Last chance: 50% off unlimited learning
Sale ends in
Course Description
Bayesian estimation offers a flexible alternative to modeling techniques where the inferences depend on p-values. In this course, you’ll learn how to estimate linear regression models using Bayesian methods and the rstanarm package. You’ll be introduced to prior distributions, posterior predictive model checking, and model comparisons within the Bayesian framework. You’ll also learn how to use your estimated model to make predictions for new data.
Prerequisites
Curriculum
Course outline
1
Introduction to Bayesian Linear Models
A review of frequentist regression using lm(), an introduction to Bayesian regression using stan_glm(), and a comparison of the respective outputs.
- Non-Bayesian Linear Regression50 XP
- Exploring the data100 XP
- Fitting a frequentist linear regression100 XP
- Bayesian Linear Regression50 XP
- Fitting a Bayesian linear regression100 XP
- Convergence criteria50 XP
- Assessing model convergence50 XP
- Comparing frequentist and Bayesian methods50 XP
- Difference between frequentists and Bayesians50 XP
- Creating credible intervals100 XP
2
Modifying a Bayesian Model
Learn how to modify your Bayesian model including changing the number and length of chains, changing prior distributions, and adding predictors.
3
Assessing Model Fit
In this chapter, we'll learn how to determine if our estimated model fits our data and how to compare competing models.
4
Presenting and Using a Bayesian Regression
In this chapter, we'll learn how to use the estimated model to create visualizations of your model and make predictions for new data.
R
Bayesian Regression Modeling with rstanarm
Course
Complete
