Searcharxiv⌕ Search

arXiv subjects

Adel Daoud

Publications and source records attributed to Adel Daoud.

36 records · Page 2Linked to original sources
arXiv2024

$ρ$-GNF: A Copula-based Sensitivity Analysis to Unobserved Confounding Using Normalizing Flows

We propose a novel sensitivity analysis to unobserved confounding in observational studies using copulas and normalizing flows. Using the idea of interventional equivalence of structural causal models, we develop $ρ$-GNF ($ρ$-graphical normalizing flow), where $ρ{\in}[-1,+1]$ is a bounded sensitivity parameter. This parameter represents the back-door non-causal association due to unobserved confounding, and which is encoded with a Gaussian copula. In other words, the $ρ$-GNF enables scholars to estimate the average causal effect (ACE) as a function of $ρ$, while accounting for various assumed strengths of the unobserved confounding. The output of the $ρ$-GNF is what we denote as the $ρ_{curve}$ that provides the bounds for the ACE given an interval of assumed $ρ$ values. In particular, the $ρ_{curve}$ enables scholars to identify the confounding strength required to nullify the ACE, similar to other sensitivity analysis methods (e.g., the E-value). Leveraging on experiments from simulated and real-world data, we show the benefits of $ρ$-GNF. One benefit is that the $ρ$-GNF uses a Gaussian copula to encode the distribution of the unobserved causes, which is commonly used in many applied settings. This distributional assumption produces narrower ACE bounds compared to other popular sensitivity analysis methods.

stat.ME↗
arXiv2024

Effect Heterogeneity with Earth Observation in Randomized Controlled Trials: Exploring the Role of Data, Model, and Evaluation Metric Choice

Many social and environmental phenomena are associated with macroscopic changes in the built environment, captured by satellite imagery on a global scale and with daily temporal resolution. While widely used for prediction, these images and especially image sequences remain underutilized for causal inference, especially in the context of randomized controlled trials (RCTs), where causal identification is established by design. In this paper, we develop and compare a set of general tools for analyzing Conditional Average Treatment Effects (CATEs) from temporal satellite data that can be applied to any RCT where geographical identifiers are available. Through a simulation study, we analyze different modeling strategies for estimating CATE in sequences of satellite images. We find that image sequence representation models with more parameters generally yield a greater ability to detect heterogeneity. To explore the role of model and data choice in practice, we apply the approaches to two influential RCTs -- Banerjee et al. (2015), a poverty study in Cusco, Peru, and Bolsen et al. (2014), a water conservation experiment in Georgia, USA. We benchmark our image sequence models against image-only, tabular-only, and combined image-tabular data sources, summarizing practical implications for investigators in a multivariate analysis. Land cover classifications over satellite images facilitate interpretation of what image features drive heterogeneity. We also show robustness to data and model choice of satellite-based generalization of the RCT results to larger geographical areas outside the original. Overall, this paper shows how satellite sequence data can be incorporated into the analysis of RCTs, and provides evidence about the implications of data, model, and evaluation metric choice for causal analysis.

stat.ME↗
arXiv2024

Can Large Language Models (or Humans) Disentangle Text?

We investigate the potential of large language models (LLMs) to disentangle text variables--to remove the textual traces of an undesired forbidden variable in a task sometimes known as text distillation and closely related to the fairness in AI and causal inference literature. We employ a range of various LLM approaches in an attempt to disentangle text by identifying and removing information about a target variable while preserving other relevant signals. We show that in the strong test of removing sentiment, the statistical association between the processed text and sentiment is still detectable to machine learning classifiers post-LLM-disentanglement. Furthermore, we find that human annotators also struggle to disentangle sentiment while preserving other semantic content. This suggests there may be limited separability between concept variables in some text contexts, highlighting limitations of methods relying on text-level transformations and also raising questions about the robustness of disentanglement methods that achieve statistical independence in representation space.

