arXiv:2601.08643v1 Announce Type: cross 
Abstract: In this paper, we extend the Riesz representation framework to causal inference under sample selection, where both treatment assignment and outcome observability are non-random. Formulating the problem in terms of a Riesz representer enables stable estimation and a transparent decomposition of omitted variable bias into three interpretable components: a data-identified scale factor, outcome confounding strength, and selection confounding strength. For estimation, we employ the ForestRiesz estimator, which accounts for selective outcome observability while avoiding the instability associated with direct propensity score inversion. We assess finite-sample performance through a simulation study and show that conventional double machine learning approaches can be highly sensitive to tuning parameters due to their reliance on inverse probability weighting, whereas the ForestRiesz estimator delivers more stable performance by leveraging automatic debiased machine learning. In an empirical application to the gender wage gap in the U.S., we find that our ForestRiesz approach yields larger treatment effect estimates than a standard double machine learning approach, suggesting that ignoring sample selection leads to an underestimation of the gender wage gap. Sensitivity analysis indicates that implausibly strong unobserved confounding would be required to overturn our results. Overall, our approach provides a unified, robust, and computationally attractive framework for causal inference under sample selection.

قدمت دراسة حديثة تمديدًا لإطار تمثيل ريز لتحسين الاستدلال السببي في نماذج اختيار العينة، حيث تتناول تعيين العلاج غير العشوائي وقابلية ملاحظة النتائج. تستخدم الدراسة مقدر ForestRiesz لتوفير تقديرات مستقرة وتفكيك انحياز المتغيرات المفقودة إلى ثلاثة مكونات، مما يظهر أداءً محسنًا مقارنة بأساليب التعلم الآلي المزدوج التقليدية.

Un estudio reciente ha presentado una extensión del marco de representación de Riesz para mejorar la inferencia causal en modelos de selección de muestras, abordando la asignación de tratamiento no aleatoria y la observabilidad de resultados. La investigación emplea el estimador ForestRiesz para proporcionar estimaciones estables y descomponer el sesgo de variables omitidas en tres componentes, demostrando un rendimiento mejorado en comparación con los métodos de aprendizaje automático doble tradicionales.

Une étude récente a introduit une extension du cadre de représentation de Riesz pour améliorer l'inférence causale dans les modèles de sélection d'échantillons, abordant l'attribution de traitement non aléatoire et l'observabilité des résultats. La recherche utilise l'estimateur ForestRiesz pour fournir des estimations stables et décomposer le biais des variables omises en trois composants, démontrant une performance améliorée par rapport aux méthodes d'apprentissage machine double traditionnelles.

A recent study has introduced an extension of the Riesz representation framework to enhance causal inference in sample selection models, addressing non-random treatment assignment and outcome observability. The research employs the ForestRiesz estimator to provide stable estimations and decompose omitted variable bias into three components, demonstrating improved performance over traditional double machine learning methods.

Automatic debiased machine learning and sensitivity analysis for sample selection models

<p>This reported machine may be linked to &ldquo;Havana syndrome,&rdquo; a debated condition characterized by a strange panoply of symptoms that were experienced by U.S. officials stationed in Cuba</p>

يُقال إن البنتاغون يختبر جهازًا يعمل بالموجات الراديوية قد يكون مرتبطًا بالحالة المثيرة للجدل المعروفة باسم 'متلازمة هافانا'، والتي أثرت على المسؤولين الأمريكيين المتمركزين في كوبا، حيث ظهرت مجموعة من الأعراض غير المفسرة.

Se informa que el Pentágono está probando un dispositivo de ondas de radio que podría estar vinculado a la controvertida condición conocida como 'síndrome de La Habana', que ha afectado a funcionarios estadounidenses estacionados en Cuba, presentando una variedad de síntomas inexplicables.

Le Pentagone teste apparemment un dispositif à ondes radio qui pourrait être lié à la condition controversée connue sous le nom de 'syndrome de La Havane', qui a touché des responsables américains stationnés à Cuba, présentant une gamme de symptômes inexpliqués.

The Pentagon is reportedly testing a radio wave device that may be linked to the controversial condition known as 'Havana Syndrome,' which has affected U.S. officials stationed in Cuba, presenting a range of unexplained symptoms.

Pentagon Reportedly Testing Radio Wave Device Linked to ‘Havana Syndrome’

One More Thing in AI – Your Shortcut to AI Mastery

Automatic debiased machine learning and sensitivity analysis for sample selection models

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

DEIbias.io

Hirex

Gyfted

Portfolio Backtest

Ready to build your own newsroom?