Pith. sign in

REVIEW 80 references

Population-adjusted indirect comparisons identify comparator-population effects, and the shared effect modifier assumption alone does not make them transportable to other populations.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · deepseek-v4-flash

2026-08-02 22:21 UTC pith:VUO4FW6M

load-bearing objection Useful two-step transportability frame and a correct warning about marginal OR/HR, but the conditional-transportability guidance quietly assumes SPFA and overstates what SEMA alone buys you.

arxiv 2602.17041 v3 pith:VUO4FW6M submitted 2026-02-19 stat.ME

Reframing Population-Adjusted Indirect Comparisons as a Transportability Problem: An Estimand-Based Perspective and Implications for Health Technology Assessment

Conor Chandler , Jack Ishak This is my paper
classification stat.ME
keywords transportabilitypopulation-adjusted indirect comparisonsmatching-adjusted indirect comparisonsimulated treatment comparisoncollapsibilityshared effect modifier assumptionestimandshealth technology assessment
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Health technology assessment often relies on indirect comparisons when no head-to-head trials exist. The paper argues that the common adjustment methods—matching-adjusted and simulated treatment comparisons—only pin down the treatment effect in the comparator trial's population, not in any other population. It shows that the shared effect modifier assumption, widely cited as justifying transport of these effects, is not enough: for non-collapsible measures such as odds ratios and hazard ratios, the marginal effect changes with the covariate distribution even when the assumption holds. If accepted, this reframing changes how PAIC results should be reported and used in cost-effectiveness modeling: population-specific estimates need an explicit additional transport step before being applied to decision-relevant populations.

Core claim

The paper's central claim is that pairwise MAIC and STC identify active-to-active contrasts defined in the comparator population, and that these contrasts are not generally portable. SEMA ensures only that effect-modification terms cancel on a chosen scale; it does not make the marginal estimand invariant. Direct transportability of a marginal effect requires three joint conditions: SEMA; effect modification and the effect measure on the same linear predictor scale; and a collapsible measure. For conditional effects, SEMA plus scale alignment suffice. The paper proves this in formal propositions and demonstrates with simulations that mean differences and log risk ratios transport under SEMA,

What carries the argument

The central object is the estimand-based decomposition of a pairwise anchored indirect comparison into two transport steps: first, conditional transport of the index-trial effect to the comparator population; second, implicit direct transport of the resulting active-to-active effect to the decision population. The technical workhorse is the structural model g(E[Y_t|X]) = m(x) + δ_t + φ(x)1{t≠A}, with a shared prognostic function m and shared effect modification φ under SEMA. Propositions A1–A2 establish when contrasts are invariant under covariate-distribution shifts; Propositions B1–B3 establish contrast-induced direct collapsibility, for example the log risk ratio case where the active-to-

Load-bearing premise

The formal results rest on the structural model in which the same baseline prognosis function applies to all treatments and the two active treatments share an identical effect-modification function on the model's scale; if those functions differ across treatments, the cancellation that produces transportable contrasts does not occur.

What would settle it

Simulate an anchored comparison with SEMA and scale alignment holding by construction for a marginal odds ratio or hazard ratio, letting the index and comparator populations differ in the mean of an effect modifier; if the true marginal active-active effect is identical in every population, the paper's central claim is false, and if it varies, the claim is confirmed.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • Pairwise MAIC/STC results on odds-ratio or hazard-ratio scales should be labelled as comparator-population estimands; applying them to the index or real-world population requires explicit re-standardization or new assumptions.
  • HTA guidance that treats SEMA as sufficient for transporting marginal relative effects is too permissive; the transport step fails exactly for the non-collapsible measures most commonly submitted.
  • Cost-effectiveness models that feed MAIC/STC hazard or odds ratios into a decision model defined for another population risk transport bias that is not captured in the statistical confidence intervals.
  • For collapsible, scale-aligned measures (mean differences, log risk ratios under a log-link SEMA), direct transport is justified; analysts can design analyses around these measures when clinically reasonable.
  • Network-based methods that estimate effects in a pre-specified target population can avoid the implicit second step, but only under stronger network-wide assumptions about shared prognostic and effect-modification functions.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Beyond the paper: the same two-step logic applies to any indirect comparison or network meta-analysis applied in an economic model; a marginal hazard ratio from an NMA is also population-specific, so the transport-bias concern is broader than MAIC/STC.
  • Beyond the paper: divergent MAIC results in different sponsors' submissions may be explained as different estimands anchored to different comparator populations, suggesting that consistency checks should compare target-population standardized effects rather than raw estimates.
  • Beyond the paper: a practical test for HTA reviews would be to request the covariate distributions of the comparator trial and run a model-based re-standardization to the decision population; if the effect changes materially, the submission should report both estimates.
  • Beyond the paper: the scale-alignment condition suggests an actionable design choice—specify effect modification on the same scale as the decision-relevant effect measure, or choose a collapsible measure—to make transportability claims more defensible.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Circularity Check

0 steps flagged

No significant circularity: the transportability results are self-contained mathematical deductions; self-citations are background, and the SPFA caveat is an assumption-reporting issue, not a circular reduction.

