Bayesian Causal Inference in Doubly Gaussian DAG-probit Models
- URL: http://arxiv.org/abs/2304.05976v1
- Date: Wed, 12 Apr 2023 16:57:47 GMT
- Title: Bayesian Causal Inference in Doubly Gaussian DAG-probit Models
- Authors: Rasool Tahmasbi and Keyvan Tahmasbi
- Abstract summary: We introduce the concept of Gaussian DAG-probit model under two groups and hence doubly Gaussian DAG-probit model.
We validated the proposed method using a comprehensive simulation experiment and applied it on two real datasets.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We consider modeling a binary response variable together with a set of
covariates for two groups under observational data. The grouping variable can
be the confounding variable (the common cause of treatment and outcome),
gender, case/control, ethnicity, etc. Given the covariates and a binary latent
variable, the goal is to construct two directed acyclic graphs (DAGs), while
sharing some common parameters. The set of nodes, which represent the
variables, are the same for both groups but the directed edges between nodes,
which represent the causal relationships between the variables, can be
potentially different. For each group, we also estimate the effect size for
each node. We assume that each group follows a Gaussian distribution under its
DAG. Given the parent nodes, the joint distribution of DAG is conditionally
independent due to the Markov property of DAGs. We introduce the concept of
Gaussian DAG-probit model under two groups and hence doubly Gaussian DAG-probit
model. To estimate the skeleton of the DAGs and the model parameters, we took
samples from the posterior distribution of doubly Gaussian DAG-probit model via
MCMC method. We validated the proposed method using a comprehensive simulation
experiment and applied it on two real datasets. Furthermore, we validated the
results of the real data analysis using well-known experimental studies to show
the value of the proposed grouping variable in the causality domain.
Related papers
- Disentanglement Analysis in Deep Latent Variable Models Matching Aggregate Posterior Distributions [0.5759862457142761]
We propose a method to evaluate disentanglement for deep latent variable models (DLVMs) in general.
The proposed technique discovers the latent vectors representing the generative factors of a dataset that can be different from the cardinal latent axes.
arXiv Detail & Related papers (2025-01-26T23:38:39Z) - Scalable Variational Causal Discovery Unconstrained by Acyclicity [6.954510776782872]
We propose a scalable Bayesian approach to learn the posterior distribution over causal graphs given observational data.
We introduce a novel differentiable DAG sampling method that can generate a valid acyclic causal graph.
We are able to model the posterior distribution over causal graphs using a simple variational distribution over a continuous domain.
arXiv Detail & Related papers (2024-07-06T07:56:23Z) - Heterogeneous Multi-Task Gaussian Cox Processes [61.67344039414193]
We present a novel extension of multi-task Gaussian Cox processes for modeling heterogeneous correlated tasks jointly.
A MOGP prior over the parameters of the dedicated likelihoods for classification, regression and point process tasks can facilitate sharing of information between heterogeneous tasks.
We derive a mean-field approximation to realize closed-form iterative updates for estimating model parameters.
arXiv Detail & Related papers (2023-08-29T15:01:01Z) - A Graphical Model for Fusing Diverse Microbiome Data [2.385985842958366]
We introduce a flexible multinomial-Gaussian generative model for jointly modeling such count data.
We present a computationally scalable variational Expectation-Maximization (EM) algorithm for inferring the latent variables and the parameters of the model.
arXiv Detail & Related papers (2022-08-21T17:54:39Z) - On the Strong Correlation Between Model Invariance and Generalization [54.812786542023325]
Generalization captures a model's ability to classify unseen data.
Invariance measures consistency of model predictions on transformations of the data.
From a dataset-centric view, we find a certain model's accuracy and invariance linearly correlated on different test sets.
arXiv Detail & Related papers (2022-07-14T17:08:25Z) - Equivariance Discovery by Learned Parameter-Sharing [153.41877129746223]
We study how to discover interpretable equivariances from data.
Specifically, we formulate this discovery process as an optimization problem over a model's parameter-sharing schemes.
Also, we theoretically analyze the method for Gaussian data and provide a bound on the mean squared gap between the studied discovery scheme and the oracle scheme.
arXiv Detail & Related papers (2022-04-07T17:59:19Z) - BCDAG: An R package for Bayesian structure and Causal learning of
Gaussian DAGs [77.34726150561087]
We introduce the R package for causal discovery and causal effect estimation from observational data.
Our implementation scales efficiently with the number of observations and, whenever the DAGs are sufficiently sparse, the number of variables in the dataset.
We then illustrate the main functions and algorithms on both real and simulated datasets.
arXiv Detail & Related papers (2022-01-28T09:30:32Z) - BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery [97.79015388276483]
A structural equation model (SEM) is an effective framework to reason over causal relationships represented via a directed acyclic graph (DAG)
Recent advances enabled effective maximum-likelihood point estimation of DAGs from observational data.
We propose BCD Nets, a variational framework for estimating a distribution over DAGs characterizing a linear-Gaussian SEM.
arXiv Detail & Related papers (2021-12-06T03:35:21Z) - GANs with Variational Entropy Regularizers: Applications in Mitigating
the Mode-Collapse Issue [95.23775347605923]
Building on the success of deep learning, Generative Adversarial Networks (GANs) provide a modern approach to learn a probability distribution from observed samples.
GANs often suffer from the mode collapse issue where the generator fails to capture all existing modes of the input distribution.
We take an information-theoretic approach and maximize a variational lower bound on the entropy of the generated samples to increase their diversity.
arXiv Detail & Related papers (2020-09-24T19:34:37Z) - Causal Structure Discovery from Distributions Arising from Mixtures of
DAGs [12.12755951035594]
We consider distributions arising from a mixture of causal models, where each model is represented by a directed acyclic graph (DAG)
We show that such algorithms recover a "union" of the component DAGs and can identify variables whose conditional distribution across the component DAGs vary.
As an immediate application, we demonstrate how retrieval of this causal information can be used to cluster samples according to each mixture component.
arXiv Detail & Related papers (2020-01-31T16:33:26Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.