Transitivity and conditional constancy cannot be tested in-sample
Source note. This entry derives in part from a source document whose inline citations were ChatGPT interface tokens rather than references, and so resolve to nothing. Claims below are attributed to that document and were checked independently where possible; anything that could not be independently sourced is marked in the verification trail.
No. Each screen sees one direction of violation, and an unmeasured modifier that makes one treatment look better in every comparison that includes it is invisible to all three: at size 0.4 it biased the network estimate by 0.40 with coverage near zero while the screens together fired at their null rate (0.28). Loop breaks and drift were detected with power rising in the number of studies, but the pattern of flags identified the mechanism poorly, and a measured modifier was always flagged although adjustment removed its bias. Read the study below.
Statement
Transitivity, consistency and conditional constancy restrict counterfactual quantities that are never jointly observed, so they cannot be verified nonparametrically from the data and passing any check does not establish transportability. Prespecifiable screens nevertheless exist: Spineli et al. (doi:10.1002/sim.70068) compute dissimilarities between treatment comparisons from study-level characteristics and cluster them to locate hot spots of potential intransitivity, backed by the tracenma database of 217 network datasets assembled to develop exactly this methodology, and Phillippo et al. (doi:10.1177/0272989X221117162) assess conditional constancy through residual heterogeneity and inconsistency, though only in sufficiently large networks. What survives is narrower than the source claimed: each screen tests one observable implication, a calibrated failure is evidence against at least one assumption without saying which, and no catalogue states which implications a population-adjusted comparison should prespecify or what action a failure triggers. The judgment also governs whether the analysis happens at all, and nothing governs the judgment: reviews that prespecify a network meta-analysis and then cannot assess whether potential effect modifiers are similar across comparisons abandon it on an unquantified reading, with no threshold, no requirement to report network estimates that were fitted and then withheld, and no convention for signaling the abandonment where readers will see it. Three 2017 Cochrane reviews from one group abandoned an identical prespecified Bayesian protocol this way, one of them after fitting the models and detecting inconsistency, and the Cochrane Central Editorial Unit required the phrase ‘attempted network meta-analysis’ to be removed from one title on the grounds that it might confuse readers. The screens are also not always executable, and nothing says when that matters: no rule states which covariates must be reported, by what fraction of the trials contributing to each comparison and at what level of detail, before a transitivity screen counts as runnable, nor what an analyst owes when it cannot be run, whether to proceed and label the network as assumption-laden, restrict to a subnetwork with adequate reporting, or decline. The consequence is visible divergence rather than acknowledged uncertainty: two Cochrane reviews abandoned planned network meta-analyses of hepatocellular carcinoma treatments because effect-modifier similarity could not be assessed, one of them across a connected 18-trial evidence base (doi:10.1002/14651858.CD011650.pub2, doi:10.1002/14651858.CD011649.pub2), while other teams synthesize and rank the same interventions, and neither the go nor the no-go decision can be checked against any stated criterion.
Why it is open
The restriction is on treatment contrasts in study and population cells that are never jointly observed, so no function of the observed data has power against every violation, and covariate balance or model fit can look excellent under severe residual confounding. The screens that exist do not close this. The dissimilarity and clustering approach works on reported study-level characteristics and returns a semi-objective judgment rather than a verdict, and in 209 real networks a likely intransitivity prevailed in all of them while statistical tests were feasible in only 61 percent and often disagreed with the dissimilarity reading. For population-adjusted comparisons the residual-heterogeneity route needs a network large enough to support it, which is not the setting where conditional constancy does the most identifying work.
