Federico Castelletti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Federico Castelletti has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Guido Consonni
Dipartimento di Scienze Statistiche, Università Cattolica del Sacro Cuore
6 shared publications Guido Consonni
Department of Statistical Sciences, Università Cattolica del Sacro Cuore , Largo Gemelli 1, Milan 20123
5 shared publications- Stefano Peluso
Department of Statistical Sciences Università Cattolica del Sacro Cuore Milan Italy
3 shared publications - Marco Luigi Della Vedova
Chalmers University of Technology
2 shared publications Stefano Peluso
Department of Statistics and Quantitative Methods, Università degli Studi di Milano-Bicocca, Milan, Italy
2 shared publications- Alessandro Mascaro
Università Cattolica del Sacro Cuore, Milan, Italy
1 shared publication
Latest Publications
- Open Access
Graphical model-based clustering of categorical data
Clustering multivariate data is a pervasive task in many applied problems, particularly in social studies and life science. Model-based approaches to clustering rely on mixture models, where each mixture component corresponds to the kernel of a distribution characterizing a latent sub-group. Current methods developed within this framework employ multivariate distributions built under the assumption of independence among variables given the cluster allocation. Accordingly, possible dependence structures characterizing differences across groups are not directly accounted for during the clustering process. In this paper we consider multivariate categorical data, and introduce a model-based clustering method which employs graphical models as a tool to encode dependencies between variables. Specifically, we consider a Dirichlet Process mixture of categorical graphical models, which clusters individuals into groups that are homogeneous in terms of dependence (graphical) structure and allied parameters. We provide full Bayesian inference for the model and develop a Markov chain Monte Carlo scheme for posterior analysis. Our method is evaluated through simulations and applied to real case studies, including the analysis of genomic data and voting records. Results reveal the merits of a graphical model-based clustering, in comparison with approaches that do not explicitly account for dependencies in the multivariate distribution of variables.
Open AccessGraphical model-based clustering of categorical data
Clustering multivariate data is a pervasive task in many applied problems, particularly in social studies and life science. Model-based approaches to clustering rely on mixture models, where each mixture component corresponds to the kernel of a distribution characterizing a latent sub-group. Current methods developed within this framework employ multivariate distributions built under the assumption of independence among variables given the cluster allocation. Accordingly, possible dependence structures characterizing differences across groups are not directly accounted for during the clustering process. In this paper we consider multivariate categorical data, and introduce a model-based clustering method which employs graphical models as a tool to encode dependencies between variables. Specifically, we consider a Dirichlet Process mixture of categorical graphical models, which clusters individuals into groups that are homogeneous in terms of dependence (graphical) structure and allied parameters. We provide full Bayesian inference for the model and develop a Markov chain Monte Carlo scheme for posterior analysis. Our method is evaluated through simulations and applied to real case studies, including the analysis of genomic data and voting records. Results reveal the merits of a graphical model-based clustering, in comparison with approaches that do not explicitly account for dependencies in the multivariate distribution of variables.
- Open Access
- 20 January 2026
- Published by Oxford University Press (OUP) in Biostatistics
- Vol. 27 (1)
Bayesian nonparametric mixtures of categorical directed graphs for personalized causal inference
Summary: Quantifying the causal effect of a treatment on a disease is a crucial task in medical science for the administration of effective therapies. Typically, such causal effects are inferred from multivariate data that are collected on patients and recorded in the form of categorical variables, including risk factors involved in disease progression, treatment assignments, and disease status. This feature motivates an approach to causal inference based on categorical Directed Acyclic Graphs (DAGs), which provide an effective framework for causal reasoning in complex multivariate settings. In this context, traditional DAG-based methods assume population homogeneity and accordingly attribute a unique causal effect to all subjects. However, this assumption is often unrealistic in clinical contexts, since patients may exhibit heterogeneous characteristics, possibly linked to unmeasured features. To address this issue, we propose a Bayesian nonparametric methodology based on a Dirichlet Process mixture of categorical DAGs, which allows treatment effects to vary across individuals because of underlying clustering structures in the data. We develop a Markov chain Monte Carlo algorithm for Bayesian posterior inference and evaluate our methodology through simulation studies. We then analyze patients affected by HER2+ breast cancer undergoing therapies that may cause cardiotoxic side effects. Importantly, our findings show that approaches neglecting population heterogeneity may produce biased results, since they can over- or under-estimate the risk of cardiotoxicity across patients.
