The second edition emphasizes the directed acyclic graph (DAG) approach to causal inference, integrating DAGs into many examples. The new edition also contains new material on the design of prior distributions, splines, ordered categorical predictors, social relations models, cross-validation, importance sampling, instrumental variables, and Hamiltonian Monte Carlo. It ends with an entirely new chapter that goes beyond generalized linear modeling, showing how domain-specific scientific models can be built into statistical analyses.
The book is accompanied by an R package, rethinking. The package is available here and from on github. The core of this package is two functions, quap and ulam, that allow many different statistical models to be built up from standard model formulas. This has the virtue of forcing the user to lay out all of the assumptions. The function quap performs maximum a posteriori fitting. The function ulam builds a Stan model that can be used to fit the model using MCMC sampling. Some of the more advanced models in the last chapter are written directly in Stan code, in order to provide a bridge to a more general tool. There is also a technical manual with additional documentation.
Richard McElreath studies human evolutionary ecology and is a Director at the Max Planck Institute for Evolutionary Anthropology in Leipzig, Germany. He has published extensively on the mathematical theory and statistical analysis of social behavior, including his first book (with Robert Boyd), Mathematical Models of Social Evolution.
\"In conclusion, Statistical Rethinking frames usual methods and tools taught in graduate statistical courses into a different way to encourage the reader to understand the details and appreciate the underlying assumptions. The accompanying R package offers example codes for some interesting problems that are not available in standard library or other popular packages. This book can be used as a supplement to a graduate course or it can be used by practitioners wanting to brush up their knowledge with better understanding of statistical techniques.\"Abhirup Mallik in Technometrics, August 2021
Why 95% The most common interval mass in the natural and social sciences is the 95% interval. This interval leaves 5% of the probability outside, corresponding to a 5% chance of the parameter not lying within the interval. This customary interval also reflects the customary threshold for statistical significance, which is 5% or p < 0.05. It is not easy to defend the choice of 95% (5%), outside of pleas to convention. Often, all confidence intervals do is communicate the shape of a distribution. In that case, a series of nested intervals may be more useful than any one interval. For example, why not present 67%, 89%, and 97% intervals, along with the median Why these values No reason. They are prime numbers, which makes them easy to remember. And these values avoid 95%, since conventional 95% intervals encourage many readers to conduct unconscious hypothesis tests.
This course provides an introduction to data modeling using the R statistical computing language and likelihood, information theoretic, and Bayesian approaches to inference. The course includes a focus on the R language as a tool for data modeling and emphasizes examples and case studies from ecological and environmental sciences. 59ce067264