index.Rmd

---
title: "DEPENd/DNPL MLM Workshop 2021"
subtitle: "Organized by Michael Hallquist"
date: "Spring 2021"
output:
  html_document:
    df_print: kable
    mathjax: default
    number_sections: no
    theme: spacelab
    toc: no
    fig_width: 9 
    fig_height: 6 
---
<style type="text/css">
body{ font-size: 20px; max-width: 1600px; margin: auto; padding: 1em; }
code.r{ font-size: 20px; }
p { padding-top: 10px; padding-bottom: 10px; }
pre { font-size: 16px; }
</style>

Welcome to the DEPENd Lab/DNPL workshop on multilevel modeling. This is the Spring 2021 edition. This website provides access to course materials and examples. For access to the `Rmd` files containing all code, see [here](https://github.com/UNCDEPENdLab/MLM_Tutorial).

The goal of this workshop is to provide an overview of multilevel modeling and to consider its application to behavioral data, particularly from cognitive and decision-making tasks.

To obtain an initial copy of the materials for this workshop, use `git clone` to download the course repository: 
`git clone https://github.com/UNCDEPENdLab/MLM_Tutorial`

If you already cloned a local copy of the repo, you can get the latest updates using `git update.` If all of this git stuff is foreign, I'd recommend a quick skim of this documentation: https://happygitwithr.com

# Meeting topics

## 21Jan2021: Review of GLM (Regression, ANOVA)
  - Video of lecture: https://www.youtube.com/watch?v=WX2H49ChOKk
  - [Regression overview](01_Regression/01_Correlation_and_Regression.html)
  - [ANOVA and GLM examples](01_Regression/03_Basic_Analysis.html)
  - [ANOVA contrast tutorial](https://cran.r-project.org/web/packages/afex/vignettes/afex_anova_example.html)
  - [Matrix algebra and the GLM](01_Regression/02_Matrix_Algebra_Overview.html)
  
## 4Feb2021: Clustering, Basics of MLM, Random Intercept Model (Alison Schreiber)
  - Video of lecture: https://www.youtube.com/watch?v=vBdirrzYAlM
  - [MLM Overview](02_Intro_MLM/MLM_S2.html)

## 18Feb2021: MLM Intuitions, lme4 implementation, Random slopes
  - Video of lecture: https://www.youtube.com/watch?v=7Dz2fgUg5ds
  - [MLM Intuitions, Within/Between and Fixed/Random](03_Foundations/03_Terms_L1L2.html)
  - [MLM implementation, Flanker Example](03_Foundations/03_Foundations.html)
  
## 4Mar2021: Effect heterogeneity
  - Video of lecture: https://www.youtube.com/watch?v=HTUO0uif1aE
  - [Random slopes, Causal effect heterogeneity](04_Heterogeneity/04_Heterogeneity.html)

## 18Mar2021: Random slopes, covariance structure, nesting
  - Video of lecture: https://www.youtube.com/watch?v=wzFozlL3nrw
  - [Understanding random slopes](05_RandomEffects_Moderation/05_RandomEffects.html)
  - [Visualizing MLM representation of clustering](05_RandomEffects_Moderation/vizrandomeffects.html)
  - [Latent disaggregation](https://psu-psychology.github.io/psy-597-SEM/15_multilevel/multilevel_sem.html#disaggregating-within--versus-between-cluster-effects)
  - [Heterogeneous variance structures](https://quantdev.ssri.psu.edu/sites/qdev/files/ILD_Ch06_2017_MLMwithHeterogeneousVariance.html)
  
## 15Apr2021: Model selection and model pruning
  - Video of model evidence lecture: https://www.youtube.com/watch?v=jBRdkMGzmIY
  - [Model selection, evidence, and maximal models](06_ModelSelection/model_comparison.html)
  - Video of full flanker analysis walkthrough: https://www.youtube.com/watch?v=rqkym6bj88k
  - [Flanker model building](06_ModelSelection/flanker_rt_mlm_publication.html)
  
## 13May2021: Incorporating neural measures into MLMs of behavior (Alex Dombrovski) 
  - Video of lecture: https://www.youtube.com/watch?v=_jC9Wx2qhF4
  - [fMRI hippocampal regression coefficients in trial-wise MLMs](07_BrainBehavior/beta_cluster_behavior_analyses_mlm_class.html)

## 27May2021: Multilevel SEM (Tim Allen)
  - Video of lecture: https://www.youtube.com/watch?v=BfnTmdNsw6c
  - [MSEM Tutorial](08_MSEM/multilevel_sem_v5.html)

## 10Jun2021: Bayesian extensions of MLM (Vanessa Brown)
  - Video of lecture: https://www.youtube.com/watch?v=biEKsCfYDIQ
  - [R syntax for analyses](09_Bayes/horizon_regressions.R)