cs.CL↗
arXiv2024

Deep Learning With DAGs

Social science theories often postulate causal relationships among a set of variables or events. Although directed acyclic graphs (DAGs) are increasingly used to represent these theories, their full potential has not yet been realized in practice. As non-parametric causal models, DAGs require no assumptions about the functional form of the hypothesized relationships. Nevertheless, to simplify the task of empirical evaluation, researchers tend to invoke such assumptions anyway, even though they are typically arbitrary and do not reflect any theoretical content or prior knowledge. Moreover, functional form assumptions can engender bias, whenever they fail to accurately capture the complexity of the causal system under investigation. In this article, we introduce causal-graphical normalizing flows (cGNFs), a novel approach to causal inference that leverages deep neural networks to empirically evaluate theories represented as DAGs. Unlike conventional approaches, cGNFs model the full joint distribution of the data according to a DAG supplied by the analyst, without relying on stringent assumptions about functional form. In this way, the method allows for flexible, semi-parametric estimation of any causal estimand that can be identified from the DAG, including total effects, conditional effects, direct and indirect effects, and path-specific effects. We illustrate the method with a reanalysis of Blau and Duncan's (1967) model of status attainment and Zhou's (2019) model of conditional versus controlled mobility. To facilitate adoption, we provide open-source software together with a series of online tutorials for implementing cGNFs. The article concludes with a discussion of current limitations and directions for future development.

stat.ML↗
arXiv2023

CausalImages: An R Package for Causal Inference with Earth Observation, Bio-medical, and Social Science Images

The causalimages R package enables causal inference with image and image sequence data, providing new tools for integrating novel data sources like satellite and bio-medical imagery into the study of cause and effect. One set of functions enables image-based causal inference analyses. For example, one key function decomposes treatment effect heterogeneity by images using an interpretable Bayesian framework. This allows for determining which types of images or image sequences are most responsive to interventions. A second modeling function allows researchers to control for confounding using images. The package also allows investigators to produce embeddings that serve as vector summaries of the image or video content. Finally, infrastructural functions are also provided, such as tools for writing large-scale image and image sequence data as sequentialized byte strings for more rapid image analysis. causalimages therefore opens new capabilities for causal inference in R, letting researchers use informative imagery in substantive analyses in a fast and accessible manner.

cs.LG↗
arXiv2023

Image-based Treatment Effect Heterogeneity

Randomized controlled trials (RCTs) are considered the gold standard for estimating the average treatment effect (ATE) of interventions. One use of RCTs is to study the causes of global poverty -- a subject explicitly cited in the 2019 Nobel Memorial Prize awarded to Duflo, Banerjee, and Kremer "for their experimental approach to alleviating global poverty." Because the ATE is a population summary, anti-poverty experiments often seek to unpack the effect variation around the ATE by conditioning (CATE) on tabular variables such as age and ethnicity that were measured during the RCT data collection. Although such variables are key to unpacking CATE, using only such variables may fail to capture historical, geographical, or neighborhood-specific contributors to effect variation, as tabular RCT data are often only observed near the time of the experiment. In global poverty research, when the location of the experiment units is approximately known, satellite imagery can provide a window into such factors important for understanding heterogeneity. However, there is no method that specifically enables applied researchers to analyze CATE from images. In this paper, using a deep probabilistic modeling framework, we develop such a method that estimates latent clusters of images by identifying images with similar treatment effects distributions. Our interpretable image CATE model also includes a sensitivity factor that quantifies the importance of image segments contributing to the effect cluster prediction. We compare the proposed methods against alternatives in simulation; also, we show how the model works in an actual RCT, estimating the effects of an anti-poverty intervention in northern Uganda and obtaining a posterior predictive distribution over effects for the rest of the country where no experimental data was collected. We make all models available in open-source software.

cs.LG↗
arXiv2023

Estimating Causal Effects Under Image Confounding Bias with an Application to Poverty in Africa

Observational studies of causal effects require adjustment for confounding factors. In the tabular setting, where these factors are well-defined, separate random variables, the effect of confounding is well understood. However, in public policy, ecology, and in medicine, decisions are often made in non-tabular settings, informed by patterns or objects detected in images (e.g., maps, satellite or tomography imagery). Using such imagery for causal inference presents an opportunity because objects in the image may be related to the treatment and outcome of interest. In these cases, we rely on the images to adjust for confounding but observed data do not directly label the existence of the important objects. Motivated by real-world applications, we formalize this challenge, how it can be handled, and what conditions are sufficient to identify and estimate causal effects. We analyze finite-sample performance using simulation experiments, estimating effects using a propensity adjustment algorithm that employs a machine learning model to estimate the image confounding. Our experiments also examine sensitivity to misspecification of the image pattern mechanism. Finally, we use our methodology to estimate the effects of policy interventions on poverty in African communities from satellite imagery.

