arXiv subjects

Martin Spindler

Publications and source records attributed to Martin Spindler.

At least 19 recordsLinked to original sources

arXiv2025

Sensitivity Analysis for Treatment Effects in Difference-in-Differences Models using Riesz Representation

Difference-in-differences (DiD) is one of the most popular approaches for empirical research in economics, political science, and beyond. Identification in these models is based on the conditional parallel trends assumption: In the absence of treatment, the average outcome of the treated and untreated group are assumed to evolve in parallel over time, conditional on pre-treatment covariates. We introduce a novel approach to sensitivity analysis for DiD models that assesses the robustness of DiD estimates to violations of this assumption due to unobservable confounders, allowing researchers to transparently assess and communicate the credibility of their causal estimation results. Our method focuses on estimation by Double Machine Learning and extends previous work on sensitivity analysis based on Riesz Representation in cross-sectional settings. We establish asymptotic bounds for point estimates and confidence intervals in the canonical $2\times2$ setting and group-time causal parameters in settings with staggered treatment adoption. Our approach makes it possible to relate the formulation of parallel trends violation to empirical evidence from (1) pre-testing, (2) covariate benchmarking and (3) standard reporting statistics and visualizations. We provide extensive simulation experiments demonstrating the validity of our sensitivity approach and diagnostics and apply our approach to two empirical applications.

econ.EM↗

arXiv2025

Sensitivity Analysis for Causal ML: A Use Case at Booking.com

Causal Machine Learning has emerged as a powerful tool for flexibly estimating causal effects from observational data in both industry and academia. However, causal inference from observational data relies on untestable assumptions about the data-generating process, such as the absence of unobserved confounders. When these assumptions are violated, causal effect estimates may become biased, undermining the validity of research findings. In these contexts, sensitivity analysis plays a crucial role, by enabling data scientists to assess the robustness of their findings to plausible violations of unconfoundedness. This paper introduces sensitivity analysis and demonstrates its practical relevance through a (simulated) data example based on a use case at Booking.com. We focus our presentation on a recently proposed method by Chernozhukov et al. (2023), which derives general non-parametric bounds on biases due to omitted variables, and is fully compatible with (though not limited to) modern inferential tools of Causal Machine Learning. By presenting this use case, we aim to raise awareness of sensitivity analysis and highlight its importance in real-world scenarios.

econ.EM↗

arXiv2025

Effect Identification and Unit Categorization in the Multi-Score Regression Discontinuity Design with Application to LED Manufacturing

RDD (Regression discontinuity design) is a widely used framework for identifying and estimating causal effects at the cutoff of a single running variable. In practice, however, decision-making often involves multiple thresholds and criteria, especially in production systems. Standard MRD (multi-score RDD) methods address this complexity by reducing the problem to a one-dimensional design. This simplification allows existing approaches to be used to identify and estimate causal effects, but it can introduce non-compliance by misclassifying units relative to the original cutoff rules. We develop theoretical tools to detect and reduce "fuzziness" when estimating the cutoff effect for units that comply with individual subrules of a multi-rule system. In particular, we propose a formal definition and categorization of unit behavior types under multi-dimensional cutoff rules, extending standard classifications of compliers, alwaystakers, and nevertakers, and incorporating defiers and indecisive units. We further identify conditions under which cutoff effects for compliers can be estimated in multiple dimensions, and establish when identification remains valid after excluding nevertakers and alwaystakers. In addition, we examine how decomposing complex Boolean cutoff rules (such as AND- and OR-type rules) into simpler components affects the classification of units into behavioral types and improves estimation by making it possible to identify and remove non-compliant units more accurately. We validate our framework using both semi-synthetic simulations calibrated to production data and real-world data from opto-electronic semiconductor manufacturing. The empirical results demonstrate that our approach has practical value in refining production policies and reduces estimation variance. This underscores the usefulness of the MRD framework in manufacturing contexts.

stat.ME↗

arXiv2024

Adventures in Demand Analysis Using AI

This paper advances empirical demand analysis by integrating multimodal product representations derived from artificial intelligence (AI). Using a detailed dataset of toy cars on textit{Amazon.com}, we combine text descriptions, images, and tabular covariates to represent each product using transformer-based embedding models. These embeddings capture nuanced attributes, such as quality, branding, and visual characteristics, that traditional methods often struggle to summarize. Moreover, we fine-tune these embeddings for causal inference tasks. We show that the resulting embeddings substantially improve the predictive accuracy of sales ranks and prices and that they lead to more credible causal estimates of price elasticity. Notably, we uncover strong heterogeneity in price elasticity driven by these product-specific features. Our findings illustrate that AI-driven representations can enrich and modernize empirical demand analysis. The insights generated may also prove valuable for applied causal inference more broadly.