full rationale

The paper's central derivation (Propositions A1–A2 and B1–B3) is a set of conditional mathematical implications from an explicitly specified structural model, Eq. (A1): g(E[Y_t|X]) = m(x) + δ_t + φ(x)1{t≠A}. The claim that SEMA alone does not make marginal OR/HR effects directly transportable is derived by computing marginal contrasts under this model and using the standard property that non-collapsible measures do not reduce to a covariate-independent contrast. No fitted constants are used to generate the illustrative results; the simulations are constructed examples, not empirical predictions. The two self-citations (Ishak et al. 2025, ref 19; Chandler & Ishak 2025, ref 77) provide background and an extension (ML-UMR), but the transportability proof does not rest on them; the load-bearing guidance citations (NICE DSU TSD 18; Phillippo et al.) are external. The skeptic's SPFA point is a genuine assumption-reporting issue: Prop. A1's Eq. (A1) sets a common m(x), and Appendix A acknowledges this as SPFA, yet Section 6.4 and Table 1 state conditional transportability under SEMA plus scale alignment without listing SPFA, and Appendix A says 'the only structural assumptions required are additivity on the g-scale and sharing of φ(x) across active treatments under SEMA.' If m(x) differed across active treatments, the x-dependence would not cancel even for conditional contrasts, so the Section 6.4 summary overstates what SEMA alone achieves. However, this is an omitted-assumption/overstatement, not a circular reduction: the formal proposition explicitly includes the common-m assumption, and the core negative result for non-collapsible marginal measures does not rely on SPFA. Therefore, under the hard rules requiring a specific reduction of a prediction to its inputs, no circular step qualifies.

Axiom & Free-Parameter Ledger

1 free parameters · 5 axioms · 0 invented entities

The central transportability claims are derived from the structural model in Eq. (A1) plus SEMA/SPFA and scale alignment. No new physical or statistical entities are postulated; the simulations use hand-set constants rather than fitted parameters. The burden falls on whether the structural model and assumptions hold in real PAIC applications.

free parameters (1)
  • Simulation scenario constants (β0, β1, γB, γC, β2,B, β2,C, μX range, Weibull ν) = Hand-set, e.g., β0=20, β1=10, γB=10, γC=5, β2=2 (§7.1); β2=log(0.9), ν=1.5 (§7.3)
    These are illustrative data-generating choices, not fitted parameters. They instantiate SEMA/no-SEMA scenarios but do not determine the qualitative transportability conclusions.
axioms (5)
  • standard math Rubin causal model with potential outcomes Y_t for t∈{A,B,C}; consistency and positivity.
    Section 2.1; the estimand framework presupposes the standard causal inference counterfactual assumptions.
  • domain assumption Conditional transportability in Step 1: all relevant effect modifiers/prognostic factors are measured and correctly modeled.
    Sections 4 and 11; the paper explicitly conditions on successful Step 1: 'Our analysis intentionally conditions on successful completion of the first transport step.'
  • ad hoc to paper Shared prognostic factor assumption (SPFA): the baseline prognostic function m(x) is common to all treatments in Eq. (A1).
    Appendix A, Eq. (A1); required for the X-dependence to cancel in η_B(x) − η_C(x). The paper notes this is 'standard' but does not test it.
  • domain assumption Shared effect modifier assumption (SEMA): the same φ(x) applies to B and C relative to A on the g-scale.
    Section 5; the central PAIC assumption, but the paper shows it is not sufficient for non-collapsible marginal measures.
  • ad hoc to paper Scale alignment: h∘g^{-1} = I on the relevant range, i.e., the effect measure operates on the linear predictor scale.
    Propositions A1/A2 and Section 6.3; an analytical condition required for direct transportability, not an empirical fact.

pith-pipeline@v1.3.0-alltime-deepseek · 30698 in / 16698 out tokens · 137787 ms · 2026-08-02T22:21:09.831206+00:00 · methodology

0 comments
read the original abstract

Population-adjusted indirect comparisons (PAICs) are widely used to synthesize evidence when randomized controlled trials enroll different patient populations and head-to-head comparisons are unavailable. Although PAICs adjust for observed population differences across trials, adjustment alone does not ensure transportability of estimated effects to decision-relevant populations for health technology assessment (HTA). We examine and formalize transportability in PAICs from an estimand-based perspective. We distinguish conditional and marginal treatment effect estimands and show how transportability depends on effect modification, collapsibility, and alignment between the scale of effect modification and the effect measure. Using illustrative examples, we demonstrate that even when effect modifiers are shared across treatments, marginal effects are generally population-dependent for commonly used non-collapsible measures, including hazard ratios and odds ratios. Conversely, collapsible and conditional effects defined on the linear predictor scale exhibit more favorable transportability properties. We further show that pairwise PAIC approaches typically identify effects defined in the comparator population and that applying these estimates to other populations entails an additional, often implicit, transport step requiring further assumptions. This has direct implications for HTA, where PAIC-derived effects are routinely applied within cost-effectiveness and decision models defined for different target populations. Our results clarify when applying PAIC-derived treatment effects to desired target populations is justified, when doing so requires additional assumptions, and when results should instead be interpreted as population-specific rather than decision-relevant, supporting more transparent and principled use of indirect evidence in HTA and related decision-making contexts.

Figures

Figures reproduced from arXiv: 2602.17041 by Conor Chandler, Jack Ishak.

