{"id":"4126b9ad-bd41-410f-b51d-2d09fe01442d","arxiv_id":"2512.17576","paper_version":2,"verdict":"UNVERDICTED","confidence":"HIGH","novelty_score":1.0,"correctness_risk":"low","formal_verification":"none","parameter_count":0,"one_line_summary":"A survey arguing that empirical panel work should replace strict exogeneity with sequential exogeneity, and reviewing what is identified when dynamics and effect heterogeneity coexist.","lead":"This survey argues that strict exogeneity—the assumption that future covariates cannot be influenced by past outcomes—is often implausible in panel data, and reviews methods built on the weaker sequential exogeneity assumption. Applied researchers and methodologists get a compact map of feedback bias, heterogeneous-coefficient identifiability, nonlinear models, and open network problems.","discovery_kind":"review","skeptic_critique":{"model":"deepseek-v4-flash","headline":"No significant objection identified: the survey's advocacy is appropriately hedged, and its central limitations are stated in the text.","rationale":"The reader identifies SeqE as the weakest assumption, and that is indeed the main limitation of the paper's toolkit. However, the paper states this limitation explicitly in Section 2.1 and does not claim that SeqE is a universal fix; it argues that SeqE is a meaningfully less restrictive assumption than SE and surveys methods that work under it. That argument is internally consistent and supported by published classic results. The main residual risk is that the modern characterization of point-identified weighted averages in §7.2 is drawn from an unpublished manuscript and is presented without proof. But the paper's headline conclusion that ATE/ATT are generally not identified under heterogeneity and feedback is already established by Chamberlain (2022), which is published. Thus the unpublished material is not load-bearing for the central claim. The reader's UNVERDICTED verdict is appropriate because the paper is a survey rather than a novel research claim; I see no reason to move it toward accept or reject. The concrete test proposed would provide a useful independent check of the one nonstandard formal result that the survey relies on, but it is a verification step rather than evidence of a current flaw.","tokens_in":27024,"tokens_out":8291,"duration_ms":94223,"concrete_test":"For §7.2, enumerate all binary sequences (X_i1, X_i2, X_i3) and all possible weight vectors c, and verify by symbolic linear algebra that c is point-identified iff it lies in the span of {(X_it − X_iT) φ_t(X_i^t)} satisfying E[φ_t(X_i^t)] = 0. Repeat for T = 2 and T = 3. This checks the unpublished necessity claim in Bonhomme (2025); if a counterexample emerges, the characterization and the 'identified weighted averages only' conclusion would need qualification, though Chamberlain's negative result for T = 2 would remain.","verdict_should_be":"UNCHANGED","load_bearing_attack":"The paper is a survey/position piece rather than a new estimator or theorem. Its central claim—that credible empirical work should relax strict exogeneity—requires only that strict exogeneity is often implausible and that useful alternatives exist. Both are supported: the classic Arellano–Bond/Blundell–Bond results and Chamberlain (2022) are published, and feedback bias in fixed-effects/event-study designs is standard. The most serious caveat is the one the reader flags: SeqE itself rules out simultaneity and serially correlated time-varying confounders (Section 2.1), so replacing SE with SeqE is not sufficient for credibility in all applications. But the paper says this explicitly and positions SeqE as a less restrictive starting point, not as a universal solution. The modern point-identification characterization in §7.2 relies on Bonhomme (2025, unpublished), but Chamberlain's negative result already establishes the key 'not ATE/ATT' conclusion for the central simple model, so the unpublished material is not load-bearing for the main message. I therefore do not find a concern that would change the verdict.","agreement_with_reader":"partial"},"referee_report":{"model":"deepseek-v4-flash","summary":"The paper is a survey and position piece arguing that strict exogeneity (SE) is too restrictive as a default assumption in panel data and difference-in-differences practice, and that sequential exogeneity (SeqE)—which allows feedback from past outcomes to future covariates—should be adopted as a less restrictive starting point. It defines SE and SeqE, illustrates the bias of OLS, fixed-effects, and event-study estimators under feedback, and cautions against relying on pre-trend checks. It then reviews classic linear dynamic panel methods (Arellano-Bond, Blundell-Bond, QML, bias correction), and moves to heterogeneous coefficients: Chamberlain's negative result, point-identified weighted averages, best identified approximations, Lee