Statistical Methods for Mediation, Confounding and Moderation Analysis Using R and SAS
Bibliographic record
Abstract
Yu and Li’s book focuses on ‘third-variables’, which are variables that intervene between a treatment or exposure and an observed outcome. These third-variables can mediate, moderate, or confound the relationship between an exposure and outcome, and the book provides a comprehensive guide to understand and analyse these relationships. Written for readers with a foundation in introductory statistics and knowledge of R or SAS, this book equips researchers with tools to examine third-variable effects across various response types, exposures, and third-variables. A notable feature of the book is that it covers methods for multiple exposures, multiple mediators, multi-level mediation and confounding, high-dimensional mediators, and non-linear relationships, as well as continuous, binary, or categorical mediators and outcomes. To my knowledge, this is the only book to cover all these topics. Another notable feature is a whole chapter devoted to the assumptions underlying these methods—a topic often not addressed—and the effects of violating these assumptions are demonstrated with simulations. A chapter on Bayesian methods uses WinBUGS for some of the simpler analyses and enables readers to get a feel for how the methods are implemented ‘under the hood’. In addition, methods to calculate power for these models are provided. Practical real-world examples are used to illustrate the methods and R code is integrated throughout, while most of the SAS macros are in an appendix. Both the R and SAS code can be found on the second author’s website: http://statweb.lsu.edu/faculty/li/book/. The main R functions are in the mma, mmabig, and mlma packages developed by the authors and available on The Comprehensive R Archive Network (CRAN). Several chapters are based on manuscripts by the authors, but the book has a logical flow and is well organised. There is a good balance between the theoretical and practical, and readers will find this to be a comprehensive guide to analysing third-variable effects.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.068 | 0.279 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.003 | 0.004 |
| Bibliometrics | 0.007 | 0.009 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.002 | 0.008 |
| Insufficient payload (model declined to judge) | 0.196 | 0.043 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".