Figure 1
Figure 1. Figure 1: Example Network for Anchored PAIC Involving Two Studies Although often described as a single adjustment, pairwise MAICs and STCs involve a two-step transport process, each relying on distinct transportability assumptions. Step 1: Conditional transport to the comparator population: In the first step, the treatment effect for 𝐵 vs. 𝐴, Δ𝐵𝐴, is conditionally transported from the index to the comparator study p… view at source ↗
Figure 2
Figure 2. Figure 2: Two-step Process to Transporting Effects in Pairwise MAICs and STCs [PITH_FULL_IMAGE:figures/full_fig_p009_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Decision Framework for Determining When Unadjusted NMAs Identify a Transportable Treatment Effect Estimand and When PAICs Are Required [PITH_FULL_IMAGE:figures/full_fig_p013_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Framework for Selecting PAIC Methods and Assessing Transportability of Treatment Effects Under Estimand Choice, Collapsibility, and SEMA [PITH_FULL_IMAGE:figures/full_fig_p013_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: displays the bias incurred when directly transporting marginal and population-average mean differences for 𝐵 vs. 𝐶 from the comparator population (identified in Step 1 of an MAIC/STC) to target populations with differing covariate distributions (Step 2). In the linear setting, population-average conditional and marginal mean differences are mathematically equivalent (i.e., direct collapsibility), and thus … view at source ↗
Figure 6
Figure 6. Figure 6: displays the bias incurred when directly transporting conditional and marginal log odds ratios for 𝐵 vs. 𝐶 from the comparator population to target populations with differing covariate distributions. For the conditional log odds ratio (left panel), the general pattern mirrors that observed for mean differences: when SEMA holds, the conditional log odds ratio for 𝐵 vs. 𝐶 is invariant across populations, res… view at source ↗
Figure 7
Figure 7. Figure 7: displays the bias incurred when directly transporting RMST-based contrasts from the comparator population to target populations with differing covariate distributions. Because RMST difference is a directly collapsible estimand, the population-average conditional and marginal RMST differences coincide within each population. However, despite being directly collapsible—analogous to mean differences from line… view at source ↗

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

80 extracted references · 39 canonical work pages

  1. [1]

    Mean difference, estimated via linear regression

  2. [2]

    Log odds ratio, estimated via logistic regression

  3. [3]

    Log risk ratio, estimated via log-binomial regression

  4. [4]

    Difference in restricted mean survival time (RMST), estimated using Weibull regression 15

  5. [5]

    This corresponds to the type of outcome regression model commonly estimated in STC and ML-NMR.𝑋was centered at the mean of the comparator population

    Log ratio of RMST, also estimated using Weibull regression For each analysis, we specified a regression model characterizing the true relative effects of𝐵vs.𝐴 and𝐶vs.𝐴, adjusting fora single covariate𝑋thatis both an effectmodifier and prognosticfactor (i.e., the true outcome model).𝑋was uniformly distributed with mean𝜇𝑋(𝑃) (which is specific to a given po...

    2025

  6. [7]

    Illustrative Examples of Two-step Transportability in MAICs/STCs In this section, we use illustrative simulations to evaluate the second step in the two-step transport process often implicit in MAICs and STCs—namely, the application of an active-to-active indirect comparisonΔ 𝐵𝐶(𝐴𝐶) , identified in the comparator population via conditional transport (Step...

  7. [8]

    Summary of Requirements for Direct Transportability BuildingontheillustrativeexamplespresentedinSection7,Table1summarizesthemathematicalprop- erties of common effect measures in PAICs, with a focus on the requirements for direct transportability ofΔ 𝐵𝐶. It presents 14 effect measures, including the five effect measures featured in the earlier illus- trati...

  8. [9]

    Extensions of Transportability in PAICs 9.1. Extension from Pairwise to Multi-arm Comparisons Theprecedingsectionsfocusontransportabilityinthebinarytreatmentsetting(𝐵vs.𝐴).Theseconcepts ofdirectandconditionaltransportabilityextendnaturallytotrialsandevidencenetworksinvolvingmore than two treatments, denoted by the setT∈{𝐴, 𝐵, 𝐶, 𝐷, ...}. In this setting, ...

    2025

  9. [10]

    This population dependence helps explain why MAICs or STCs conducted by different sponsors mayleadtodifferingresultsorconclusions

    Implications for PAICs and HTA Theresultsofthisworkhaveseveralimplicationsfortheinterpretationandapplicationofrelativetreat- menteffectsinHTA,acrossarangeofevidencesynthesismethods,includingPAICs.Incommonlyused MAIC and STC analyses targeting marginal estimands on non-collapsible effect scales, the estimated active-to-activeeffectisgenerallydefinedintheco...

  10. [11]

    Concluding Remarks This paper examines how relative treatment effects from PAICs are applied outside the populations in whichtheyareestimated.Inpractice,pairwisePAICsoftenidentifyanactive-to-activeeffectdefinedin the comparator trial population, yet this estimate is subsequently applied to an index trial or decision- modelpopulationwithdifferentbaselineri...

  11. [12]

    2021;7(1):1

    References 1.WaleJL,ThomasS,HamerlijnckD,HollanderR.Patientsandpublicareimportantstakeholdersin healthtechnologyassessmentbutthelevelofinvolvementislow-acalltoaction.ResInvolvEngagem. 2021;7(1):1. doi:10.1186/s40900-020-00248-9

    work page doi:10.1186/s40900-020-00248-9 2021

  12. [13]

    Real World Data in Health Technology Assessment of Complex Health Technologies.Front Pharmacol

    Hogervorst MA, Ponten J, Vreman RA, et al. Real World Data in Health Technology Assessment of Complex Health Technologies.Front Pharmacol. 2022;13:837302. doi:10.3389/fphar.2022.837302 24Chandler et al

    arXiv 2022

  13. [14]