bounds, and scalar-heterogeneity/large-T fixes. The final sections cover nonlinear likelihood models with feedback, linear-programming characterizations of identified sets, restricted feedback processes, and network extensions.","tokens_in":27317,"tokens_out":9869,"duration_ms":103566,"significance":"The paper's main value is synthetic and pedagogical. It draws together classic and recent results on feedback in panel data and presents them in a coherent framework. The three-period pre-trends counterexample in Section 5.2 is particularly effective: it gives a transparent case where pre-trends are parallel yet the DID estimand is biased. The review of Section 7 is also useful, especially the linear-weight characterization of point-identified averages and the contrast between unconditional and conditional sequential exogeneity. The paper is appropriately hedged: Section 2.1 explicitly acknowledges that SeqE rules out simultaneity and serially correlated time-varying confounders, so the advocacy is not overstated. If the survey is accepted as a position piece, it can help redirect applied practice toward dynamic feedback and partial identification rather than strict exogeneity. The main caveat is that several technical claims are deferred to the author's unpublished companion papers, but these are not load-bearing for the paper's central message.","major_comments":[],"minor_comments":[{"comment":"In the bias decomposition after Eq. (1), the text defines term (I) as (X1X1'+X2X2')^{-1} X1 U1, but then writes E[(I)] = E[(X1X1'+X2X2')^{-1} X2 E[U1|X1,X2]]. The X2 outside the bracket should be X1. The conclusion that the term is generally nonzero under feedback is unaffected, but the displayed equality is false as written.","section":"Section 3.1"},{"comment":"The completeness claim that, absent functions φ_t satisfying (39)–(40), the identified set for μ is the whole real line is stated without proof and attributed to Bonhomme (2025, unpublished). Since this is a survey, the attribution is acceptable, but the 'if and only if' and 'identified set equals R' claims are strong. Please add a short proof sketch or an explicit theorem number from the companion paper so the reader can verify the result.","section":"Section 7.2"},{"comment":"In model (58), the time index is written as t=1,...,N; presumably this should be t=1,...,T. In addition, after (59), the notation 'X^t denotes the set of all X_{ijs} for ... s ≤ t' would be clearer if written as X^t = {X_{ijs}: s ≤ t}.","section":"Section 9"},{"comment":"The sentence 'there is no reason at all for λ1=λ0 to imply that the bias in (23) is zero' is correct but could confuse readers. With λ1=λ0, the pre-trend condition (22) holds exactly, while the bias (23) is generally nonzero whenever λ1≠0 and the conditional means of Z_i differ across groups. A brief clarification would help.","section":"Section 5.2"},{"comment":"Section 2.1: 'counfounders' should be 'confounders'. Figure 3 caption: 'Identifed region' should be 'Identified region'. Section 8.1: 'Woutersen (2000) derive' should be 'Woutersen (2000) derives'.","section":"Minor typos"}],"recommendation":"minor_revision","confidential_remarks":"This is a survey/position piece by an author who is also the author of several of the methods being reviewed. The manuscript is candid about limitations, and I find no load-bearing technical error. The main editorial consideration is the reliance on the author's unpublished companion papers for the completeness claims in Section 7.2 and the FHR characterization in Section 8.2; this is common in the field, but the editor may want to confirm that the companion papers are publicly available before publication. The paper fits the journal's scope as a survey."},"author_rebuttal":null,"desk_editor":{"model":"deepseek-v4-flash","letter":"You should know two things up front. First, this is a review/position piece, not a new estimator or theorem. It argues that strict exogeneity in panel and did designs is often implausible and that sequential exogeneity should be the default starting point. That argument is not new, but the paper makes it cleanly and honestly. Second, the most modern material leans on the author's own unpublished working papers, but the core message does not depend on those: Chamberlain's negative result is published and the standard Arellano-Bond/Blundell-Bond machinery is textbook material.\n\nThe paper does a lot well. It defines strict versus sequential exogeneity carefully, spells out the feedback-bias mechanism, and shows clearly why TWFE and event-study estimates are inconsistent under SeqE. The three-period example where pre-trends are parallel yet the DID estimand is biased is a nice expository contribution—simple and effective. Section 7 gives a compact characterization of which weighted averages are point-identified under SeqE plus coefficient heterogeneity, and the Lee bounds are laid out correctly without getting lost in technicalities. The network discussion is brief but responsible.