General resources to refresh (or learn from scratch). These are notes for myself to check and find good material once again as much as they are for others.
These are lecture notes, workshops, and general standalone documents made freely by individuals.
Former (now works in industry) lead statistician in University of Michigan Center for Statistics Computing and Analytics Research (CSCAR), Michael Clark makes amazing workshop/technical documents on statistical models as well as R. You can find them under https://m-clark.github.io/documents.html and https://m-clark.github.io/workshops.html. Honestly, check out is website! It is a gold mine!
Kerbey Shedden is the director University of Michigan Center for Statistics Computing and Analytics Research (CSCAR). His notes are both detailed and easy to understand.
Introduction to Data Science: https://dept.stat.lsa.umich.edu/~kshedden/introds/
Regression Analysis (STATS-600 at UofM): https://dept.stat.lsa.umich.edu/~kshedden/Courses/Regression_Notes/
Overviews of Different Statistical Methods (Notes from STATS-504 at UofM): https://dept.stat.lsa.umich.edu/~kshedden/stats504/. It contains documents on the following subjects: Regression, Generalized Linear Models, Censored Data/Survival Analysis, Time Series, Mixed Effects Models
Nathaniel E Helwig, Associate Professor of Psychology and Statistics at the University of Minnesota, has some good notes on applied and non-parametric statistics in his personal site: http://users.stat.umn.edu/~helwig/teaching.html
Dimitris Rizopoulos, one of the developers of GLMMadaptive, has extensive teaching slides on longitudinal and survival models on his personal site: https://www.drizopoulos.com/#teaching
Andrew Tyre, Professor of Wildlife Ecology at the University of Nebraska - Lincoln, has his teaching material online. The notes for Ecological Statistics course covers linear, additive, and mixed effects models with code examples in R.
Keith Conrad, Associate Professor of Mathematics at University of Connecticut, has a bunch of lecture notes on different areas of math, ranging from linear algebra and number theory to analysis.
William Greene, author of one Econometric Analysis of the most popular graduate textbooks in econometrics, has lecture notes from Applied Econometrics/ Econometrics I in his old personal site. There are also additional, unassorted files located there as well.
These are notes and workshops from centers within universities that are available and contain information on a vast number of topics
UCLA Statistical Consulting Group has a bunch of documents ranging from full on treatments (ex: documents for Mixed Effects Models) to short applied data analysis examples. They are especially useful as their examples are done across multiple statistical languages like R and STATA.
Workshops/Seminars: https://stats.oarc.ucla.edu/other/mult-pkg/seminars/
Data Analysis Examples: https://stats.oarc.ucla.edu/other/dae/
Frequently Asked Questions (R-Squared, Effect Encoding, etc.): https://stats.oarc.ucla.edu/other/mult-pkg/faq/general/
University of Wisconsin's Social Science Computing Cooperative has a knowledge base with online documents/self-paced workshops for both learning common statistical languages (R, STATA, Python) as well as implementing different statistical methods (under the analysis section).
R Knowledge Base (Analysis Section for models with R implementation): https://www.sscc.wisc.edu/statistics/r/
STATA Knowledge Base: https://www.sscc.wisc.edu/statistics/stata/
The material for PDHPs workshops are made available freely under this section.
These are textbooks that are available for free online divided into different subjects.
Causal Inference: The Mixtape: Scott Cunningham's popular textbook on Causal Inference is available freely online too! My favorite aspect of the online version is that code is available in R, STATA, and Python (A truly revolutionary undertaking as most textbooks usually pick one language and go with it)!
The Effect: An Introduction to Research Design and Causality : Another popular textbook on causal inference written by Nick Huntington-Klein. Just as with The Mixtape, it is also freely available online! Furthermore, like with The Mixtape, the examples are also available with R, STATA, and Python code but this time with an accompanying package! It is not surprising both books are listed as "frequently bought together" under Amazon.
The book has links to slides for courses on Applied Econometrics and Causality as well.
Introduction to Econometrics with R: Based on curricula of econometrics classes at the University of Duisburg-Essen, this book contains practical examples implemented in R with reproducible code. A handy reference to have.
Hadley Wickham, the chief scientist of RStudio (now Poscit) has his books available free of charge online:
R for Data Science: Introduces R, Tidyverse, and elementary programming principles. Useful for those starting learn R.
Advanced R: Advanced topics and intricacies of R. Good for learning about memory management and speeding up code.
R Packages: Developing R packages
ggplot2: Elegant Graphics for Data Analysis: A full on treatment of ggplot2
Hastie and Tibshirani have collaborated on some of the most widely used books on statistical learning. In general, Elements of Statistical Learning is used for graduate level statistical learning courses with Introduction to Statistical Learning being used for undergraduate courses.
Elements of Statistical Learning (ESL): Graduate version of ISL. More in depth treatment of math. Covers wide range of foundational methods in statistics. Truly a one-shop reference.
Introduction to Statistical Learning (ISL): The undergraduate version of ESL with a lower barrier of entry with regards to mathematics. Still a useful companion to ESL. The material applied with sample code in R (and a new version released with sample code in Python). Also an online mini-course is included.
Statistical Learning with Sparsity: Another collaboration from Hastie and Tibshirani that is available freely online.
Core Statistics by Simon Wood: A short book covering fundamental material for advance coursework in statistics.
Welcome to Text Mining with R: A Tidy Approach: An introductory book on text mining that assumes minimal prior knowledge besides that of R. The models are presented intuitively as opposed to mathematically. It is a very short read with multiple case studies so it is perfect for beginners.
Supervised Machine Learning for Text Analysis in R: A more through treatment of text mining and methods for analyzing text data