- 20 January 2026
- Published by Oxford University Press (OUP) in Biostatistics
- Vol. 27 (1)
Open AccessBayesian nonparametric mixtures of categorical directed graphs for personalized causal inference
Summary: Quantifying the causal effect of a treatment on a disease is a crucial task in medical science for the administration of effective therapies. Typically, such causal effects are inferred from multivariate data that are collected on patients and recorded in the form of categorical variables, including risk factors involved in disease progression, treatment assignments, and disease status. This feature motivates an approach to causal inference based on categorical Directed Acyclic Graphs (DAGs), which provide an effective framework for causal reasoning in complex multivariate settings. In this context, traditional DAG-based methods assume population homogeneity and accordingly attribute a unique causal effect to all subjects. However, this assumption is often unrealistic in clinical contexts, since patients may exhibit heterogeneous characteristics, possibly linked to unmeasured features. To address this issue, we propose a Bayesian nonparametric methodology based on a Dirichlet Process mixture of categorical DAGs, which allows treatment effects to vary across individuals because of underlying clustering structures in the data. We develop a Markov chain Monte Carlo algorithm for Bayesian posterior inference and evaluate our methodology through simulation studies. We then analyze patients affected by HER2+ breast cancer undergoing therapies that may cause cardiotoxic side effects. Importantly, our findings show that approaches neglecting population heterogeneity may produce biased results, since they can over- or under-estimate the risk of cardiotoxicity across patients.
- Open Access
- 1 July 2024
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 80 (3)
Joint structure learning and causal effect estimation for categorical graphical models
The scope of this paper is a multivariate setting involving categorical variables. Following an external manipulation of one variable, the goal is to evaluate the causal effect on an outcome of interest. A typical scenario involves a system of variables representing lifestyle, physical and mental features, symptoms, and risk factors, with the outcome being the presence or absence of a disease. These variables are interconnected in complex ways, allowing the effect of an intervention to propagate through multiple paths. A distinctive feature of our approach is the estimation of causal effects while accounting for uncertainty in both the dependence structure, which we represent through a directed acyclic graph (DAG), and the DAG-model parameters. Specifically, we propose a Markov chain Monte Carlo algorithm that targets the joint posterior over DAGs and parameters, based on an efficient reversible-jump proposal scheme. We validate our method through extensive simulation studies and demonstrate that it outperforms current state-of-the-art procedures in terms of estimation accuracy. Finally, we apply our methodology to analyze a dataset on depression and anxiety in undergraduate students.
- 1 July 2024
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 80 (3)
Open AccessJoint structure learning and causal effect estimation for categorical graphical models
The scope of this paper is a multivariate setting involving categorical variables. Following an external manipulation of one variable, the goal is to evaluate the causal effect on an outcome of interest. A typical scenario involves a system of variables representing lifestyle, physical and mental features, symptoms, and risk factors, with the outcome being the presence or absence of a disease. These variables are interconnected in complex ways, allowing the effect of an intervention to propagate through multiple paths. A distinctive feature of our approach is the estimation of causal effects while accounting for uncertainty in both the dependence structure, which we represent through a directed acyclic graph (DAG), and the DAG-model parameters. Specifically, we propose a Markov chain Monte Carlo algorithm that targets the joint posterior over DAGs and parameters, based on an efficient reversible-jump proposal scheme. We validate our method through extensive simulation studies and demonstrate that it outperforms current state-of-the-art procedures in terms of estimation accuracy. Finally, we apply our methodology to analyze a dataset on depression and anxiety in undergraduate students.