econ.GN↗

arXiv2024

Collusion Detection with Graph Neural Networks

Collusion is a complex phenomenon in which companies secretly collaborate to engage in fraudulent practices. This paper presents an innovative methodology for detecting and predicting collusion patterns in different national markets using neural networks (NNs) and graph neural networks (GNNs). GNNs are particularly well suited to this task because they can exploit the inherent network structures present in collusion and many other economic problems. Our approach consists of two phases: In Phase I, we develop and train models on individual market datasets from Japan, the United States, two regions in Switzerland, Italy, and Brazil, focusing on predicting collusion in single markets. In Phase II, we extend the models' applicability through zero-shot learning, employing a transfer learning approach that can detect collusion in markets in which training data is unavailable. This phase also incorporates out-of-distribution (OOD) generalization to evaluate the models' performance on unseen datasets from other countries and regions. In our empirical study, we show that GNNs outperform NNs in detecting complex collusive patterns. This research contributes to the ongoing discourse on preventing collusion and optimizing detection methodologies, providing valuable guidance on the use of NNs and GNNs in economic applications to enhance market fairness and economic welfare.

econ.EM↗

arXiv2024

Credit Ratings: Heterogeneous Effect on Capital Structure

Why do companies choose particular capital structures? A compelling answer to this question remains elusive despite extensive research. In this article, we use double machine learning to examine the heterogeneous causal effect of credit ratings on leverage. Taking advantage of the flexibility of random forests within the double machine learning framework, we model the relationship between variables associated with leverage and credit ratings without imposing strong assumptions about their functional form. This approach also allows for data-driven variable selection from a large set of individual company characteristics, supporting valid causal inference. We report three findings: First, credit ratings causally affect the leverage ratio. Having a rating, as opposed to having none, increases leverage by approximately 7 to 9 percentage points, or 30\% to 40\% relative to the sample mean leverage. However, this result comes with an important caveat, captured in our second finding: the effect is highly heterogeneous and varies depending on the specific rating. For AAA and AA ratings, the effect is negative, reducing leverage by about 5 percentage points. For A and BBB ratings, the effect is approximately zero. From BB ratings onwards, the effect becomes positive, exceeding 10 percentage points. Third, contrary to what the second finding might imply at first glance, the change from no effect to a positive effect does not occur abruptly at the boundary between investment and speculative grade ratings. Rather, it is gradual, taking place across the granular rating notches ("+/-") within the BBB and BB categories.

econ.GN↗

arXiv2024

Management Decisions in Manufacturing using Causal Machine Learning -- To Rework, or not to Rework?

In this paper, we present a data-driven model for estimating optimal rework policies in manufacturing systems. We consider a single production stage within a multistage, lot-based system that allows for optional rework steps. While the rework decision depends on an intermediate state of the lot and system, the final product inspection, and thus the assessment of the actual yield, is delayed until production is complete. Repair steps are applied uniformly to the lot, potentially improving some of the individual items while degrading others. The challenge is thus to balance potential yield improvement with the rework costs incurred. Given the inherently causal nature of this decision problem, we propose a causal model to estimate yield improvement. We apply methods from causal machine learning, in particular double/debiased machine learning (DML) techniques, to estimate conditional treatment effects from data and derive policies for rework decisions. We validate our decision model using real-world data from opto-electronic semiconductor manufacturing, achieving a yield improvement of 2 - 3% during the color-conversion process of white light-emitting diodes (LEDs).

cs.LG↗

arXiv2024

Applied Causal Inference Powered by ML and AI

An introduction to the emerging fusion of machine learning and causal inference. The book presents ideas from classical structural equation models (SEMs) and their modern AI equivalent, directed acyclical graphs (DAGs) and structural causal models (SCMs), and covers Double/Debiased Machine Learning methods to do inference in such models using modern predictive tools.

econ.EM↗

arXiv2024

Hyperparameter Tuning for Causal Inference with Double Machine Learning: A Simulation Study