What has been tried
| Work | What it contributes |
|---|---|
| Spineli et al. 2024, Low awareness of the transitivity assumption in complex networks of interventions: a systematic survey from 721 network meta-analyses, BMC Medicine | sources the previously unattributed claim that transitivity is examined poorly in practice: most reviews evaluated it statistically rather than conceptually (40 percent versus 12 percent before PRISMA-NMA, 54 percent versus 11 percent after), with consistency evaluation the most preferred device (34 percent to 47 percent) |
| Spineli 2024, An empirical study on 209 networks of treatments revealed intransitivity to be common and multiple statistical tests suboptimal to assess transitivity, BMC Medical Research Methodology | empirical evidence that a likely intransitivity prevailed in all datasets examined and that statistical tests were feasible in only 61 percent of them and often conflicted with a study-dissimilarity reading |
| Spineli et al. 2025, Exploring the Transitivity Assumption in Network Meta-Analysis: A Novel Approach and Its Implications, Statistics in Medicine | gives a prespecifiable quantitative transitivity screen from dissimilarity matrices and hierarchical clustering that detects hot spots of potential intransitivity and supports semi-objective judgments; it does not verify the assumption |
| tracenma R package v0.1.1 (2025), database for developing transitivity methodology in network meta-analysis; companion paper doi:10.1186/s12874-025-02634-x | public benchmark database of 217 network meta-analysis datasets with extracted study-level candidate effect modifiers, built expressly to develop transitivity methodology |
| Phillippo et al. 2023, Validating the Assumptions of Population Adjustment: Application of Multilevel Network Meta-regression to a Network of Treatments for Plaque Psoriasis, Medical Decision Making | assesses population-adjustment assumptions inside a nine-study network: splits the common class interaction into treatment-specific interactions one covariate at a time, checks conditional constancy through residual heterogeneity and inconsistency in sufficiently large networks, and reports that the shared-interaction restriction was required to identify the model where a treatment was informed only by aggregate data |
| Mantzoukis et al. 2017, Pharmacological interventions for acute hepatitis B infection: an attempted network meta-analysis, Cochrane Database of Systematic Reviews | Shows what happens when the transitivity screen cannot be run: the planned network meta-analysis was abandoned because it was not possible to assess whether potential effect modifiers were similar across comparisons, and the Cochrane Central Editorial Unit then required the phrase ‘attempted network meta-analysis’ to be removed from the review title on the grounds that it might confuse readers, so the abandonment is invisible in the Cochrane Library record while PubMed retains it. |
| Lombardi et al. 2017, Pharmacological interventions for non-alcohol related fatty liver disease (NAFLD): an attempted network meta-analysis, Cochrane Database of Systematic Reviews | A second review from the same group with the same prespecified Bayesian protocol, abandoned on the identical unquantified judgment that it was not possible to assess whether potential effect modifiers were similar across comparisons; 77 trials and 6287 participants were then synthesized pairwise instead. |
| Buzzetti et al. 2017, Pharmacological interventions for alcoholic liver disease (alcohol-related liver disease): an attempted network meta-analysis, Cochrane Database of Systematic Reviews | The case where the models were fitted and the results withheld: in the subgroup where effect modifiers appeared reasonably similar across comparisons there was evidence of inconsistency, so the network results were not reported and 81 trials were synthesized pairwise. It shows the abandonment decision arising after fitting as well as before it. |
| van der Mark et al. 2012, A systematic review with attempted network meta-analysis of asthma therapy recommended for five to eighteen year olds in GINA guidelines, BMC Pulmonary Medicine | An earlier attempted network meta-analysis, establishing that abandonment after prespecification predates the 2017 group of reviews and is not confined to one editorial group. |
| Boonpattharatthiti et al. 2025, Reporting and evaluation of assumptions and certainty of evidence in network meta-analyses, Research Synthesis Methods | Surveys how assumptions and certainty of evidence are reported and evaluated across published network meta-analyses, which is the reporting-practice side of the same transitivity judgment. |