- 1 June 2024
- Published by Cambridge University Press (CUP) in Psychometrika
- Vol. 89 (2) , 658-686
Learning Bayesian Networks: A Copula Approach for Mixed-Type Data
Estimating dependence relationships between variables is a crucial issue in many applied domains and in particular psychology. When several variables are entertained, these can be organized into a network which encodes their set of conditional dependence relations. Typically however, the underlying network structure is completely unknown or can be partially drawn only; accordingly it should be learned from the available data, a process known as structure learning. In addition, data arising from social and psychological studies are often of different types, as they can include categorical, discrete and continuous measurements. In this paper, we develop a novel Bayesian methodology for structure learning of directed networks which applies to mixed data, i.e., possibly containing continuous, discrete, ordinal and binary variables simultaneously. Whenever available, our method can easily incorporate known dependence structures among variables represented by paths or edge directions that can be postulated in advance based on the specific problem under consideration. We evaluate the proposed method through extensive simulation studies, with appreciable performances in comparison with current state-of-the-art alternative methods. Finally, we apply our methodology to well-being data from a social survey promoted by the United Nations, and mental health data collected from a cohort of medical students. R code implementing the proposed methodology is available at https://github.com/FedeCastelletti/bayes_networks_mixed_data.
- 1 June 2024
- Published by Cambridge University Press (CUP) in Psychometrika
- Vol. 89 (2) , 658-686
Learning Bayesian Networks: A Copula Approach for Mixed-Type Data
Estimating dependence relationships between variables is a crucial issue in many applied domains and in particular psychology. When several variables are entertained, these can be organized into a network which encodes their set of conditional dependence relations. Typically however, the underlying network structure is completely unknown or can be partially drawn only; accordingly it should be learned from the available data, a process known as structure learning. In addition, data arising from social and psychological studies are often of different types, as they can include categorical, discrete and continuous measurements. In this paper, we develop a novel Bayesian methodology for structure learning of directed networks which applies to mixed data, i.e., possibly containing continuous, discrete, ordinal and binary variables simultaneously. Whenever available, our method can easily incorporate known dependence structures among variables represented by paths or edge directions that can be postulated in advance based on the specific problem under consideration. We evaluate the proposed method through extensive simulation studies, with appreciable performances in comparison with current state-of-the-art alternative methods. Finally, we apply our methodology to well-being data from a social survey promoted by the United Nations, and mental health data collected from a cohort of medical students. R code implementing the proposed methodology is available at https://github.com/FedeCastelletti/bayes_networks_mixed_data.
- 1 May 2024
- Published by Institute of Mathematical Statistics in Statistical Science
- Vol. 39 (2) , 305-321
Bayesian Sample Size Determination for Causal Discovery
Graphical models based on Directed Acyclic Graphs (DAGs) are widely used to answer causal questions across a variety of scientific and social disciplines. However, observational data alone cannot distinguish in general between DAGs representing the same conditional independence assertions (Markov equivalent DAGs); as a consequence, the orientation of some edges in the graph remains indeterminate. Interventional data, produced by exogenous manipulations of variables in the network, enhance the process of structure learning because they allow to distinguish among equivalent DAGs, thus sharpening causal inference. Starting from an equivalence class of DAGs, a few procedures have been devised to produce a collection of variables to be manipulated in order to identify a causal DAG. Yet, these algorithmic approaches do not determine the sample size of the interventional data required to obtain a desired level of statistical accuracy. We tackle this problem from a Bayesian experimental design perspective, taking as input a sequence of target variables to be manipulated to identify edge orientation. We then propose a method to determine, at each intervention, the optimal sample size to produce an experiment which, with high assurance, will deliver an overall probability of decisive and correct evidence.
- 1 May 2024
- Published by Institute of Mathematical Statistics in Statistical Science
- Vol. 39 (2) , 305-321
Bayesian Sample Size Determination for Causal Discovery
Graphical models based on Directed Acyclic Graphs (DAGs) are widely used to answer causal questions across a variety of scientific and social disciplines. However, observational data alone cannot distinguish in general between DAGs representing the same conditional independence assertions (Markov equivalent DAGs); as a consequence, the orientation of some edges in the graph remains indeterminate. Interventional data, produced by exogenous manipulations of variables in the network, enhance the process of structure learning because they allow to distinguish among equivalent DAGs, thus sharpening causal inference. Starting from an equivalence class of DAGs, a few procedures have been devised to produce a collection of variables to be manipulated in order to identify a causal DAG. Yet, these algorithmic approaches do not determine the sample size of the interventional data required to obtain a desired level of statistical accuracy. We tackle this problem from a Bayesian experimental design perspective, taking as input a sequence of target variables to be manipulated to identify edge orientation. We then propose a method to determine, at each intervention, the optimal sample size to produce an experiment which, with high assurance, will deliver an overall probability of decisive and correct evidence.