    Use of Real-World Evidence in Health Technology Reassessments Across 6 Health Technology Assessment Agencies.Value Health

    Jaksa A, Arena PJ, Hanisch M, Marsico M. Use of Real-World Evidence in Health Technology Reassessments Across 6 Health Technology Assessment Agencies.Value Health. 2025;28(6):898-906. doi:10.1016/j.jval.2025.02.012 4.HaritonE,LocascioJJ.Randomisedcontrolledtrials-thegoldstandardforeffectivenessresearch: Study design: randomised controlled trials.BJOG. 201...

    arXiv 2025

  14. [15]

    Factors that can affect the external validity of randomised controlled trials.PLoS Clin Trials

    Rothwell PM. Factors that can affect the external validity of randomised controlled trials.PLoS Clin Trials. 2006;1(1):e9. doi:10.1371/journal.pctr.0010009 6.StecklerA,McLeroyKR.Theimportanceofexternalvalidity.AmJPublicHealth.2008;98(1):9-

    work page doi:10.1371/journal.pctr.0010009 2006

  15. [16]

    doi:10.2105/AJPH.2007.126847

    Pith/arXiv arXiv 2007

  16. [17]

    Guidance on Validity of Clinical Studies

    Member State Coordination Group on Health Technology Assessment (HTA CG). Guidance on Validity of Clinical Studies. 2024. Accessed 2025, https://health.ec.europa.eu/document/download/ 9f9dbfe4-078b-4959-9a07-df9167258772_en?filename=hta_clinical-studies-validity_guidance_en. pdf

    2024

  17. [18]

    Eligibility criteria of randomized controlled trials published in high-impact general medical journals: a systematic sampling review.JAMA

    Van Spall HG, Toren A, Kiss A, Fowler RA. Eligibility criteria of randomized controlled trials published in high-impact general medical journals: a systematic sampling review.JAMA. 2007;297(11):1233-1240. doi:10.1001/jama.297.11.1233

    doi:10.1001/jama.297.11.1233 2007

  18. [19]

    Chapman & Hall/CRC; 2020

    Hernán MA, Robins JM.Causal Inference: What If. Chapman & Hall/CRC; 2020

    2020

  19. [20]

    The use of propensity scores to assess the gen- eralizability of results from randomized trials.Journal of the Royal Statistical Society: Series A

    Stuart EA, Cole SR, Bradshaw CP, Leaf PJ. The use of propensity scores to assess the gen- eralizability of results from randomized trials.Journal of the Royal Statistical Society: Series A. 2011;174(2):369-386. doi:10.1111/j.1467-985X.2010.00673.x

    Pith/arXiv arXiv 2011

  20. [21]

    Transporting Comparative Effectiveness Evidence Between Countries:ConsiderationsforHealthTechnologyAssessments.PharmacoEconomics.2024;42(2):165-

    Turner AJ, Sammon C, Latimer N. Transporting Comparative Effectiveness Evidence Between Countries:ConsiderationsforHealthTechnologyAssessments.PharmacoEconomics.2024;42(2):165-

    2024

  21. [22]

    Systematic review of applied transporta- bility and generalizability analyses: A landscape analysis.Ann Epidemiol

    Vuong Q, Metcalfe RK, Ling A, et al. Systematic review of applied transporta- bility and generalizability analyses: A landscape analysis.Ann Epidemiol. 2025;104:61-70. doi:10.1016/j.annepidem.2025.03.001 14.BareinboimE,PearlJ.Causalinferenceandthedata-fusionproblem.ProceedingsoftheNational Academy of Sciences. 2016;113(27):7345-7352. doi:10.1073/pnas.1510507113

    work page doi:10.1016/j.annepidem.2025.03.001 2025

  22. [23]

    Use of transportability methods for real-world evidence generation: a review of current applications.J Comp Eff Res

    Levy NS, Arena PJ, Jemielita T, et al. Use of transportability methods for real-world evidence generation: a review of current applications.J Comp Eff Res. 2024;13(11):e240064. doi:10.57264/cer- 2024-0064

    work page doi:10.57264/cer- 2024

  23. [24]

    Extending inferences from a randomized trial to a new target population.Stat Med

    Dahabreh IJ, Robertson SE, Steingrimsson JA, et al. Extending inferences from a randomized trial to a new target population.Stat Med. 2020;39(14):1999-2014. doi:10.1002/sim.8426

    doi:10.1002/sim.8426 2020

  24. [25]

    Transporting causal inferences: methods and assumptions.Epidemiology

    Dahabreh IJ, Robertson SE, Stuart EA, Hernan MA. Transporting causal inferences: methods and assumptions.Epidemiology. 2019;30(4):538-544. doi:10.1097/EDE.0000000000001030

    work page doi:10.1097/ede.0000000000001030 2019

  25. [26]

    M., Welton, N

    Remiro-Azócar A, Phillippo, D. M., Welton, N. J., Dias, S., Ades, A. E., Heath, A., & Baio, G. Marginal and conditional summary measures: Transportability and compatibility across studies.Wiley StatsRef: Statistics Reference Online. 2025

    2025

  26. [27]

    A Framework for Reliable, Transparent, and Repro- ducible Population-Adjusted Indirect Comparisons.Pharmacoeconomics

    Ishak KJ, Chandler C, Liu FF, Klijn S. A Framework for Reliable, Transparent, and Repro- ducible Population-Adjusted Indirect Comparisons.Pharmacoeconomics. 2025;doi:10.1007/s40273- 025-01503-1

    work page doi:10.1007/s40273- 2025

  27. [28]