| Majumdar, Roccarina, Thorburn, Davidson, Tsochatzis and Gurusamy 2017, Management of people with early- or very early-stage hepatocellular carcinoma: an attempted network meta-analysis, Cochrane Database of Systematic Reviews CD011650 | A planned network meta-analysis of 18 eligible randomized trials abandoned on the stated ground that it was not possible to assess whether the potential effect modifiers were similar across different comparisons, so performing a network meta-analysis in this scenario can be misleading; the review reverts to pairwise comparisons and issues no ranking. |
| Roccarina, Majumdar, Thorburn, Davidson, Tsochatzis and Gurusamy 2017, Management of people with intermediate-stage hepatocellular carcinoma: an attempted network meta-analysis, Cochrane Database of Systematic Reviews CD011649 | The companion review reaching the same abstention on the same grounds in an adjacent evidence base, showing that the no-go decision is a repeated practice of one group rather than a single reviewer’s judgment, and still resting on no stated criterion. |
Probable solution or research direction
The screening step no longer needs inventing, so the work is calibration and prespecification: characterize the operating characteristics of the dissimilarity and clustering screen against the tracenma datasets, and fix in advance which implications are checked, on what scale, and what a failure obliges the analyst to do. Around it, assemble the falsification devices that population adjustment still lacks, including held-out-trial contrast prediction, bridge deletion, negative controls, transported versus observed control-arm comparison, cross-trial interaction replication, and transport checks separated by calendar time, geography and setting. Report all of them with an explicit statement that passing does not establish transportability, and where falsification is impossible attach an explicit bias function to the restriction instead of asserting it.
Our study
What each transitivity screen can see
The question put to it. Do the available transitivity screens (covariate dissimilarity, loop inconsistency, heterogeneity), run together, detect the violations that bias a network estimate, and can their pattern of flags identify the mechanism?
What it found. No. Each screen sees one direction of violation, and an unmeasured modifier that makes one treatment look better in every comparison that includes it is invisible to all three: at size 0.4 it biased the network estimate by 0.40 with coverage near zero while the screens together fired at their null rate (0.28). Loop breaks and drift were detected with power rising in the number of studies, but the pattern of flags identified the mechanism poorly, and a measured modifier was always flagged although adjustment removed its bias.
Results.
- Refuting sentence fails: loop-consistent unmeasured modification of 0.4, any-screen detection 0.281 and 0.279 against 0.274 and 0.283 with no violation; bias -0.40.
- Loop break of 0.4: detected in 0.77 (2 studies per comparison) and 0.98 (5); drift of 0.4: 0.95 and 1.00.
- Measured modifier: dissimilarity flagged 100% of analyses; meta-regression bias at most 0.003.
- Mechanism read from the flag pattern: loop breaks 43% correct, drift 34%; drift often triggered the loop test.
Design.
- Estimand
- B versus C effect in a declared target population
- Methods compared
- covariate dissimilarity screen, Bucher loop inconsistency test, Cochran’s Q heterogeneity screen, their union
- Data-generating mechanism
- Triangle networks with two or five studies per comparison and five violation mechanisms, including a loop-consistent unmeasured modifier constructed to be invisible to every screen; 26 cells, 2000 replicates each; detection, bias, coverage and mechanism identification.
- Replicates
- 2000 per scenario, 52,000 in total
What this does not answer. Stylized triangle networks with continuous estimates; calendar drift as random shifts; abandonment records not scored. Peer review has not been done.
Peer review. Not yet done. The result stands on the study alone until it is.
Read it: PDF · Markdown · OpenDocument · Code and data: studies/IDN-01-calibrating-transitivity-screens · Protocol: registered before the run
Verification
Verdict. Partially addressed. Auditors agreed the problem is open and no counterevidence surfaced. Reopened by the full-text reading: 4 findings from 4 papers survived both the reader and an independent second reviewer, so the verdict moves from confirmed-open to partially-addressed.
The source said. “Standard ITC requires transitivity, consistency and a sensible effect scale, and PAIC adds conditional constancy of relative effects, yet these assumptions cannot be fully tested from the observed data. Research should therefore be redirected from impossible assumption tests towards prespecified falsification opportunities, accepting that success does not prove transportability while failure is highly informative.”