cs.LG↗
arXiv2023

Integrating Earth Observation Data into Causal Inference: Challenges and Opportunities

Observational studies require adjustment for confounding factors that are correlated with both the treatment and outcome. In the setting where the observed variables are tabular quantities such as average income in a neighborhood, tools have been developed for addressing such confounding. However, in many parts of the developing world, features about local communities may be scarce. In this context, satellite imagery can play an important role, serving as a proxy for the confounding variables otherwise unobserved. In this paper, we study confounder adjustment in this non-tabular setting, where patterns or objects found in satellite images contribute to the confounder bias. Using the evaluation of anti-poverty aid programs in Africa as our running example, we formalize the challenge of performing causal adjustment with such unstructured data -- what conditions are sufficient to identify causal effects, how to perform estimation, and how to quantify the ways in which certain aspects of the unstructured image object are most predictive of the treatment decision. Via simulation, we also explore the sensitivity of satellite image-based observational inference to image resolution and to misspecification of the image-associated confounder. Finally, we apply these tools in estimating the effect of anti-poverty interventions in African communities from satellite imagery.

stat.ML↗
arXiv2022

To What Extent Do Disadvantaged Neighborhoods Mediate Social Assistance Dependency? Evidence from Sweden

Occasional social assistance prevents individuals from a range of social ills, particularly unemployment and poverty. It remains unclear, however, how and to what extent continued reliance on social assistance leads to individuals becoming trapped in social assistance dependency. In this paper, we build on the theory of cumulative disadvantage and examine whether the accumulated use of social assistance over the life course is associated with an increased risk of future social assistance recipiency. We also analyze the extent to which living in disadvantaged neighborhoods constitutes an important mechanism in the explanation of this association. Our analyses use Swedish population registers for the full population of individuals born in 1981, and these individuals are followed for approximately 17 years. While most studies are limited by a lack of granular, life-history data, our granular individual-level data allow us to apply causal-mediation analysis, and thereby quantify the extent to which the likelihood of ending up in social assistance dependency is affected by residing in disadvantaged neighborhoods. Our findings show the accumulation of social assistance over the studied period is associated with a more than four-fold increase on a risk ratio scale for future social assistance recipiency, compared to never having received social assistance during the period examined. Then, we examine how social assistance dependency is mediated by prolonged exposure to disadvantaged neighborhoods. Our results suggest that the indirect effect of disadvantaged neighborhoods is weak to moderate. Therefore, social assistance dependency may be a multilevel process. Future research is to explore how the mediating effects of disadvantaged neighborhoods vary in different contexts.

econ.GN↗
arXiv2022

Conceptualizing Treatment Leakage in Text-based Causal Inference

Causal inference methods that control for text-based confounders are becoming increasingly important in the social sciences and other disciplines where text is readily available. However, these methods rely on a critical assumption that there is no treatment leakage: that is, the text only contains information about the confounder and no information about treatment assignment. When this assumption does not hold, methods that control for text to adjust for confounders face the problem of post-treatment (collider) bias. However, the assumption that there is no treatment leakage may be unrealistic in real-world situations involving text, as human language is rich and flexible. Language appearing in a public policy document or health records may refer to the future and the past simultaneously, and thereby reveal information about the treatment assignment. In this article, we define the treatment-leakage problem, and discuss the identification as well as the estimation challenges it raises. Second, we delineate the conditions under which leakage can be addressed by removing the treatment-related signal from the text in a pre-processing step we define as text distillation. Lastly, using simulation, we show how treatment leakage introduces a bias in estimates of the average treatment effect (ATE) and how text distillation can mitigate this bias.

cs.CL↗
arXiv2022

Personalized Public Policy Analysis in Social Sciences using Causal-Graphical Normalizing Flows