    The Acceptance of Indirect Treatment Comparison MethodsinOncologybyHealthTechnologyAssessmentAgenciesinEngland,France,Germany,Italy, and Spain.Pharmacoecon Open

    Macabeo B, Rotrou T, Millier A, et al. The Acceptance of Indirect Treatment Comparison MethodsinOncologybyHealthTechnologyAssessmentAgenciesinEngland,France,Germany,Italy, and Spain.Pharmacoecon Open. 2024;8(1):5-18. doi:10.1007/s41669-023-00455-6 25

    work page doi:10.1007/s41669-023-00455-6 2024

  28. [29]

    The results of direct and indirect treat- ment comparisons in meta-analysis of randomized controlled trials.Journal of Clinical Epidemiology

    Bucher HC, Guyatt GH, Griffith LE, Walter SD. The results of direct and indirect treat- ment comparisons in meta-analysis of randomized controlled trials.Journal of Clinical Epidemiology. 1997;50(6):683-691. doi:10.1016/S0895-4356(97)00049-8

    work page doi:10.1016/s0895-4356(97)00049-8 1997

  29. [30]

    NICE DSU Technical Support Document 2: A generalised linear modelling framework for pair-wise and network meta-analysis of randomised controlled trials

    Dias S, Welton NJ, Sutton AJ, AEA. NICE DSU Technical Support Document 2: A generalised linear modelling framework for pair-wise and network meta-analysis of randomised controlled trials. 2011; 23.DiasS,SuttonAJ,AdesAE,WeltonNJ.Evidencesynthesisfordecisionmaking2:ageneralized linear modeling framework for pairwise and network meta-analysis of randomized c...

    doi:10.1177/0272989x12458724 2011

  30. [31]

    Network meta-analysis for indirect treatment comparisons.Stat Med

    Lumley T. Network meta-analysis for indirect treatment comparisons.Stat Med. 2002;21(16):2313-2324. doi:10.1002/sim.1201 25.HoaglinDC,HawkinsN,JansenJP,etal.Conductingindirect-treatment-comparisonandnetwork- meta-analysis studies: report of the ISPOR Task Force on Indirect Treatment Comparisons Good Research Practices: part 2.Value Health. 2011;14(4):429-...

    work page doi:10.1002/sim.1201 2002

  31. [32]

    Twenty years of network meta-analysis: Continuing controversies and recent developments.Res Synth Methods

    Ades AE, Welton NJ, Dias S, et al. Twenty years of network meta-analysis: Continuing controversies and recent developments.Res Synth Methods. 2024;doi:10.1002/jrsm.1700

    doi:10.1002/jrsm.1700 2024

  32. [33]

    Simulation and matching-based approaches for indirect comparisonoftreatments.Pharmacoeconomics.2015;33(6):537-549.doi:10.1007/s40273-015-0271-1

    Ishak KJ, Proskorovsky I, Benedict A. Simulation and matching-based approaches for indirect comparisonoftreatments.Pharmacoeconomics.2015;33(6):537-549.doi:10.1007/s40273-015-0271-1

    work page doi:10.1007/s40273-015-0271-1 2015

  33. [34]

    Methods for population-adjusted indirect comparisons in health technology appraisal.Medical Decision Making

    Phillippo DM, Ades AE, Dias S, et al. Methods for population-adjusted indirect comparisons in health technology appraisal.Medical Decision Making. 2018;38(2):200-211. doi:10.1177/0272989X17725740 29.PhillippoDM,DiasS,ElsadaA,etal.PopulationAdjustmentMethodsforIndirectComparisons: A Review of National Institute for Health and Care Excellence Technology App...

    work page doi:10.1177/0272989x17725740 2018

  34. [35]

    No head-to-head trial? simulate the missing arms.Pharmacoeconomics

    Caro JJ, Ishak KJ. No head-to-head trial? simulate the missing arms.Pharmacoeconomics. 2010;28(10):957-967. doi:10.2165/11537420-000000000-00000

    doi:10.2165/11537420-000000000-00000 2010

  35. [36]

    Matching-adjusted indirect comparisons: a new tool for timely comparative effectiveness research.Value Health

    Signorovitch JE, Sikirica V, Erder MH, et al. Matching-adjusted indirect comparisons: a new tool for timely comparative effectiveness research.Value Health. 2012;15(6):940-947. doi:10.1016/j.jval.2012.05.004

    work page doi:10.1016/j.jval.2012.05.004 2012

  36. [37]

    Signorovitch JE, Wu EQ, Yu AP, et al. Comparative effectiveness without head-to-head trials: a method for matching-adjusted indirect comparisons applied to psoriasis treatment with adalimumab or etanercept.Pharmacoeconomics. 2010;28(10):935-945. doi:10.2165/11538370-000000000-00000

    work page doi:10.2165/11538370-000000000-00000 2010

  37. [38]

    Methods for Indirect Treatment Compari- son: Results from a Systematic Literature Review.J Mark Access Health Policy

    Macabeo B, Quenechdu A, Aballea S, et al. Methods for Indirect Treatment Compari- son: Results from a Systematic Literature Review.J Mark Access Health Policy. 2024;12(2):58-80. doi:10.3390/jmahp12020006 34.PhillippoDM,DiasS,AdesAE,WeltonNJ.Assessingtheperformanceofpopulationadjustment methods for anchored indirect comparisons: A simulation study.Stat Med...