- Open Access
- 26 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 61185-61197
Bayesian Learning of Causal Networks for Unsupervised Fault Diagnosis in Distributed Energy Systems
Distributed energy generation systems, key for producing electricity near usage points, are essential to meet theglobal electricity demand, leveraging diverse sources likerenewables, traditional fuels, and industrial waste heat. Despite theirhigh reliability, these systemsare not immune to faults and failures. Such incidents can result in considerable downtime and reduced efficiency, underlining the need for effectivefault detection and diagnosis techniques. Implementing these strategies is crucial not just for mitigating damage and preventing potential disasters, but also to maintain optimal performance levels. This paper introduces a novel methodology based on Bayesian graphical modeling for unsupervised fault diagnosis, focusing on organic Rankine cycle case study. It employsstructural learning to discern unknown intervention points within a directed acyclic graph that models the power plant’s operations. By analyzing real-world data, the study demonstrates the effectiveness of this approach, pinpointing a subset of variables that could be implicated in specific faults.
- 26 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 61185-61197
Open AccessBayesian Learning of Causal Networks for Unsupervised Fault Diagnosis in Distributed Energy Systems
Distributed energy generation systems, key for producing electricity near usage points, are essential to meet theglobal electricity demand, leveraging diverse sources likerenewables, traditional fuels, and industrial waste heat. Despite theirhigh reliability, these systemsare not immune to faults and failures. Such incidents can result in considerable downtime and reduced efficiency, underlining the need for effectivefault detection and diagnosis techniques. Implementing these strategies is crucial not just for mitigating damage and preventing potential disasters, but also to maintain optimal performance levels. This paper introduces a novel methodology based on Bayesian graphical modeling for unsupervised fault diagnosis, focusing on organic Rankine cycle case study. It employsstructural learning to discern unknown intervention points within a directed acyclic graph that models the power plant’s operations. By analyzing real-world data, the study demonstrates the effectiveness of this approach, pinpointing a subset of variables that could be implicated in specific faults.
- Open Access
Learning Bayesian networks: a copula approach for mixed-type data
Estimating dependence relationships between variables is a crucial issue in many applied domains, such as medicine, social sciences and psychology. When several variables are entertained, these can be organized into a network which encodes their set of conditional dependence relations. Typically however, the underlying network structure is completely unknown or can be partially drawn only; accordingly it should be learned from the available data, a process known as structure learning. In addition, data arising from social and psychological studies are often of different types, as they can include categorical, discrete and continuous measurements. In this paper we develop a novel Bayesian methodology for structure learning of directed networks which applies to mixed data, i.e. possibly containing continuous, discrete, ordinal and binary variables simultaneously. Whenever available, our method can easily incorporate known dependence structures among variables represented by paths or edge directions that can be postulated in advance based on the specific problem under consideration. We evaluate the proposed method through extensive simulation studies, with appreciable performances in comparison with current state-of-the-art alternative methods. Finally, we apply our methodology to well-being data from a social survey promoted by the United Nations, and mental health data collected from a cohort of medical students.
Open AccessLearning Bayesian networks: a copula approach for mixed-type data
Estimating dependence relationships between variables is a crucial issue in many applied domains, such as medicine, social sciences and psychology. When several variables are entertained, these can be organized into a network which encodes their set of conditional dependence relations. Typically however, the underlying network structure is completely unknown or can be partially drawn only; accordingly it should be learned from the available data, a process known as structure learning. In addition, data arising from social and psychological studies are often of different types, as they can include categorical, discrete and continuous measurements. In this paper we develop a novel Bayesian methodology for structure learning of directed networks which applies to mixed data, i.e. possibly containing continuous, discrete, ordinal and binary variables simultaneously. Whenever available, our method can easily incorporate known dependence structures among variables represented by paths or edge directions that can be postulated in advance based on the specific problem under consideration. We evaluate the proposed method through extensive simulation studies, with appreciable performances in comparison with current state-of-the-art alternative methods. Finally, we apply our methodology to well-being data from a social survey promoted by the United Nations, and mental health data collected from a cohort of medical students.
