STATISTICAL SOFTWARE
RevMan Meta-Analysis Service
Review Data Entered and Pooled Correctly
Our RevMan meta-analysis service carries out the analysis of systematic reviews in RevMan, with effect measures, data types and directions checked at entry, and the RevMan project and an extraction audit table provided where agreed so that the review can be reproduced.
No Commitment Required
Strictly Confidential
In-House PhD-Level Statisticians
Fixed Project Fee
Same-Day Response
What Is RevMan Used For in Research?
Review Manager (RevMan) is Cochrane’s software for preparing and maintaining systematic reviews. It holds the review text, the included studies, risk of bias assessments and the data tables, and it calculates meta-analyses and draws forest plots and funnel plots. Researchers use it for Cochrane reviews and for other systematic reviews that follow Cochrane methods, because the data, the analysis and the report stay together in one project. OnlineSPSS, a specialist statistical consultancy for academic, clinical and professional research, provides a RevMan meta-analysis service in which an in-house PhD-level statistician carries out the agreed analysis in RevMan from your extraction data and documents each choice.
WHEN TO ENGAGE
Four Situations in Which Review Teams Bring Us a RevMan Project
RevMan systematic review analysis is requested at the point where extracted data meet the analysis section, when a result looks wrong, when reviewers push back or when the review needs more than RevMan offers.
Data Ready for Analysis Studies are included and data are extracted, and the comparisons and outcomes must be set up with the right data types before any pooled result is reported.
Implausible Pooled Results A forest plot shows an extreme estimate or heterogeneity the studies do not seem to justify, and the cause is more often in how the effects were entered than in the studies.
Editorial or Peer Review Comments Reviewers or editors question the model, the sensitivity analyses or the risk of bias judgments, and the analysis has to be revisited, explained and documented.
Analysis Beyond RevMan The review needs meta-regression, a network analysis or a bivariate model that RevMan itself does not provide, and the external analysis is run elsewhere and documented with the project.
ANALYSES IN REVMAN
Review Analyses Carried Out in RevMan for Your Question
Each analysis follows the protocol and the type of outcome data, and its card links to the method page where the choice of method is explained.
Systematic Review
Outcomes, comparisons and subgroups prespecified in the protocol are entered as planned, and any later change is recorded as a deviation from it.
Meta-Analysis
Study effects are pooled by inverse-variance or Mantel-Haenszel methods and shown in a RevMan forest plot. Random-effects analyses in current RevMan default to REML with Hartung-Knapp-Sidik-Jonkman intervals and a prediction interval, so an analysis first run in an older version is rerun and any difference explained.
Relative Risk & Odds Ratios
Dichotomous outcomes are entered as events and totals and pooled as risk ratios or odds ratios, with Peto's method kept for rare events in groups of similar size.
Diagnostic Test Accuracy Meta-Analysis
Study-level sensitivity and specificity are tabulated and plotted, while a pooled bivariate or hierarchical model is run in an external tool and documented with the review.
SWiM (Synthesis Without Meta-Analysis)
Where outcomes or effect measures are too varied to pool, studies are tabulated and synthesized without pooling, with the grouping and the method stated and the tables kept with the project.
Survival Analysis
Time-to-event results enter as log hazard ratios with standard errors through the generic inverse-variance method, so the scale is confirmed before the studies are pooled.
COMMON REVMAN ISSUES
Where Review Analyses Go Wrong Before the Forest Plot
Errors in a review analysis usually enter with the data, and a polished plot can conceal them, so each check below is made before a pooled effect is interpreted.
Data Type Matched to the Outcome Dichotomous, continuous and generic inverse-variance data are entered differently. An outcome entered under the wrong type pools the wrong quantity, so each is matched to the extraction table.
Direction and Standard Errors A scale reversed in one study, or a standard error typed into the standard deviation field, shifts that study's effect or weight and can create extreme heterogeneity, so every entry is traced to its source.
Change Scores and Final Values A mean difference may combine change-from-baseline and final values, but a standardized mean difference may not, because the two rest on different standard deviations. The choice is fixed per outcome.
Model Follows the Question A fixed-effect or random-effects model is chosen from the synthesis question and the comparability of the studies, not from the result of a heterogeneity test or an I-squared threshold.
Risk of Bias Informs the Synthesis Risk of bias is judged by domain and outcome with support from the study text, and it feeds a sensitivity analysis. The RevMan risk of bias table is not collapsed into a single score.
Unit of Analysis Cluster-randomized and cross-over trials, and multi-arm trials with a shared control group, are adjusted before entry so that participants are not counted twice and precision is not overstated.
DELIVERABLES
What You Receive From a RevMan Analysis
The files follow a documented review workflow, agreed in the scope and provided where applicable, so that your team can audit every pooled result against the source studies.
RevMan Project The RevMan project with studies, data tables, analyses and plots, so that the review team can reopen it and continue the work.
Extraction and Effect Audit Table A table of every value entered, its source in the paper, the effect measure and its direction, so that each entry can be traced and checked.
Forest and Funnel Plots Forest plots for each comparison and funnel plots where the number of studies supports reading them, with outcome, direction and interval labeled.
External Analyses Documented Where RevMan is insufficient, the analysis run elsewhere is documented with its code or settings and its results, and kept beside the project.
Results Tables and Methods Text Summary tables and methods wording that state the model, the effect measures and the sensitivity analyses, in the form your target journal expects.
Statistical Interpretation Each pooled result is interpreted statistically, with heterogeneity, imprecision and small-study effects set out so that your team can apply them in its own certainty-of-evidence assessment.