    work page doi:10.3390/jmahp12020006 2024

  38. [39]

    Transportability of model-based estimands in evidence synthesis.Stat Med

    Remiro-Azocar A. Transportability of model-based estimands in evidence synthesis.Stat Med. 2024;43(22):4217-4249. doi:10.1002/sim.10111

    work page doi:10.1002/sim.10111 2024

  39. [40]

    Addendum on estimands and sensitivity analysis in clinical trials to the guideline on statistical principles for clinical trials E9(R1)

    International Council for Harmonisation of Technical Requirements for Pharmaceuticals for Human Use (ICH). Addendum on estimands and sensitivity analysis in clinical trials to the guideline on statistical principles for clinical trials E9(R1). 2019

    2019

  40. [41]

    Some considerations on target estimands for health technology assessment

    Remiro-Azocar A. Some considerations on target estimands for health technology assessment. Stat Med. 2022;41(28):5592-5596. doi:10.1002/sim.9566

    work page doi:10.1002/sim.9566 2022

  41. [42]

    Target estimands for population-adjusted indirect comparisons.Stat Med

    Remiro-Azocar A. Target estimands for population-adjusted indirect comparisons.Stat Med. 2022;41(28):5558-5569. doi:10.1002/sim.9413 39.PearlJ,BareinboimE.ExternalValidityandTransportability:AFormalApproach.International Statistical Institute Proceedings of the 58th World Statistical Congress (Paper 450268). 2011; 26Chandler et al

    work page doi:10.1002/sim.9413 2022

  42. [43]

    External Validity: From Do-Calculus to Transportability Across Populations.Statistical Science

    Pearl J, Bareinboim E. External Validity: From Do-Calculus to Transportability Across Populations.Statistical Science. 2014;29(4):579-595. doi:10.1214/14-STS486

    doi:10.1214/14-sts486 2014

  43. [44]

    Estimating causal effects of treatments in randomized and nonrandomized studies

    Rubin DB. Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of Educational Psychology. 1974;66:688–701

    1974

  44. [45]

    Statistics and causal inference.Journal of the American Statistical Association

    Holland PW. Statistics and causal inference.Journal of the American Statistical Association. 1986;81:945–970

    1986

  45. [46]

    Causal Inference in Oncology: Why, What, How and When.Clin Oncol (R Coll Radiol)

    van Amsterdam WAC, Elias S, Ranganath R. Causal Inference in Oncology: Why, What, How and When.Clin Oncol (R Coll Radiol). 2025;38:103616. doi:10.1016/j.clon.2024.07.002

    work page doi:10.1016/j.clon.2024.07.002 2025

  46. [47]

    Commentary: On Causes, Causal Inference, and Potential Outcomes.Int J Epidemiol

    VanderWeele TJ. Commentary: On Causes, Causal Inference, and Potential Outcomes.Int J Epidemiol. 2016;45(6):1809-1816. doi:10.1093/ije/dyw230 45.WestreichD,EdwardsJK,ColeSR,etal.Imputationapproachesforpotentialoutcomesincausal inference.Int J Epidemiol. 2015;44(5):1731-1737. doi:10.1093/ije/dyv135

    work page doi:10.1093/ije/dyw230 2016

  47. [48]

    Phillippo DM R-AA, Heath A, Baio G, Dias S, Ades AE, Welton NJ. Effect modification and non-collapsibility together may lead to conflicting treatment decisions: A review of marginal and conditional estimands and recommendations for decision-making.Research Synthesis Methods. 2025;16(2):323–349

    2025

  48. [49]

    Study Designs for Extending Causal Infer- ences From a Randomized Trial to a Target Population.Am J Epidemiol

    Dahabreh IJ, Haneuse SJA, Robins JM, et al. Study Designs for Extending Causal Infer- ences From a Randomized Trial to a Target Population.Am J Epidemiol. 2021;190(8):1632-1642. doi:10.1093/aje/kwaa270

    work page doi:10.1093/aje/kwaa270 2021

  49. [50]

    Implementation of G-computation on a simulated data set: demonstration of a causal inference technique.Am J Epidemiol

    Snowden JM, Rose S, Mortimer KM. Implementation of G-computation on a simulated data set: demonstration of a causal inference technique.Am J Epidemiol. 2011;173(7):731-738. doi:10.1093/aje/kwq472

    work page doi:10.1093/aje/kwq472 2011

  50. [51]

    Parametric G-computation for compatible indirect treat- ment comparisons with limited individual patient data.Res Synth Methods

    Remiro-Azocar A, Heath A, Baio G. Parametric G-computation for compatible indirect treat- ment comparisons with limited individual patient data.Res Synth Methods. 2022;13(6):716-744. doi:10.1002/jrsm.1565

    work page doi:10.1002/jrsm.1565 2022

  51. [52]

    Model-based standardization using multiple imputation

    Remiro-Azocar A, Heath A, Baio G. Model-based standardization using multiple imputation. BMC Med Res Methodol. 2024;24(1):32. doi:10.1186/s12874-024-02157-x

    work page doi:10.1186/s12874-024-02157-x 2024

  52. [53]

    Transportability of Trial Results Using Inverse Odds of Sampling Weights.Am J Epidemiol

    Westreich D, Edwards JK, Lesko CR, et al. Transportability of Trial Results Using Inverse Odds of Sampling Weights.Am J Epidemiol. 2017;186(8):1010-1014. doi:10.1093/aje/kwx164

    doi:10.1093/aje/kwx164 2017

  53. [54]