\n\nSoft spots are minor and mostly inherent to the genre. There is no new empirical evidence that strict exogeneity fails broadly; the case rests on examples and on the logical point that SE rules out feedback by construction. The unpublished working papers for the nonlinear parts mean a referee cannot fully verify those claims from this manuscript alone, but the main substantive conclusion—that average effects are generally not point-identified under SeqE and heterogeneity—already follows from the published Chamberlain result. Also, the paper itself acknowledges that SeqE still rules out simultaneity and serially correlated time-varying confounders (Section 2.1), so it does not oversell the assumption. That caveat is stated clearly, which I appreciate.\n\nThe citation pattern is fine. Self-citations are to working papers, but they are identified as such and the attribution is accurate. No invented entities, no hidden free parameters.\n\nWho gets value from this? Applied microeconomists who want an accessible map of dynamic panel methods and the modern heterogeneity-plus-feedback literature, and graduate students who need context before diving into technical papers. It is not for someone hunting for new results.\n\nMy recommendation: send it to peer review as a survey. It deserves a serious referee. If a journal wants a review article, this should be accepted after light-to-moderate revision. I would bring it to a reading group and would cite it when discussing sequential exogeneity.","headline":"A clear, well-written survey making the case that sequential exogeneity deserves to be the default in panel applications; no new results, but the synthesis and examples are valuable.","tokens_in":27741,"tokens_out":1755,"would_cite":true,"duration_ms":22867,"reading_group":"yes","serious_thinker":"yes","would_accept_peer_review":true},"rs_alignment":null,"lean_confirmation":null,"pith_extraction":{"msc":["62P20","91B82"],"pacs":[],"model":"deepseek-v4-flash","headline":"The paper argues that credible panel analysis requires replacing strict exogeneity with sequential exogeneity—a shift that makes standard two-way fixed-effects and difference-in-differences estimators biased and breaks point identification","keywords":["sequential exogeneity","strict exogeneity","feedback","panel data","difference-in-differences","heterogeneous treatment effects","identification","dynamic models"],"falsifier":"Simulate a two-period binary-treatment panel where the treatment depends on the lagged outcome shock, and verify that the two-way fixed-effects estimator deviates from the true ATT while the sequential-exogeneity-robust weighted average recovers it. Alternatively, re-examine a job-training evaluation with a randomized benchmark; if the sequential-exogeneity-based estimate does not move closer to the benchmark than the difference-in-differences estimate does, the framework's practical value is weakened.","tokens_in":26926,"feed_emoji":"📊","tokens_out":4675,"duration_ms":44896,"temperature":0.7,"pith_summary":"The paper argues that strict exogeneity—the assumption that current shocks are uncorrelated with all past and future covariates—is too strong for most empirical settings, since treatments and covariates typically respond to past outcomes. It proposes sequential exogeneity, which allows such feedback, as the more credible benchmark, and shows that standard two-way fixed effects and difference-in-differences estimators become biased and inconsistent in short panels when only sequential exogeneity holds. The paper further shows that, with coefficient heterogeneity, allowing feedback destroys point identification of average treatment effects on changers, so analysts must instead estimate identified weighted averages or construct bounds. Finally, it surveys methods for nonlinear and network models that remain valid under feedback. If true, this reasoning implies a shift in how applied researchers should specify and interpret panel data models.","feed_headline":"Past outcomes shape future treatments: allow feedback in panels","feed_subtitle":"Replacing strict exogeneity with sequential exogeneity exposes large biases in fixed-effects and DID estimators and forces a redefinition of","key_machinery":"The central object is the feedback process—the conditional density of current covariates given past outcomes and covariates—which strict exogeneity rules out and sequential exogeneity allows. The argument is carried by: (i) the sequential moment restrictions that lagged covariates satisfy when strict exogeneity fails, which underlie classic GMM and quasi-likelihood estimators; (ii) a linear characterization of point-identified weighted averages of heterogeneous coefficients, leading to a best identified approximation; (iii) moment inequalities that yield