OTHER PLATFORMS
When Another Platform May Be More Appropriate
RevMan suits standard review analyses, but the software follows the synthesis question, and some questions need another tool.
ILLUSTRATIVE EXAMPLE
How a RevMan Analysis May Look in Practice
An illustration of how trials with different units of randomization are prepared before they are pooled.
ILLUSTRATIVE EXAMPLE · SMOKING CESSATION EVIDENCE REVIEW · UNITED STATES
A university review team wanted to pool randomized trials of a counseling intervention for smoking cessation, using abstinence at follow-up as the dichotomous outcome.
The protocol fixed the outcome, the effect measure and the comparison before extraction. Two of the included trials had randomized clinics, not individual patients, and had reported their results as if each patient were independent. Entering those figures directly would have counted participants as more independent than they were and made the pooled interval too narrow. The team adjusted the sample sizes with a design effect based on an intracluster correlation taken from a stated external source, and showed the pooled result with and without the adjusted trials as a sensitivity analysis. Risk of bias was judged by domain for each trial and used to inform that analysis, and the model was chosen from the synthesis question, not from the heterogeneity result.
Outcome: The team received the RevMan project, an extraction audit table with the adjustments documented, forest plots for the comparison and the sensitivity analysis, and a methods paragraph describing the model and the handling of cluster trials.
This example does not describe a real client or project. We never share details of actual client work, in line with the confidentiality we promise every researcher. This illustrative example is included to show the type, scope, and standard of work involved in this kind of analysis.
RESEARCH DISCIPLINES
Research Fields Where RevMan Is Common
RevMan is most often used in medicine and health care, where Cochrane-style reviews are standard, and the same entry and synthesis questions arise in education, psychology and other fields that review intervention studies.
HOW WE ASSESS YOUR PROJECT
We Review Your Actual Research
Your assessment is based on a review of your actual research materials and analytical requirements, not a generic project category.
You Submit Your Project Details
Share whatever is available at the current stage, such as the research aim, protocol or proposal, dataset, variable list, manuscript or statistical requirements.
We Review Your Research and Define the Scope
Your statistically trained Research Coordinator reviews the materials to understand the study design, research questions, data structure, analytical requirements and expected deliverables. If clarification is needed, additional documents or information can be requested before the assessment is finalized.
Your Analysis Is Completed and Delivered
Once the scope and fixed project fee are agreed, the in-house statistician completes the work and the Research Coordinator remains the communication point through delivery, with the analysis, deliverables and timeline as agreed.
RESEARCHER VOICE
What Researchers Say
Feedback from a systematic review lead on effect directions and standard errors entered inconsistently across studies, and on outputs the team could audit.
“Keeping the analysis in RevMan mattered because the rest of the project team needed to rerun it later. They dealt with effect directions and standard errors being entered inconsistently across studies, documented the analytical steps clearly, and gave us outputs that were much easier to audit and report.”
Statistical Support Within Your Research OnlineSPSS provides the agreed methodological, analytical and statistical reporting support, including the RevMan files described in the scope. The researcher or research team retains the scientific question, substantive interpretation, conclusions and overall responsibility for the research.
FREQUENTLY ASKED QUESTIONS
Questions About RevMan Analysis for Research
Short answers to what review teams ask before sharing a RevMan project, from the analyses we carry out and existing projects to external analyses, Cochrane methods and confidentiality.
Which analyses do you carry out in RevMan?
Our Cochrane RevMan analysis covers data entry and checking, pooled meta-analysis under fixed-effect and random-effects models, subgroup and sensitivity analyses, forest and funnel plots and the risk of bias tables. The choice follows your protocol and the outcome data, and it is confirmed during the assessment.
Can you work from my RevMan project and extraction data?
We work from the RevMan project and the extraction data themselves, not from pooled figures alone. Entries are checked against the source papers before the analysis is extended, and a finished review analysis can be examined through Independent Statistical Review, which rechecks data types, directions and the unit of analysis study by study.
What if my review needs an analysis RevMan does not offer?
It is run in a tool that supports it, usually R or Stata, while RevMan keeps the data, the forest plots and the review text. Meta-regression, network meta-analysis and bivariate diagnostic models are the usual cases, and the methods section names both programs so that readers know which result came from which.
Do I have to follow Cochrane methods to use RevMan?
No. RevMan is also used for other systematic reviews. Cochrane reviews follow the Cochrane Handbook and the requirements of the review group, while another review follows its own protocol and reporting guideline, and the analysis is documented accordingly.
How do you protect my research data and confidentiality?
Your extraction data, RevMan projects and review protocol are handled confidentially, and project information is not published. An NDA is available where required and can be arranged before sensitive materials are shared. Read more about confidentiality and data security.
What happens when I request an assessment, and how long does it take?
You share your research question, design and relevant materials, such as the review protocol and extraction data, and a statistically trained Research Coordinator reviews the request and responds the same day. The analysis, deliverables, timeline and one fixed project fee are then confirmed before any work begins, so the timeline follows from the agreed scope.
Still have a question? Find more answers in our full FAQ.
NEXT STEP
Discuss Your
RevMan Analysis With Us
Share your review question, protocol, extraction data or RevMan project and the comparisons you plan. We check how the studies were entered and confirm the analysis before any work begins.
No Commitment Required
Strictly Confidential
Fixed Project Fee
In-House PhD-Level Statisticians
Same-Day Response
Serving Researchers Since 2014