    Transporting observational study results to a target populationofinterestusinginverseoddsofparticipationweighting.PLoSOne.2022;17(12):e0278842

    Ling AY, Jreich R, Montez-Rath ME, et al. Transporting observational study results to a target populationofinterestusinginverseoddsofparticipationweighting.PLoSOne.2022;17(12):e0278842. doi:10.1371/journal.pone.0278842

    work page doi:10.1371/journal.pone.0278842 2022

  54. [55]

    Assessing the generalizability of randomized trial results to target populations.Prev Sci

    Stuart EA, Bradshaw CP, Leaf PJ. Assessing the generalizability of randomized trial results to target populations.Prev Sci. 2015;16(3):475-485. doi:10.1007/s11121-014-0513-z

    doi:10.1007/s11121-014-0513-z 2015

  55. [56]

    Doubly robust estimation of causal effects.Am J Epidemiol

    Funk MJ, Westreich D, Wiesen C, et al. Doubly robust estimation of causal effects.Am J Epidemiol. 2011;173(7):761-767. doi:10.1093/aje/kwq439

    work page doi:10.1093/aje/kwq439 2011

  56. [57]

    Doubly robust estimators for generalizing treatment effects on survival outcomesfromrandomizedcontrolledtrialstoatargetpopulation.JCausalInference.2022;10(1):415-

    Lee D, Yang S, Wang X. Doubly robust estimators for generalizing treatment effects on survival outcomesfromrandomizedcontrolledtrialstoatargetpopulation.JCausalInference.2022;10(1):415-

    2022

  57. [58]

    Practical Guideline for Quantitative Evidence Synthesis: Direct and Indirect Comparisons

    Member State Coordination Group on Health Technology Assessment (HTA CG). Practical Guideline for Quantitative Evidence Synthesis: Direct and Indirect Comparisons. 2024. Accessed 2025, https://health.ec.europa.eu/document/download/1f6b8a70-5ce0-404e-9066-120dc9a8df75_en? filename=hta_practical-guideline_direct-and-indirect-comparisons_en.pdf 27

    2024

  58. [59]

    Doubly Robust Estimation of Causal Effect: Upping the Odds of Getting the Right Answers.Circ Cardiovasc Qual Outcomes

    Li X, Shen C. Doubly Robust Estimation of Causal Effect: Upping the Odds of Getting the Right Answers.Circ Cardiovasc Qual Outcomes. 2020;13(1):e006065. doi:10.1161/CIRCOUTCOMES.119.006065 57.PhillippoDM,AdesAE,DiasS,etal.NICEDSUTechnicalSupportDocument18:Methodsfor population-adjusted indirect comparisons in submissions to NICE. 2016

    work page doi:10.1161/circoutcomes.119.006065 2020

  59. [60]

    Risk ratio, odds ratio, risk difference

    Bénédicte Colnet JJ, Gaël Varoquaux, Erwan Scornet. Risk ratio, odds ratio, risk difference... Which causal measure is easier to generalize?arXiv:230316008. 2024

    2024

  60. [61]

    Making apples from oranges: Comparing noncollapsible effect estimatorsandtheirstandarderrorsafteradjustmentfordifferentcovariatesets.BiomJ.2021;63(3):528-

    Daniel R, Zhang J, Farewell D. Making apples from oranges: Comparing noncollapsible effect estimatorsandtheirstandarderrorsafteradjustmentfordifferentcovariatesets.BiomJ.2021;63(3):528-

    2021

  61. [62]

    Uncertain about uncertainty in matching-adjusted indirect com- parisons? A simulation study to compare methods for variance estimation.Res Synth Methods

    Chandler CO, Proskorovsky I. Uncertain about uncertainty in matching-adjusted indirect com- parisons? A simulation study to compare methods for variance estimation.Res Synth Methods. 2024;15(6):1094-1110. doi:10.1002/jrsm.1759

    work page doi:10.1002/jrsm.1759 2024

  62. [63]

    The Effects of Model Misspecification in Unanchored Matching-AdjustedIndirectComparison:ResultsofaSimulationStudy.ValueHealth.2020;23(6):751-

    Hatswell AJ, Freemantle N, Baio G. The Effects of Model Misspecification in Unanchored Matching-AdjustedIndirectComparison:ResultsofaSimulationStudy.ValueHealth.2020;23(6):751-

    2020

  63. [64]

    Methods for population adjustment with limited access to individual patient data: A review and simulation study.Res Synth Methods

    Remiro-Azocar A, Heath A, Baio G. Methods for population adjustment with limited access to individual patient data: A review and simulation study.Res Synth Methods. 2021;12(6):750-775. doi:10.1002/jrsm.1511

    work page doi:10.1002/jrsm.1511 2021

  64. [65]

    Advancing unanchored simulated treatment com- parisons: A novel implementation and simulation study.Res Synth Methods

    Ren S, Ren S, Welton NJ, Strong M. Advancing unanchored simulated treatment com- parisons: A novel implementation and simulation study.Res Synth Methods. 2024;15(4):657-670. doi:10.1002/jrsm.1718

    work page doi:10.1002/jrsm.1718 2024

  65. [66]

    Four alternative methodologies for simulated treatment comparison: How could the use of simulation be re-invigorated?Res Synth Methods

    Zhang L, Bujkiewicz S, Jackson D. Four alternative methodologies for simulated treatment comparison: How could the use of simulation be re-invigorated?Res Synth Methods. 2024;15(2):227-