What was wrong with it. The source carried no citations and asserted both that there is no agreed catalogue of which implications to check or how to prespecify them and that a failed check is highly informative. The literature auditor sourced the practice claims (doi:10.1186/s12916-024-03322-1, doi:10.1186/s12874-024-02436-7) and found a prespecifiable transitivity screen already published (doi:10.1002/sim.70068, with cran:tracenma), so the entry is now sourced; the source-code auditor cut ‘highly informative’ back to evidence against at least one unidentified assumption, since a failure can equally reflect sampling variation, support failure, outcome-version differences or an invalid control.
Revised by the full-text reading. Applied full-text reading.
- merged-in
- absorbed a proposal the reading raised separately: No standard governs abandoning a prespecified NMA 5 citation(s) added. The drafter disagreed with placing it here: The merge is right about the trigger and incomplete about the consequence. The reason for abandonment is exactly the in-sample untestability IDN-01 describes, so it belongs here. What does not fit IDN-01’s scope is the reporting half: no requirement to disclose fitted-but-withheld network estimates, no convention for signaling abandonment in the title or abstract, and no accounting of what the fallback to pairwise synthesis discards. That is a transparency requirement of the kind DEC-13 covers for population-adjusted analyses, and it will not be visible to a reader who arrives at IDN-01 looking for an identification problem.
- merged-in
- absorbed a proposal the reading raised separately: No criterion decides whether covariate reporting licenses NMA 2 citation(s) added
- Verdict changed
- confirmed-open -> partially-addressed 4 surviving findings from: A process for assessing the feasibility of a network meta-an; Comparative effectiveness of biological medicines in rheumat; Exploring the Transitivity Assumption in Network Meta-Analys; Network meta-analysis including treatment by covariate inter. New citations: 10.1002/jrsm.1257, 10.1002/sim.70068, 10.1136/bmj.m2288, 10.1186/1741-7015-12-93
- Literature and prior-art check
- open / supported-with-caveat. Retrieved Spineli et al. 2024 (BMC Med, 721 NMAs) and Spineli 2024 (BMC Med Res Methodol, 209 networks), which supply exactly the empirical backing this unsourced entry lacks: transitivity is mostly evaluated statistically rather than conceptually (40% vs 12% pre-PRISMA-NMA; 54% vs 11% post), consistency evaluation is the single most-used device (34% -> 47%), and likely intransitivity ‘prevailed in all datasets’. Phillippo et al. 2023 independently states that conditional constancy ‘may be assessed by checking for residual heterogeneity and inconsistency’ only ‘in sufficiently large networks’. The core claim (the restriction is on counterfactuals never jointly observed, so no in-sample test has power against every violation) is unsolvable by construction and stays open. Caveat: why_open asserts ‘no agreed catalogue of which implications are worth checking, how to prespecify them’. That is now materially narrowed. Spineli et al. 2025 (Stat Med) give a prespecifiable dissimilarity-plus-clustering transitivity screen with empirically derived thresholds, backed by the public tracenma CRAN database (217 NMA datasets) built expressly to develop such methodology. The entry cites none of this and should. Cites 10.1186/s12916-024-03322-1: Sources the unsourced claims that transitivity is poorly examined in practice and that NMA diagnostics lean on after-the-fact inconsistency. Cites 10.1186/s12874-024-02436-7: Empirical evidence that intransitivity is common and that statistical tests are a poor device for assessing it. Cites 10.1002/sim.70068: Provides a prespecifiable, quantitative transitivity screen (dissimilarity matrices plus hierarchical clustering) that narrows the entry’s claim that no catalogue or prespecification procedure exists. Cites cran:tracenma: A public benchmark database of 217 NMA datasets with extracted study-level candidate effect modifiers, built specifically to develop transitivity methodology.
