Staged Tree Models: With Applications in R

Staged Tree Models: With Applications in R, by Manuele Leonelli and Gherardo Varando, is forthcoming with CRC Press. The book gives an overview of categorical data analysis with staged trees and the stagedtrees R package, from graphical models and conditional independence to structural learning, special classes of staged trees, and causal inference and discovery.

The code in the book requires stagedtrees 2.4.0 or later. Until this version is available on CRAN, the development version can be installed from GitHub:

remotes::install_github("stagedtrees/stagedtrees")

This page will host news about the book and, in due course, datasets, exercises and code to complement the book and give readers further practice.

Table of contents

  1. Graphical Models and Conditional Independence
    1. Introductory Example
    2. Probability Review
    3. Graphs and Their Properties
    4. Bayesian Networks
    5. Conditional Independence
    6. Bayesian Networks in R: The bnlearn Package
    7. Conclusions
  2. Staged Tree Models
    1. The Barking Puppy
    2. Beyond Bayesian Networks
    3. Non-Symmetric Conditional Independence
    4. Staged Trees
    5. Asymmetry-Labeled DAGs
    6. Chain Event Graphs
    7. Conclusions
  3. Specifying and Exploring Staged Trees
    1. Introductory Example
    2. The stagedtrees parametrization
    3. Estimating Staged Tree Parameters
    4. Dealing with Missing Observations
    5. Probabilistic Inference
    6. Exploring and Comparing Staged Trees
    7. Conclusions
  4. Learning Staged Trees from Data
    1. Introductory Example
    2. Score-Based Learning Algorithms
    3. Clustering Learning Algorithms
    4. Choosing a Variables’ Ordering
    5. Bayesian Learning
    6. Conclusions
  5. Special Classes of Staged Trees
    1. Introductory Example
    2. k-Parents Staged Trees
    3. Simple Staged Trees
    4. Context-Specific Staged Trees
    5. Staged Tree Classifiers
    6. Naive Staged Trees
    7. Conclusions
  6. Causal Inference and Discovery with Staged Trees
    1. Introductory Example
    2. Causal Models Based on Staged Trees
    3. Discovering Context-Specific Causal Relationships from Data
    4. Statistical and Causal Equivalence of Staged Tree Models
    5. Heterogeneous Treatment Effect Estimation
    6. Conclusions
  7. Conclusions