    2024

  66. [67]

    strmst2 and strmst2pw: New commands to compare survival curves using the restricted mean survival time.The Stata Journal

    Cronin A, Tian L, Uno H. strmst2 and strmst2pw: New commands to compare survival curves using the restricted mean survival time.The Stata Journal. 2016;16(3):702–716. 68.ZhongY,ZhaoO,ZhangB,YaoB.Adjustingforcovariatesinanalysisbasedonrestrictedmean survival times.Pharm Stat. 2022;21(1):38-54. doi:10.1002/pst.2151

    work page doi:10.1002/pst.2151 2016

  67. [68]

    Is the Use of Unanchored Matching-Adjusted Indirect Comparison AlwaysSuperiortoNaiveIndirectComparisononSurvivalOutcomes?ASimulationStudy.ApplHealth Econ Health Policy

    Liu Y, He X, Liu J, Wu J. Is the Use of Unanchored Matching-Adjusted Indirect Comparison AlwaysSuperiortoNaiveIndirectComparisononSurvivalOutcomes?ASimulationStudy.ApplHealth Econ Health Policy. 2025;23(4):693-704. doi:10.1007/s40258-025-00952-1

    work page doi:10.1007/s40258-025-00952-1 2025

  68. [69]

    Adjusted restricted mean survival times in observational studies.Stat Med

    Conner SC, Sullivan LM, Benjamin EJ, et al. Adjusted restricted mean survival times in observational studies.Stat Med. 2019;38(20):3832-3860. doi:10.1002/sim.8206

    work page doi:10.1002/sim.8206 2019

  69. [70]

    On the logic of collapsibility for causal effect measures.Biom J

    Didelez V, Stensrud MJ. On the logic of collapsibility for causal effect measures.Biom J. 2022;64(2):235-242. doi:10.1002/bimj.202000305 71.LuWE,NiA.Causaleffectestimationonrestrictedmeansurvivaltimeundercase-cohortdesign via propensity score stratification.Lifetime Data Anal. 2025;31(4):898-931. doi:10.1007/s10985-025- 09667-w 72.NiA,LinZ,LuB.StratifiedR...

    work page doi:10.1002/bimj.202000305 2022

  70. [73]

    The hazards of hazard ratios.Epidemiology

    Hernan MA. The hazards of hazard ratios.Epidemiology. 2010;21(1):13-15. doi:10.1097/EDE.0b013e3181c1ea43

    doi:10.1097/ede.0b013e3181c1ea43 2010

  71. [74]

    On the collapsibility of measures of effect in the counter- factual causal framework.Emerg Themes Epidemiol

    Huitfeldt A, Stensrud MJ, Suzuki E. On the collapsibility of measures of effect in the counter- factual causal framework.Emerg Themes Epidemiol. 2019;16:1. doi:10.1186/s12982-018-0083-9 75.SjolanderA,DahlqwistE,ZetterqvistJ.ANoteontheNoncollapsibilityofRateDifferencesand Rate Ratios.Epidemiology. 2016;27(3):356-359. doi:10.1097/EDE.0000000000000433 76.Phi...

    work page doi:10.1186/s12982-018-0083-9 2019

  72. [77]

    Anchors Away: Navigating Unanchored Indirect Comparisons With Multilevel Unanchored Meta-Regression.Value in Health

    Chandler C, Ishak J. Anchors Away: Navigating Unanchored Indirect Comparisons With Multilevel Unanchored Meta-Regression.Value in Health. 2025;28(12)(1):S498. 28Chandler et al

    2025

  73. [78]

    C., Abrahami, D., Chen, Y., Chu, H

    Jiang Z, Liu, J., Alemayehu, D., Cappelleri, J. C., Abrahami, D., Chen, Y., Chu, H. A criti- cal assessment of matching-adjusted indirect comparisons in relation to target populations.Research Synthesis Methods. 2025;16(3):569–574

    2025

  74. [79]

    Reframing Population-Adjusted Indirect Comparisons as a Trans- portability Problem: An Estimand-Based Perspective and Implications for Health Technology Assessment

    Faria R, Hernandez Alava M, Manca A, AJ W. NICE DSU Technical Support Document 17: The use of observational data to inform estimates of treatment effectiveness in technology appraisal: methods for comparative individual patient data. 2015 Acknowledgments.TheauthorsthankCarolineCole,RuthSharf,andRichardLeasonforeditorialandgraphicaldesignsupport on this ma...

    2015

  75. [176]

    2018;23(1):17-19

    doi:10.1007/s40273-023-01323-1 12.MuradMH,KatabiA,BenkhadraR,MontoriVM.Externalvalidity,generalisability,applicability and directness: a brief primer.BMJ Evid Based Med. 2018;23(1):17-19. doi:10.1136/ebmed-2017- 110800

    work page doi:10.1007/s40273-023-01323-1 2018

  76. [241]

    doi:10.1002/jrsm.1681

    work page doi:10.1002/jrsm.1681

  77. [440]

    doi:10.1515/jci-2022-0004

    work page doi:10.1515/jci-2022-0004 2022

  78. [557]

    doi:10.1002/bimj.201900297

    doi:10.1002/bimj.201900297

  79. [759]

    doi:10.1016/j.jval.2020.02.008

    work page doi:10.1016/j.jval.2020.02.008 2020

  80. [1210]

    doi:10.1111/rssa.12579

    work page doi:10.1111/rssa.12579