- Open Access
Bayesian causal discovery from unknown general interventions
We consider the problem of learning causal Directed Acyclic Graphs (DAGs) using combinations of observational and interventional experimental data. Current methods tailored to this setting assume that interventions either destroy parent-child relations of the intervened (target) nodes or only alter such relations without modifying the parent sets, even when the intervention targets are unknown. We relax this assumption by proposing a Bayesian method for causal discovery from general interventions, which allow for modifications of the parent sets of the unknown targets. Even in this framework, DAGs and general interventions may be identifiable only up to some equivalence classes. We provide graphical characterizations of such interventional Markov equivalence and devise compatible priors for Bayesian inference that guarantee score equivalence of indistinguishable structures. We then develop a Markov Chain Monte Carlo (MCMC) scheme to approximate the posterior distribution over DAGs, intervention targets and induced parent sets. Finally, we evaluate the proposed methodology on both simulated and real protein expression data.
Open AccessBayesian causal discovery from unknown general interventions
We consider the problem of learning causal Directed Acyclic Graphs (DAGs) using combinations of observational and interventional experimental data. Current methods tailored to this setting assume that interventions either destroy parent-child relations of the intervened (target) nodes or only alter such relations without modifying the parent sets, even when the intervention targets are unknown. We relax this assumption by proposing a Bayesian method for causal discovery from general interventions, which allow for modifications of the parent sets of the unknown targets. Even in this framework, DAGs and general interventions may be identifiable only up to some equivalence classes. We provide graphical characterizations of such interventional Markov equivalence and devise compatible priors for Bayesian inference that guarantee score equivalence of indistinguishable structures. We then develop a Markov Chain Monte Carlo (MCMC) scheme to approximate the posterior distribution over DAGs, intervention targets and induced parent sets. Finally, we evaluate the proposed methodology on both simulated and real protein expression data.
- 25 July 2023
- Published by Springer Nature
- p. 53-65
Bayesian Multivariate Analysis of Mixed Data
- Open Access
Joint structure learning and causal effect estimation for categorical graphical models
We consider a a collection of categorical random variables. Of special interest is the causal effect on an outcome variable following an intervention on another variable. Conditionally on a Directed Acyclic Graph (DAG), we assume that the joint law of the random variables can be factorized according to the DAG, where each term is a categorical distribution for the node-variable given a configuration of its parents. The graph is equipped with a causal interpretation through the notion of interventional distribution and the allied "do-calculus". From a modeling perspective, the likelihood is decomposed into a product over nodes and parents of DAG-parameters, on which a suitably specified collection of Dirichlet priors is assigned. The overall joint distribution on the ensemble of DAG-parameters is then constructed using global and local independence. We account for DAG-model uncertainty and propose a reversible jump Markov Chain Monte Carlo (MCMC) algorithm which targets the joint posterior over DAGs and DAG-parameters; from the output we are able to recover a full posterior distribution of any causal effect coefficient of interest, possibly summarized by a Bayesian Model Averaging (BMA) point estimate. We validate our method through extensive simulation studies, wherein comparisons with alternative state-of-the-art procedures reveal an outperformance in terms of estimation accuracy. Finally, we analyze a dataset relative to a study on depression and anxiety in undergraduate students.
Open AccessJoint structure learning and causal effect estimation for categorical graphical models
We consider a a collection of categorical random variables. Of special interest is the causal effect on an outcome variable following an intervention on another variable. Conditionally on a Directed Acyclic Graph (DAG), we assume that the joint law of the random variables can be factorized according to the DAG, where each term is a categorical distribution for the node-variable given a configuration of its parents. The graph is equipped with a causal interpretation through the notion of interventional distribution and the allied "do-calculus". From a modeling perspective, the likelihood is decomposed into a product over nodes and parents of DAG-parameters, on which a suitably specified collection of Dirichlet priors is assigned. The overall joint distribution on the ensemble of DAG-parameters is then constructed using global and local independence. We account for DAG-model uncertainty and propose a reversible jump Markov Chain Monte Carlo (MCMC) algorithm which targets the joint posterior over DAGs and DAG-parameters; from the output we are able to recover a full posterior distribution of any causal effect coefficient of interest, possibly summarized by a Bayesian Model Averaging (BMA) point estimate. We validate our method through extensive simulation studies, wherein comparisons with alternative state-of-the-art procedures reveal an outperformance in terms of estimation accuracy. Finally, we analyze a dataset relative to a study on depression and anxiety in undergraduate students.