New Book
I’ve completed a new bookdown document, Models by Example, that converts most of the code from my Miscellaneous R repo. I initially just wanted to update the code, but decided to use a more formal approach to make it cleaner and more accessible. It’s mostly complete, though may be added to on rare occasion, and further cleaned as I find annoying bits here and there. Each topic contains ‘by-hand’ demonstration, such that you can see conceptually how a model is estimated, or technique employed. This can help those that want to dive a little deeper to get a peek behind the curtain of the functions and packages they use, hopefully empowering them to go further with such models.
Topics covered include the following, and I plan to post a sample chapter soon.
Models
- Linear Regression
- Logistic Regression
- One-factor Mixed Model
- Two-factor Mixed Model
- Mixed Model via ML
- Probit & Bivariate Probit
- Heckman Selection
- Marginal Structural Model
- Tobit
- Cox Survival
- Hurdle Model
- Zero-Inflated Model
- Naive Bayes
- Multinomial
- Ordinal
- Markov Model
- Hidden Markov Model
- Quantile Regression
- Cubic Spline Model
- Gaussian Processes
- Neural Net
- Extreme Learning Machine
- Reproducing Kernel Hilbert Space Regression
- Confirmatory Factor Analysis
Bayesian
- Basics
- Bayesian t-test
- Bayesian Linear Regression
- Bayesian Beta Regression
- Bayesian Mixed Model
- Bayesian Multilevel Mediation
- Bayesian IRT
- Bayesian CFA
- Bayesian Nonparametric Models
- Bayesian Stochastic Volatility Model
- Bayesian Multinomial Models
- Variational Bayes Regression
- Topic Model
Estimation
- Maximum Likelihood
- Penalized Maximum Likelihood
- L1 (lasso) regularization
- L2 (ridge) regularization
- Newton and IRLS
- Nelder Mead
- Expectation-Maximization
- Gradient Descent
- Stochastic Gradient Descent
- Metropolis Hastings
- Hamiltonian Monte Carlo
Reuse
Citation
@online{clark2020,
author = {Clark, Michael},
title = {Models by {Example}},
date = {2020-11-30},
url = {https://m-clark.github.io/posts/2020-11-30-models-by-example/},
langid = {en}
}