This repository contains resources and information for a colearning group meeting regularly to discuss lectures and homework assignments from the Statistical Rethinking 2022 course.
Adjusting from Richard’s schedule for our pace. Note these are meeting dates indicating when lectures, readings and homework are assigned, to be discussed on/completed by the next meeting.
| Meeting date | Lectures | Reading | Homework |
|---|---|---|---|
| 2022-01-13 | (1) The Golem of Prague, (2) Bayesian Inference | Chapters 1, 2 and 3 | Homework 1 |
| 2022-01-26 | (3) Basic Regression, (4) Categories & Curves | Chapter 4 | Homework 2 |
| 2022-02-11 | (5) Confounding, (6) Even Worse Confounding | Chapters 5 and 6 | Homework 3 |
| 2022-02-24 | (7) Overfitting | Chapter 7 | |
| 2022-03-11 | (8) Markov Chain Monte Carlo | Chapter 8, 9 | Homework 4 |
| 2022-03-25 | (9) Logistic and Binomial GLMs, (10) Sensitivity and Poisson GLMs | Chapters 10, 11 | Homework 5 |
| 2022-04-06 | (11) Ordered Categories, (12) Multilevel Models | Chapters 12, 13 | Homework 6 |
| 2022-04-22 | (13) Multi-Multilevel Models, (14) Correlated varying effects | Chapters 13, 14 | Homework 7 |
- Lectures: https://github.com/rmcelreath/stat_rethinking_2022#calendar--topical-outline
- Homework: https://github.com/rmcelreath/stat_rethinking_2022/tree/main/homework
Additional material using other packages or languages
- Original R: https://github.com/rmcelreath/rethinking/
- R + Tidyverse + ggplot2 + brms: https://bookdown.org/content/4857/
- Python and PyMC3: Python/PyMC3
- Julia and Turing: https://github.com/StatisticalRethinkingJulia and https://github.com/StatisticalRethinkingJulia/TuringModels.jl
See Richard’s comments about these here: https://github.com/rmcelreath/stat_rethinking_2022#original-r-flavor
Also, Alec’s notes and solutions of the 2019 material: https://github.com/robitalec/statistical-rethinking and https://www.statistical-rethinking.robitalec.ca/
Package specific install directions. We’ll update these as we go!
Rethinking
Stan
Targets
V8, needed for the dagitty package
This repository is structured with a homework/ folder for homework
solutions, and notes/ folder for notes. For folks joining in the
colearning group, you are encouraged to make your own branch in this
repository and share your notes and/or homework solutions.
The R/ folder can be used to store reusable functions useful across
homework solutions and your own model situations.
For example, the dag_plot function makes a DAG plot from a DAG:
library(ggplot2)
library(ggdag)##
## Attaching package: 'ggdag'
## The following object is masked from 'package:stats':
##
## filter
library(dagitty)
source('R/dag_plot.R')
dag <- dagify(
Z ~ A + B,
B ~ A,
exposure = 'A',
outcome = 'Z'
)
dag_plot(dag)
See the full list of branches.
Many thanks to Richard McElreath for a continued emphasis on teaching Bayesian statistics and for providing this incredible resource of lectures and homework assignments free for everyone.
Also thank you to the developers of R, Stan and innumerous R packages that allow us to pursue this interest.
Please note that this project is released with a Code of Conduct. By participating in this project you agree to abide by its terms.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent