MétaCan
Menu
Back to cohort
Record W7071900186

Value search estimators of individualized treatment regimes using a new class of weights

2016· dissertation· en· W7071900186 on OpenAlexaff

Bibliographic record

VenueeScholarship@McGill (McGill) · 2016
Typedissertation
Languageen
FieldMathematics
TopicAdvanced Causal Inference Techniques
Canadian institutionsMcGill UniversityMcGill University Health Centre
Fundersnot available
KeywordsClass (philosophy)EstimatorValue (mathematics)Variation (astronomy)Feature (linguistics)
DOInot available

Abstract

fetched live from OpenAlex

I would like to dedicate this thesis to my dearest parents, whose unconditionally emotional and financial support and constant encouragement have always been, and will always be, my greatest source of strength and inspiration. R ÉSUM ÉLa médecine personnalisée est un domaine de recherche en pleine croissance.Les programmes dynamiques de traitement (PDT) permettent de formaliser et d'adapter une série de décisions en fonction de l'historique médicale d'un patient.L'estimation des PDT dépend souvent d'estimateurs pondérés selon la probabilité inverse (EPPI) ou d'estimateurs augmentés pondérés selon la probabilité inverse (EAPPI).Ces deux familles d'estimateurs spécifient non seulement une classe restreinte de programmes, elles permettent aussi d'identifier le programme optimal au moyen de la maximisation de la réponse espérée pour chaque programme.Les EPPI sont des estimateurs robustes simples: ils requièrent une spécification correcte du modèle de traitement.Les EAPPI bénéficient toutefois d'une double robustesse: ils sont non biaisés à condition que soient correctement spécifiés le modèle de traitement ou le modèle de régression pour la réponse.Récemment, une nouvelle méthode d'estimation des PDT a été proposée: la méthode des moindres carrés ordinaires, pondérés et dynamiques (MCOPD).Elle combine deux méthodes communes: le Q-learning et le Gestimation.Dans ce mémoire, plutôt que la pondération selon la probabilité inverse conventionnelle, je propose la pondération de style MCOPD pour les estimateurs robustes simples et doubles dans le contexte des PDT.Je démontre que le nouvel estimateur robuste simple est cohérent, contrairement à l'estimateur robuste double.J'illustre la performance des méthodes proposées par l'intermédiaire de simulations et de l'analyse de données tirées du National Health and Nutrition Survey (NHANES) des États Unis.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.031
metaresearch head score (Gemma)0.138
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.031
Threshold uncertainty score0.162

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0310.138
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0040.002
Bibliometrics0.0030.004
Science and technology studies0.0010.003
Scholarly communication0.0040.008
Open science0.0040.003
Research integrity0.0030.007
Insufficient payload (model declined to judge)0.0070.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.118
GPT teacher head0.391
Teacher spread0.273 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2016
Admission routes1
Has abstractyes

Explore more

Same venueeScholarship@McGill (McGill)Same topicAdvanced Causal Inference TechniquesFrench-language works237,207