Proper hyperparameter tuning is essential for achieving optimal performance of modern machine learning (ML) methods in predictive tasks. While there is an extensive literature on tuning ML learners for prediction, there is only little guidance available on tuning ML learners for causal machine learning and how to select among different ML learners. In this paper, we empirically assess the relationship between the predictive performance of ML methods and the resulting causal estimation based on the Double Machine Learning (DML) approach by Chernozhukov et al. (2018). DML relies on estimating so-called nuisance parameters by treating them as supervised learning problems and using them as plug-in estimates to solve for the (causal) parameter. We conduct an extensive simulation study using data from the 2019 Atlantic Causal Inference Conference Data Challenge. We provide empirical insights on the role of hyperparameter tuning and other practical decisions for causal estimation with DML. First, we assess the importance of data splitting schemes for tuning ML learners within Double Machine Learning. Second, we investigate how the choice of ML methods and hyperparameters, including recent AutoML frameworks, impacts the estimation performance for a causal parameter of interest. Third, we assess to what extent the choice of a particular causal model, as characterized by incorporated parametric assumptions, can be based on predictive performance metrics.

econ.EM↗

arXiv2024

DoubleMLDeep: Estimation of Causal Effects with Multimodal Data

This paper explores the use of unstructured, multimodal data, namely text and images, in causal inference and treatment effect estimation. We propose a neural network architecture that is adapted to the double machine learning (DML) framework, specifically the partially linear model. An additional contribution of our paper is a new method to generate a semi-synthetic dataset which can be used to evaluate the performance of causal effect estimation in the presence of text and images as confounders. The proposed methods and architectures are evaluated on the semi-synthetic dataset and compared to standard approaches, highlighting the potential benefit of using text and images directly in causal studies. Our findings have implications for researchers and practitioners in economics, marketing, finance, medicine and data science in general who are interested in estimating causal quantities using non-traditional data.

cs.LG↗

arXiv2023

Causally Learning an Optimal Rework Policy

In manufacturing, rework refers to an optional step of a production process which aims to eliminate errors or remedy products that do not meet the desired quality standards. Reworking a production lot involves repeating a previous production stage with adjustments to ensure that the final product meets the required specifications. While offering the chance to improve the yield and thus increase the revenue of a production lot, a rework step also incurs additional costs. Additionally, the rework of parts that already meet the target specifications may damage them and decrease the yield. In this paper, we apply double/debiased machine learning (DML) to estimate the conditional treatment effect of a rework step during the color conversion process in opto-electronic semiconductor manufacturing on the final product yield. We utilize the implementation DoubleML to develop policies for the rework of components and estimate their value empirically. From our causal machine learning analysis we derive implications for the coating of monochromatic LEDs with conversion layers.

stat.ML↗

arXiv2022

Bernstein-type Inequalities and Nonparametric Estimation under Near-Epoch Dependence

The major contributions of this paper lie in two aspects. Firstly, we focus on deriving Bernstein-type inequalities for both geometric and algebraic irregularly-spaced NED random fields, which contain time series as special case. Furthermore, by introducing the idea of "effective dimension" to the index set of random field, our results reflect that the sharpness of inequalities are only associated with this "effective dimension". Up to the best of our knowledge, our paper may be the first one reflecting this phenomenon. Hence, the first contribution of this paper can be more or less regarded as an update of the pioneering work from \citeA{xu2018sieve}. Additionally, as a corollary of our first contribution, a Bernstein-type inequality for geometric irregularly-spaced $\alpha$-mixing random fields is also obtained. The second aspect of our contributions is that, based on the inequalities mentioned above, we show the $L_{\infty}$ convergence rate of the many interesting kernel-based nonparametric estimators. To do this, two deviation inequalities for the supreme of empirical process are derived under NED and $\alpha$-mixing conditions respectively. Then, for irregularly-spaced NED random fields, we prove the attainability of optimal rate for local linear estimator of nonparametric regression, which refreshes another pioneering work on this topic, \citeA{jenish2012nonparametric}. Subsequently, we analyze the uniform convergence rate of uni-modal regression under the same NED conditions as well. Furthermore, by following the guide of \citeA{rigollet2009optimal}, we also prove that the kernel-based plug-in density level set estimator could be optimal up to a logarithm factor. Meanwhile, when the data is collected from $\alpha$-mixing random fields, we also derive the uniform convergence rate of a simple local polynomial density estimator \cite{cattaneo2020simple}.

math.ST↗

arXiv2021

Machine Learning for Financial Forecasting, Planning and Analysis: Recent Developments and Pitfalls