Structural Equation/Causal Models (SEMs/SCMs) are widely used in epidemiology and social sciences to identify and analyze the average causal effect (ACE) and conditional ACE (CACE). Traditional causal effect estimation methods such as Inverse Probability Weighting (IPW) and more recently Regression-With-Residuals (RWR) are widely used - as they avoid the challenging task of identifying the SCM parameters - to estimate ACE and CACE. However, much work remains before traditional estimation methods can be used for counterfactual inference, and for the benefit of Personalized Public Policy Analysis (P$^3$A) in the social sciences. While doctors rely on personalized medicine to tailor treatments to patients in laboratory settings (relatively closed systems), P$^3$A draws inspiration from such tailoring but adapts it for open social systems. In this article, we develop a method for counterfactual inference that we name causal-Graphical Normalizing Flow (c-GNF), facilitating P$^3$A. First, we show how c-GNF captures the underlying SCM without making any assumption about functional forms. Second, we propose a novel dequantization trick to deal with discrete variables, which is a limitation of normalizing flows in general. Third, we demonstrate in experiments that c-GNF performs on-par with IPW and RWR in terms of bias and variance for estimating the ATE, when the true functional forms are known, and better when they are unknown. Fourth and most importantly, we conduct counterfactual inference with c-GNFs, demonstrating promising empirical performance. Because IPW and RWR, like other traditional methods, lack the capability of counterfactual inference, c-GNFs will likely play a major role in tailoring personalized treatment, facilitating P$^3$A, optimizing social interventions - in contrast to the current `one-size-fits-all' approach of existing methods.

cs.LG↗
arXiv2022

Counterfactual Analysis of the Impact of the IMF Program on Child Poverty in the Global-South Region using Causal-Graphical Normalizing Flows

This work demonstrates the application of a particular branch of causal inference and deep learning models: \emph{causal-Graphical Normalizing Flows (c-GNFs)}. In a recent contribution, scholars showed that normalizing flows carry certain properties, making them particularly suitable for causal and counterfactual analysis. However, c-GNFs have only been tested in a simulated data setting and no contribution to date have evaluated the application of c-GNFs on large-scale real-world data. Focusing on the \emph{AI for social good}, our study provides a counterfactual analysis of the impact of the International Monetary Fund (IMF) program on child poverty using c-GNFs. The analysis relies on a large-scale real-world observational data: 1,941,734 children under the age of 18, cared for by 567,344 families residing in the 67 countries from the Global-South. While the primary objective of the IMF is to support governments in achieving economic stability, our results find that an IMF program reduces child poverty as a positive side-effect by about 1.2$\pm$0.24 degree (`0' equals no poverty and `7' is maximum poverty). Thus, our article shows how c-GNFs further the use of deep learning and causal inference in AI for social good. It shows how learning algorithms can be used for addressing the untapped potential for a significant social impact through counterfactual inference at population level (ACE), sub-population level (CACE), and individual level (ICE). In contrast to most works that model ACE or CACE but not ICE, c-GNFs enable personalization using \emph{`The First Law of Causal Inference'}.

cs.AI↗
arXiv2021

The International Monetary Funds intervention in education systems and its impact on childrens chances of completing school

Enabling children to acquire an education is one of the most effective means to reduce inequality, poverty, and ill-health globally. While in normal times a government controls its educational policies, during times of macroeconomic instability, that control may shift to supporting international organizations, such as the International Monetary Fund (IMF). While much research has focused on which sectors has been affected by IMF policies, scholars have devoted little attention to the policy content of IMF interventions affecting the education sector and childrens education outcomes: denoted IMF education policies. This article evaluates the extent which IMF education policies exist in all programs and how these policies and IMF programs affect childrens likelihood of completing schools. While IMF education policies have a small adverse effect yet statistically insignificant on childrens probability of completing school, these policies moderate effect heterogeneity for IMF programs. The effect of IMF programs (joint set of policies) adversely effect childrens chances of completing school by six percentage points. By analyzing how IMF-education policies but also how IMF programs affect the education sector in low and middle-income countries, scholars will gain a deeper understanding of how such policies will likely affect downstream outcomes.

econ.GN↗
arXiv2020

The wealth of nations and the health of populations: A quasi-experimental design of the impact of sovereign debt crises on child mortality

The wealth of nations and the health of populations are intimately strongly associated, yet the extent to which economic prosperity (GDP per capita) causes improved health remains disputed. The purpose of this article is to analyze the impact of sovereign debt crises (SDC) on child mortality, using a sample of 57 low- and middle-income countries surveyed by the Demographic and Health Survey between the years 1990 and 2015. These surveys supply 229 household data and containing about 3 million childbirth history records. This focus on SDC instead of GDP provides a quasi-experimental moment in which the influence of unobserved confounding is less than a moment analyzing the normal fluctuations of GDP. This study measures child mortality at six thresholds: neonatal, under-one (infant), under-two, under-three, under-four, and under-five mortality. Using a machine-learning (ML) model for causal inference, this study finds that while an SDC causes an adverse yet statistically insignificant effect on neonatal mortality, all other child mortality group samples are adversely affected between a probability of 0.12 to 0.14 (all statistically significant at the 95-percent threshold). Through this ML, this study also finds that the most important treatment heterogeneity moderator, in the entire adjustment set, is whether a child is born in a low-income country.

