Data Cloning Workshop 2023 - Edmonton
CalgaryR & YEGRUG Meetup: Data Cloning - Hierarchical Models Made Easy
Jointly organized by the Edmonton R User Group & CalgaryR
This is a 4-hour long hybrid (in-person and online) event:
- Date: April 13, 2023
- Time: 2-6 pm
- Location: University of Alberta, Dept. Biological Sciences, room G-113 (map)
- Subhash Lele, Professor Emeritus, Dept. of Mathematical and Statistical Sciences, U. of Alberta
- Peter Solymos, Senior Data Scientist, Organizer of Edmonton R User Group, R package author
 |
 |
|---|---|
| Meetup fees, publicity | Conferencing, catering |
Mixed models, also known as hierarchical models and multilevel models, is a useful class of models for applied sciences. The goal of this workshop is to give an introduction to the logic, theory, and implementation of these models to solve practical problems. The workshop will include a seminar style overview and hands on exercises including common model classes and examples that participants can extend for their own needs.
Participants are expected to know the basics of R programming and regression techniques. A basic idea about hierarchical models and Bayesian/MCMC techniques will help but is not required.
At the end of the workshop, you will have a good idea about why everyone is not a Bayesian, how to use Bayesian techniques for frequentist inference, how to critically diagnose identifiability issues, and how to make likelihood-based inference for (almost) any hierarchical modeling case.
Follow instructions to set up your laptop, or wait for the link for a cloud server.
Read the notes about statistical concepts and the workflow we will rely on, and play with the Shiny app.
If you are using your own computer, download the zipped version or clone it with git clone https://github.com/datacloning/workshop-2023-edmonton.git.
You can use our cloud server as well, you will receive login information in email.
You will receive a link to a short follow up survey.
The rendered GitHub pages in this repository are best viewed without dark mode. This way all the mathematical notation will be legible.
| Topic | Links |
|---|---|
| Setup | Instructions |
| Part 1. Preliminaries | Notes, App |
| Part 2. Mixed models | Notes |
| Part 3. Time series | Notes |
| Part 4. Practical considerations | Notes |
| References | PDF files |
The course material is shared under the Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) license. In publications, please use the following citations to refer to the workshop, theory, and software implementation:
- Lele, S. R., and Solymos, P., 2023. Data Cloning Workshop - Hierarchical Models Made Easy. April 13, 2023. URL https://github.com/datacloning/workshop-2023-edmonton
- Lele, S.R., B. Dennis and F. Lutscher, 2007. Data cloning: easy maximum likelihood estimation for complex ecological models using Bayesian Markov chain Monte Carlo methods. Ecology Letters 10, 551-563. DOI 10.1111/j.1461-0248.2007.01047.x
- Lele, S. R., Nadeem, K., and Schmuland, B., 2010. Estimability and likelihood inference for generalized linear mixed models using data cloning. Journal of the American Statistical Association 105, 1617-1625. DOI 10.1198/jasa.2010.tm09757
- Solymos, P., 2010. dclone: Data Cloning in R. The R Journal 2(2), 29-37. URL https://journal.r-project.org/archive/2010/RJ-2010-011/RJ-2010-011.pdf
For software license, please refer to the corresponding packages used during the workshop. JAGS, rjags, R2WinBUGS, and dclone are all licensed under GPL-2.