- GPT-5.6 Sol, technical and source-code lens
- open / overstated. The central nonidentification point is correct: observed data cannot verify equality of counterfactual treatment contrasts across unobserved study-treatment cells, and balance or model fit cannot rule out residual bias. However, C6 is a false scientific-versus-statistical dichotomy because these are formal statistical restrictions informed by science, sometimes with testable implications. C13 is materially too strong: a failed held-out prediction or negative control may reflect sampling variation, heterogeneity, support failure, outcome-version differences, model misspecification, or an invalid negative control. It is not automatically highly informative about transitivity. C14 additionally requires that withholding the trial preserve identification and that prediction and observation target the same population-specific estimand. C15 requires a valid negative control sharing the relevant bias pathway. C8-C10 are empirical literature claims outside this audit lens.
- Decision path
-
R5:default-open → R9:substantiated-single-overstatement:codex
How the evidence falls in time
103 papers in the reviewed corpus bear on this problem, published 2011 to 2026. Partial progress is on the record, and later work still calls this open. Both belong in view.
This problem is recurrent: three or more papers spanning at least eight years assert it independently. Sustained restatement by authors who mostly do not cite each other is the strongest evidence this reading can offer that a gap is real rather than one group’s framing.
It is also being closed in pieces: partial results come from more than one paper in more than one year, each covering a different part.
| Year | Says | Paper |
|---|---|---|
| 2011 | confirms it is open | Conducting indirect-treatment-comparison and network-meta-analysis studies: report of the ISPOR Task Force on Indirect Treatment Comparisons Good Research Practices: part 2 |
| 2011 | confirms it is open | Interpreting indirect treatment comparisons and network meta-analysis for health-care decision making: report of the ISPOR Task Force on Indirect Treatment Comparisons Good Research Practices: part 1 |
| 2011 | confirms it is open | Quantifying nonsteroidal anti-inflammatory drug (NSAID) risk: can combining the evidence with the use of a network meta-analysis provide a solution? |
| 2012 | confirms it is open | Consistency and inconsistency in network meta-analysis: concepts and models for multi-arm studies |
| 2012 | confirms it is open | Consistency and inconsistency in network meta-analysis: model estimation using multivariate meta-regression |
| 2012 | confirms it is open | Impact of Reporting Bias in Network Meta-Analysis of Antidepressant Placebo-Controlled Trials |
| 2012 | confirms it is open | Meta-analyses: what they can and cannot do |
| 2012 | confirms it is open | Simulation evaluation of statistical properties of methods for indirect and mixed treatment comparisons |
| 2013 | confirms it is open | Demystifying trial networks and network meta-analysis |
| 2013 | confirms it is open | Evaluation of inconsistency in networks of interventions |
| 2013 | confirms it is open | Evidence synthesis for decision making 4: inconsistency in networks of evidence based on randomized controlled trials |
| 2013 | confirms it is open | Graphical tools for network meta-analysis in STATA |
| 2013 | confirms it is open | Is network meta-analysis as valid as standard pairwise meta-analysis? It all depends on the distribution of effect modifiers |
| 2013 | confirms it is open | Which placebo to cure depression? A thought-provoking network meta-analysis |
| 2014 | partly addresses it | A process for assessing the feasibility of a network meta-analysis: a case study of everolimus in combination with hormonal therapy versus chemotherapy for advanced breast cancer |
| 2014 | confirms it is open | An overview of conducting systematic reviews with network meta-analysis |
| 2014 | confirms it is open | Characteristics of a loop of evidence that affect detection and estimation of inconsistency: a simulation study |
| 2014 | confirms it is open | Characteristics of networks of interventions: a description of a database of 186 published networks |
| 2014 | confirms it is open | Evaluating the quality of evidence from a network meta-analysis |
