{"paper":{"title":"Assessment of Simulation-based Inference Methods for Stochastic Compartmental Models in Epidemiological Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Likelihood-free Bayesian methods accurately estimate parameters in stochastic SIS, SIR and SEIR epidemic models from noisy data.","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Jan Hasenauer, Lorenzo Contento, Martin K\\\"uhn, Nils Wassmuth, Vincent Wieland","submitted_at":"2025-12-02T08:45:31Z","abstract_excerpt":"Global pandemics, such as the recent COVID-19 crisis, highlight the need for stochastic epidemic models that can capture the randomness inherent in the spread of disease. Such models must be accompanied by methods for estimating parameters in order to generate fast nowcasts and short-term forecasts that can inform public health decisions. This paper presents a comparison of two advanced Bayesian inference methods: 1) pseudo-marginal particle Markov chain Monte Carlo, using an unbiased likelihood estimate obtained by Particle Filter (PF), and 2) Conditional Normalizing Flows (CNF). We investiga"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our analysis highlights how these likelihood-free methods provide accurate and robust inference capabilities... Results on an Ethiopian cohort study demonstrate operational robustness under real-world noise and irregular data sampling.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen observation models and noise structures in the simulation study adequately represent the irregularities and biases present in real epidemiological surveillance data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Simulation study and Ethiopian cohort data show that particle MCMC and conditional normalizing flows both deliver accurate parameter estimates and forecasts for stochastic compartmental epidemic models with intractable likelihoods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Likelihood-free Bayesian methods accurately estimate parameters in stochastic SIS, SIR and SEIR epidemic models from noisy data.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"022e29e8810126b09873c2b29d83702971dee2b2050d47aad182d9b47e0fe766"},"source":{"id":"2512.02528","kind":"arxiv","version":4},"verdict":{"id":"21a3fd45-a44f-4742-8d84-36922e63ec10","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T02:52:57.448172Z","strongest_claim":"Our analysis highlights how these likelihood-free methods provide accurate and robust inference capabilities... Results on an Ethiopian cohort study demonstrate operational robustness under real-world noise and irregular data sampling.","one_line_summary":"Simulation study and Ethiopian cohort data show that particle MCMC and conditional normalizing flows both deliver accurate parameter estimates and forecasts for stochastic compartmental epidemic models with intractable likelihoods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen observation models and noise structures in the simulation study adequately represent the irregularities and biases present in real epidemiological surveillance data.","pith_extraction_headline":"Likelihood-free Bayesian methods accurately estimate parameters in stochastic SIS, SIR and SEIR epidemic models from noisy data."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.02528/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"59aeae276b4b10b83f7a4e44e5bfc9d657ce0f6b469e9a4ff0780b35cca701b1"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}