econ.GN↗
arXiv2020

Statistical modeling: the three cultures

Two decades ago, Leo Breiman identified two cultures for statistical modeling. The data modeling culture (DMC) refers to practices aiming to conduct statistical inference on one or several quantities of interest. The algorithmic modeling culture (AMC) refers to practices defining a machine-learning (ML) procedure that generates accurate predictions about an event of interest. Breiman argued that statisticians should give more attention to AMC than to DMC, because of the strengths of ML in adapting to data. While twenty years later, DMC has lost some of its dominant role in statistics because of the data-science revolution, we observe that this culture is still the leading practice in the natural and social sciences. DMC is the modus operandi because of the influence of the established scientific method, called the hypothetico-deductive scientific method. Despite the incompatibilities of AMC with this scientific method, among some research groups, AMC and DMC cultures mix intensely. We argue that this mixing has formed a fertile spawning pool for a mutated culture that we called the hybrid modeling culture (HMC) where prediction and inference have fused into new procedures where they reinforce one another. This article identifies key characteristics of HMC, thereby facilitating the scientific endeavor and fueling the evolution of statistical cultures towards better practices. By better, we mean increasingly reliable, valid, and efficient statistical practices in analyzing causal relationships. In combining inference and prediction, the result of HMC is that the distinction between prediction and inference, taken to its limit, melts away. We qualify our melting-away argument by describing three HMC practices, where each practice captures an aspect of the scientific cycle, namely, ML for causal inference, ML for data acquisition, and ML for theory prediction.

stat.ME↗
arXiv2020

Extending Social Resource Exchange to Events of Abundance and Sufficiency

This article identifies how scarcity, abundance, and sufficiency influence exchange behavior. Analyzing the mechanisms governing exchange of resources constitutes the foundation of several social-science perspectives. Neoclassical economics provides one of the most well-known perspectives of how rational individuals allocate and exchange resources. Using Rational Choice Theory (RCT), neoclassical economics assumes that exchange between two individuals will occur when resources are scarce and that these individuals interact rationally to satisfy their requirements (i.e., preferences). While RCT is useful to characterize interaction in closed and stylized systems, it proves insufficient to capture social and psychological reality where culture, emotions, and habits play an integral part in resource exchange. Social Resource Theory (SRT) improves on RCT in several respects by making the social nature of resources the object of study. SRT shows how human interaction is driven by an array of psychological mechanisms, from emotions to heuristics. Thus, SRT provides a more realistic foundation for analyzing and explaining social exchange than the stylized instrumental rationality of RCT. Yet SRT has no clear place for events of abundance and sufficiency as additional motivations to exchange resources. This article synthesize and formalize a foundation for SRT using not only scarcity but also abundance and sufficiency.

econ.GN↗
arXiv2020

Combining distributive ethics and causal Inference to make trade-offs between austerity and population health

The International Monetary Fund (IMF) provides financial assistance to its member-countries in economic turmoil, but requires at the same time that these countries reform their public policies. In several contexts, these reforms are at odds with population health. While researchers have empirically analyzed the consequences of these reforms on health, no analysis exist on identifying fair tradeoffs between consequences on population health and economic outcomes. Our article analyzes and identifies the principles governing these tradeoffs. First, this article reviews existing policy-evaluation studies, which show, on balance, that IMF policies frequently cause adverse effects on child health and material standards in the pursuit of macroeconmic improvement. Second, this article discusses four theories in distributive ethics (maximization, egalitarianianism, prioritarianiasm, and sufficientarianism) to identify which is the most compatible with the core mission of the IMF, that is, improved macroeconomics (Articles of Agreement) while at the same time balancing consequences on health. Using a distributive-ethics analyses of IMF polices, we argue that sufficientarianism is the most compatible theory. Third, this article offer a qualitative rearticulation of the Articles of Agreement, and formalize sufficientarian principles in the language of causal inference. We also offer a framework on how to empirically measure, from observational data, the extent that IMF policies trade off fairly between population health and economic outcomes. We conclude with policy recommendations and suggestions for future research.

econ.GN↗