| 2014 | confirms it is open | Network-meta analysis made easy: detection of inconsistency using factorial analysis-of-variance models |
| 2014 | confirms it is open | Placebo for depression: we need to improve the quality of scientific information but also reject too simplistic approaches or ideological nihilism |
| 2014 | confirms it is open | The quality of reporting methods and results in network meta-analyses: an overview of reviews and suggestions for improvement |
| 2015 | confirms it is open | A primer on network meta-analysis with emphasis on mental health |
| 2015 | confirms it is open | Automated generation of node-splitting models for assessment of inconsistency in network meta-analysis |
| 2015 | confirms it is open | Comparative effectiveness of exercise and drug interventions on mortality outcomes: metaepidemiological study |
| 2015 | confirms it is open | Extending DerSimonian and Laird’s methodology to perform network meta-analyses with random inconsistency effects |
| 2015 | confirms it is open | Indirect Comparisons and Network Meta-Analyses: Estimation of Effects in the Absence of Head-to-Head Trials (Part 22 of a Series on Evaluation of Scientific Publications) |
| 2015 | confirms it is open | Methods and characteristics of published network meta-analyses using individual patient data: protocol for a scoping review |
| 2015 | confirms it is open | Network Meta-analysis: Users’ Guide for Surgeons: Part I - Credibility |
| 2015 | confirms it is open | Network Meta-analysis: Users’ Guide for Surgeons: Part II - Certainty |
| 2015 | confirms it is open | Network meta-analysis incorporating randomized controlled trials and non-randomized comparative cohort studies for assessing the safety and effectiveness of medical treatments: challenges and opportunities |
| 2016 | confirms it is open | A scoping review of indirect comparison methods and applications using individual patient data |
| 2016 | confirms it is open | Assumptions of Mixed Treatment Comparisons in Health Technology Assessments - Challenges and Possible Steps for Practical Application |
| 2016 | confirms it is open | Exploratory Network Meta Regression Analysis of Stroke Prevention in Atrial Fibrillation Fails to Identify Any Interactions with Treatment Effect |
| 2016 | confirms it is open | GetReal in network meta-analysis: a review of the methodology |
| 2016 | confirms it is open | Use of network meta-analysis in systematic reviews: a survey of authors |
| 2017 | partly addresses it | Network meta-analysis including treatment by covariate interactions: Consistency can vary across covariate values |
| 2017 | confirms it is open | Multivariate and network meta-analysis of multiple outcomes and multiple treatments: rationale, concepts, and examples |
| 2017 | confirms it is open | Multiple Score Comparison: a network meta-analysis approach to comparison and external validation of prognostic scores |
| 2017 | confirms it is open | Characteristics and knowledge synthesis approach for 456 network meta-analyses: a scoping review |
| 2017 | confirms it is open | Common pitfalls and mistakes in the set-up, analysis and interpretation of results in network meta-analysis: what clinicians should look for in a published article |
| 2017 | confirms it is open | Management of people with early- or very early-stage hepatocellular carcinoma: an attempted network meta-analysis |
| 2017 | confirms it is open | Network meta-analysis: drawing conclusions regarding trials of psychosocial interventions for bipolar disorder |
| 2017 | confirms it is open | Pharmacological interventions for acute hepatitis B infection: an attempted network meta-analysis |
| 2017 | confirms it is open | Pharmacological interventions for alcoholic liver disease (alcohol-related liver disease): an attempted network meta-analysis |
| 2017 | confirms it is open | Pharmacological interventions for non-alcohol related fatty liver disease (NAFLD): an attempted network meta-analysis |
| 2017 | confirms it is open | Pharmacological interventions for primary sclerosing cholangitis: an attempted network meta-analysis |
| 2018 | confirms it is open | Dismantling cognitive-behaviour therapy for panic disorder: a systematic review and component network meta-analysis |
| 2018 | confirms it is open | A systematic review of network meta-analyses for pharmacological treatment of common mental disorders |
