any relevant work or training events.

26 Jan 2025