This article is an introduction to machine learning for financial forecasting, planning and analysis (FP\&A). Machine learning appears well suited to support FP\&A with the highly automated extraction of information from large amounts of data. However, because most traditional machine learning techniques focus on forecasting (prediction), we discuss the particular care that must be taken to avoid the pitfalls of using them for planning and resource allocation (causal inference). While the naive application of machine learning usually fails in this context, the recently developed double machine learning framework can address causal questions of interest. We review the current literature on machine learning in FP\&A and illustrate in a simulation study how machine learning can be used for both forecasting and planning. We also investigate how forecasting and planning improve as the number of data points increases.

econ.EM↗

arXiv2021

DoubleML -- An Object-Oriented Implementation of Double Machine Learning in Python

DoubleML is an open-source Python library implementing the double machine learning framework of Chernozhukov et al. (2018) for a variety of causal models. It contains functionalities for valid statistical inference on causal parameters when the estimation of nuisance parameters is based on machine learning methods. The object-oriented implementation of DoubleML provides a high flexibility in terms of model specifications and makes it easily extendable. The package is distributed under the MIT license and relies on core libraries from the scientific Python ecosystem: scikit-learn, numpy, pandas, scipy, statsmodels and joblib. Source code, documentation and an extensive user guide can be found at https://github.com/DoubleML/doubleml-for-py and https://docs.doubleml.org.

stat.ML↗

arXiv2021

DoubleML -- An Object-Oriented Implementation of Double Machine Learning in R

The R package DoubleML implements the double/debiased machine learning framework of Chernozhukov et al. (2018). It provides functionalities to estimate parameters in causal models based on machine learning methods. The double machine learning framework consist of three key ingredients: Neyman orthogonality, high-quality machine learning estimation and sample splitting. Estimation of nuisance components can be performed by various state-of-the-art machine learning methods that are available in the mlr3 ecosystem. DoubleML makes it possible to perform inference in a variety of causal models, including partially linear and interactive regression models and their extensions to instrumental variable estimation. The object-oriented implementation of DoubleML enables a high flexibility for the model specification and makes it easily extendable. This paper serves as an introduction to the double machine learning framework and the R package DoubleML. In reproducible code examples with simulated and real data sets, we demonstrate how DoubleML users can perform valid inference based on machine learning methods.

stat.ML↗

arXiv2021

Big Data meets Causal Survey Research: Understanding Nonresponse in the Recruitment of a Mixed-mode Online Panel

Survey scientists increasingly face the problem of high-dimensionality in their research as digitization makes it much easier to construct high-dimensional (or "big") data sets through tools such as online surveys and mobile applications. Machine learning methods are able to handle such data, and they have been successfully applied to solve \emph{predictive} problems. However, in many situations, survey statisticians want to learn about \emph{causal} relationships to draw conclusions and be able to transfer the findings of one survey to another. Standard machine learning methods provide biased estimates of such relationships. We introduce into survey statistics the double machine learning approach, which gives approximately unbiased estimators of causal parameters, and show how it can be used to analyze survey nonresponse in a high-dimensional panel setting.

stat.ME↗

arXiv2020

Insights from Optimal Pandemic Shielding in a Multi-Group SEIR Framework

The COVID-19 pandemic constitutes one of the largest threats in recent decades to the health and economic welfare of populations globally. In this paper, we analyze different types of policy measures designed to fight the spread of the virus and minimize economic losses. Our analysis builds on a multi-group SEIR model, which extends the multi-group SIR model introduced by Acemoglu et al.~(2020). We adjust the underlying social interaction patterns and consider an extended set of policy measures. The model is calibrated for Germany. Despite the trade-off between COVID-19 prevention and economic activity that is inherent to shielding policies, our results show that efficiency gains can be achieved by targeting such policies towards different age groups. Alternative policies such as physical distancing can be employed to reduce the degree of targeting and the intensity and duration of shielding. Our results show that a comprehensive approach that combines multiple policy measures simultaneously can effectively mitigate population mortality and economic harm.

econ.GN↗

arXiv2020

Estimation and Uniform Inference in Sparse High-Dimensional Additive Models

We develop a novel method to construct uniformly valid confidence bands for a nonparametric component $f_1$ in the sparse additive model $Y=f_1(X_1)+\ldots + f_p(X_p) + \varepsilon$ in a high-dimensional setting. Our method integrates sieve estimation into a high-dimensional Z-estimation framework, facilitating the construction of uniformly valid confidence bands for the target component $f_1$. To form these confidence bands, we employ a multiplier bootstrap procedure. Additionally, we provide rates for the uniform lasso estimation in high dimensions, which may be of independent interest. Through simulation studies, we demonstrate that our proposed method delivers reliable results in terms of estimation and coverage, even in small samples.

stat.ME↗