| 2018 | confirms it is open | Assessing the consistency assumptions underlying network meta-regression using aggregate data |
| 2018 | confirms it is open | Evidence synthesis, practice guidelines and real-world prescriptions of new generation antidepressants in the treatment of depression: a protocol for cumulative network meta-analyses and meta-epidemiological study |
| 2018 | confirms it is open | Cumulative network-meta-analyses, practice guidelines and actual prescriptions of drug treatments for postmenopausal osteoporosis: a study protocol for cumulative network meta-analyses and meta-epidemiological study |
| 2018 | confirms it is open | Large-scale external validation and comparison of prognostic models: an application to chronic obstructive pulmonary disease |
| 2018 | confirms it is open | Living network meta-analysis compared with pairwise meta-analysis in comparative effectiveness research: empirical study |
| 2018 | confirms it is open | Network meta-analysis explained |
| 2018 | confirms it is open | Network meta-analysis in health psychology and behavioural medicine: a primer |
| 2018 | confirms it is open | Network meta-analysis, a new statistical technique at urologists’ disposal to improve decision making |
| 2018 | confirms it is open | Network meta-analysis: users’ guide for pediatricians |
| 2019 | confirms it is open | Acupuncture in sham device controlled trials may not be as effective as acupuncture in the real world: a preliminary network meta-analysis of studies of acupuncture for hot flashes in menopausal women |
| 2020 | partly addresses it | Comparative effectiveness of biological medicines in rheumatoid arthritis: systematic review and network meta-analysis including aggregate results from reanalysed individual patient data |
| 2020 | confirms it is open | Psychological and pharmacological interventions for posttraumatic stress disorder and comorbid mental health problems following complex traumatic events: Systematic review and component network meta-analysis |
| 2020 | confirms it is open | Extending inferences from a randomized trial to a new target population (Dahabreh, Robertson, Steingrimsson, Stuart, Hernan; tutorial, arXiv:1805.00550v3) |
| 2020 | confirms it is open | A simulation study to compare different estimation approaches for network meta-analysis and corresponding methods to evaluate the consistency assumption |
| 2020 | confirms it is open | CINeMA: An approach for assessing confidence in the results of a network meta-analysis |
| 2020 | confirms it is open | Different control conditions can produce different effect estimates in psychotherapy trials for depression |
| 2020 | confirms it is open | Comparative efficacy of placebos in short-term antidepressant trials for major depression: a secondary meta-analysis of placebo-controlled trials |
| 2020 | confirms it is open | Statistical analyses and quality of individual participant data network meta-analyses were suboptimal: a cross-sectional study |
| 2021 | confirms it is open | Supplementary appendix to Furukawa et al., Dismantling, optimising, and personalising internet cognitive behavioural therapy for depression: a systematic review and component network meta-analysis using individual participant data |
| 2021 | confirms it is open | Transportability of Causal Effects: Completeness Results (Bareinboim & Pearl, Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, pp. 698-704) |
| 2021 | confirms it is open | A method for assessing robustness of the results of a star-shaped network meta-analysis under the unidentifiable consistency assumption |
| 2021 | confirms it is open | Concepts and emerging issues of network meta-analysis |
| 2021 | confirms it is open | Prevalence of evidence of inconsistency and its association with network structural characteristics in 201 published networks of interventions |
| 2022 | confirms it is open | Baseline imbalance and heterogeneity are present in meta-analyses of randomized clinical trials examining the effects of exercise and medicines for blood pressure management |
| 2022 | confirms it is open | Comparing the Efficacy and Safety Profile of Triple Fixed-Dose Combinations in COPD: A Meta-Analysis and IBiS Score |
| 2022 | confirms it is open | Complex speech-language therapy interventions for stroke-related aphasia: the RELEASE study incorporating a systematic review and individual participant data network meta-analysis |