finite bounds under conditional sequential exogeneity; and (iv) feedback-and-heterogeneity-robust moment conditions in nonlinear models, wi","core_discovery":"The central claim is that credible empirical work requires meaningfully relaxing strict exogeneity assumptions, replacing them with sequential exogeneity under which current shocks are mean-independent of past and current covariates but may be correlated with future covariates. The paper demonstrates that, under sequential exogeneity, fixed-effects and difference-in-differences estimators have a bias of order 1/T in panel data, that pre-trend checks do not reveal this bias, and that in models with unrestricted coefficient heterogeneity average treatment effects on changers are not point-identified. It then characterizes the identified weighted averages and the bounds that remain available, a","pith_inferences":["A natural extension the paper leaves implicit: in designs with many periods, feedback bias shrinks as T grows, so combining short-T robust methods with long-T bias corrections could restore some of the point identification lost under heterogeneity.","The linear-programming characterization of identified sets suggests that computational inference approaches—e.g., checking whether a target parameter lies in the identified set—could be implemented with off-the-shelf LP solvers in empirical work.","The paper's logic implies that external instruments matter more than often acknowledged: because sequential exogeneity cannot handle simultaneity or serially correlated confounders, instruments external to the model remain necessary in those settings.","The framework invites a re-examination of published difference-in-differences studies to assess whether feedback is plausible from the institutional context, and to report sensitivity of conclusions to replacing strict exogeneity with sequential exogeneity."],"forward_implications":["Two-way fixed effects and event-study estimates should be interpreted as depending on strict exogeneity; under feedback they are biased by an amount that shrinks only like 1/T.","Pre-trend checks cannot establish strict exogeneity; parallel pre-trends can coexist with substantial feedback bias, so they should not be used as validation.","With heterogeneous treatment effects and feedback, the average effect on changers is not identified; researchers should target identified weighted averages or report partial-identification bounds.","Nonlinear panel models admit feedback-robust moment conditions in restricted classes (multiplicative, Poisson, proportional hazard), and their identified sets can be computed via linear programming.","Network models of worker-firm mobility need to relax the exogenous-mobility assumption to allow job changes to respond to past wage shocks; methods for this are at an early stage."],"fun_headline_variants":["Feedback in panels: pre-trends won't save fixed effects","Sequential exogeneity: panel estimators get bias 1/T","Why strict exogeneity fails: feedback in panel data","When outcomes affect treatments, panel estimates lie","Relaxing exogeneity: heterogenous effects not identified"],"cache_read_input_tokens":2304,"weakest_assumption_plain":"The whole toolkit hinges on sequential exogeneity being the right relaxation: it rules out simultaneity and serially correlated time-varying confounders, so if those are present the methods no longer deliver credible estimates.","fun_headline_variants_meta":{"raw":{"variants":["Feedback in panels: pre-trends won't save fixed effects","Sequential exogeneity: panel estimators get bias 1/T","Why strict exogeneity fails: feedback in panel data","When outcomes affect treatments, panel estimates lie","Relaxing exogeneity: heterogenous effects not identified"]},"model":"deepseek-v4-flash","effort":"low","cost_usd":0.000255,"raw_usage":{"total_tokens":1351,"prompt_tokens":627,"completion_tokens":724,"prompt_tokens_details":{"cached_tokens":256},"prompt_cache_hit_tokens":256,"prompt_cache_miss_tokens":371,"completion_tokens_details":{"reasoning_tokens":644}},"tokens_in":371,"tokens_out":724,"duration_ms":6462,"temperature":1.0,"reasoning_tokens":644,"cache_read_input_tokens":256,"cache_creation_input_tokens":0},"cache_creation_input_tokens":0},"created_at":"2026-08-03T15:12:27.667740+00:00","model_set":{"reader":"deepseek-v4-flash"},"falsifier":"Simulate a two-period binary-treatment panel where the treatment depends on the lagged outcome shock, and verify that the two-way fixed-effects estimator deviates from the true ATT while the sequential-exogeneity-robust weighted average recovers it. Alternatively, re-examine a job-training evaluation with a randomized benchmark; if the sequential-exogeneity-based estimate does not move closer to the benchmark than the difference-in-differences estimate does, the framework's practical value is weakened.","supporting_citations":[],"review_version":1}