| 2023 | confirms it is open | A new approach to evaluating loop inconsistency in network meta-analysis |
| 2023 | confirms it is open | A guide and pragmatic considerations for applying GRADE to network meta-analysis |
| 2023 | confirms it is open | The roles of expectation, comparator, administration route, and population in open-label placebo effects: a network meta-analysis |
| 2024 | confirms it is open | Exploring the Effectiveness of Self-Management Interventions in Type 2 Diabetes: A Systematic Review and Network Meta-Analysis |
| 2024 | confirms it is open | Letter to the Editor Regarding ‘Matching-Adjusted Indirect Comparison of the Long-Term Efficacy Maintenance and Adverse Event Rates of Lebrikizumab Versus Dupilumab in Moderate-to-Severe Atopic Dermatitis’ |
| 2024 | confirms it is open | An empirical study on 209 networks of treatments revealed intransitivity to be common and multiple statistical tests suboptimal to assess transitivity |
| 2024 | confirms it is open | Effectiveness of Rehabilitation for Osteoarthritis of the Knee: A Scoping Review of Network Meta-Analyses |
| 2024 | confirms it is open | How to conduct and report checking transitivity and inconsistency in network-meta-analysis: a narrative review including practical worked examples, code and source data for sports and exercise medicine researchers |
| 2024 | confirms it is open | Local inconsistency detection using the Kullback-Leibler divergence measure |
| 2024 | confirms it is open | Low awareness of the transitivity assumption in complex networks of interventions: a systematic survey from 721 network meta-analyses |
| 2024 | confirms it is open | Transitivity, coherence, and reliability of network meta-analyses comparing proximal humerus fracture treatments: a meta-epidemiological study |
| 2024 | confirms it is open | Twenty years of network meta-analysis: Continuing controversies and recent developments |
| 2025 | partly addresses it | Exploring the Transitivity Assumption in Network Meta-Analysis: A Novel Approach and Its Implications |
| 2025 | confirms it is open | Evaluating the feasibility of a network meta-analysis comparing treatment options in polycythemia vera |
| 2025 | confirms it is open | Letter to the Editor Regarding “Dupilumab Versus Lebrikizumab Demonstrates Greater Likelihood of Achieving and Maintaining Improvements in Efficacy Outcomes Using a Placebo Adjusted Indirect Treatment Comparison” |
| 2025 | confirms it is open | The hazards of using hazard ratios from proportional hazard models in indirect treatment comparisons |
| 2025 | confirms it is open | A database to initiate methodological advances in the evaluation of transitivity assumption in network meta-analysis: qualitative features and limitations of the tracenma R package |
| 2025 | confirms it is open | Implementation of the Anchor-Based Indirect Comparison Method for Equivalence Margin Derivation in Biosimilar Development |
| 2025 | confirms it is open | Lord’s Paradox and two network meta-analysis models |
| 2025 | confirms it is open | Methodologies for network meta-analysis of randomised controlled trials in pain, anaesthesia, and perioperative medicine: a narrative review |
| 2025 | confirms it is open | Reporting and evaluation of assumptions and certainty of evidence in network meta-analyses |
| 2025 | confirms it is open | Two-stage Bayesian network meta-analysis of individualized treatment rules for multiple treatments with siloed data |
| 2026 | confirms it is open | A novel approach for visualizing local consistency in network meta-analysis |
| 2026 | confirms it is open | Active treatment vs. expectant management of patent ductus arteriosus in preterm infants: critical analysis of a meta-analysis |
| 2026 | confirms it is open | Considerations in reviewing network meta-analyses of heterogeneous clinical trial designs: a methodological review in Crohn’s disease and ulcerative colitis |
| 2026 | confirms it is open | Influence Analyses of “Designs” for Evaluating Inconsistency in Network Meta-Analysis. |
| 2026 | confirms it is open | NMAstudio 2.0: An interactive tool for network meta-analysis to enhance understanding, interpretation, and communication of the findings. |
| 2026 | confirms it is open | What can we learn from network meta-analyses published in top medical journals |
Source
Derived from A:L5, A:L44, A:L60, C:L214-215, C:L222, C:L253, C:L394-396, C:L406 of the reviewed corpus.