Questions or problems regarding this site should be sent to cja@illinois.edu.

  General Information :

• Syllabus 2022.  
  

Announcements:

• Oct 14:  The following are now available
  
  • mixture modeling via jags (for 1 week only)
  • bayesian mixed via bayesmix package (for 1 week only)
  • revised multilevel lecture notes
  • revised multilevel anorexia example
• Oct 2:  R script for fitting multiple regression model to SAT data
  
• Sept 29:   Example of Bayesian Model averaging added under linear regression
  
• Sept 26:  posted revised Gibbs sample example for anorexia data.  The revision goes into detail on what various measures give in output are equal to.  The illustration also shows how to pull the posterior samples and compute sample statistics.
  
• Sept 5: Homework 2 is posted below
  
• Sept 2:  Link added for all the presidential data under section on proportions  (I had the data posted but not the link but this is fixed now).
  
• Aug 25:  turn in homework via e-mail to anderson.UofI@gmail.com
  
• Aug 25:  Homework 1 is posted below (due Thur Sept 1);  Up-dated lecture notes on estimation of mean (&variance) of normal variable
• This course is an advanced graduate seminar is designed for Ph.D. students in QUERIES, quantitative psychology, or related field. Required for this seminar is knowledge of multilevel modeling, mulitvariate statistics, different probability distributions beyond the "big 5", and basic mathematical statistics.
• Class participation is very important. The student presentations of their projects will be placed online in login based learning management system that is password protected
• R will be used for computing.


Announcements: Lectures Notes:
(I will up-date these throughout the semester)

• Introduction   (updated, 8/20/2022)
  
  
• Estimation and Inferences for a Proportion   (updated 8/22/2022)
  R scripts:
  • R code to plot various priors, likelihoods, and posteriors
  • Function to plot different binomial and different beta distributions
  • R functions that plot prior, likelihood, and resulting posterior "beta.bnomial" function
    
  • US president height example for post 1924 US presidential candidates
  • R for example comparing two probabilities.
  • Data for Example with 2 proportions height of post 1924 US presidential candidates
  • All the presidential data
  • R function: grid.BetaBin.txt
  • Practice using COVID19 data from CDC
    • Data number of cases
    • Data number of deaths
    • Markdown example (html)
    • Rmd file of the marked example
  • Additional examples to use for practice:
    • DATA for practice: GSS 2018, approve laws regarding gun ownership. for three different years.
    • DATA for practice: GSS 2012 Does earth revolve around the sun? (and years of education)
    • DATA for practice: GSS 2012 Does earth revolve around the sun? (and number of children)




• Inference mean of a normally distribution variable with known variance  (up-dated Aug 25)
  • R function normal prior x normal likelihood
  • R anorexia data example.
  • Anorexia data
  • Practice:
    • Getting what you pay for data I pulled this from web and added some variables. Information about the data: SAT data -- getting what you pay for; Data are from 1994-95; Data source: Deborah Guber, Depart Political Science, U of Vermont;
    • Markdown for getting what you paid for (html).  This will get you started.
    • Rmd file that generated  So that you can add your own commands to this
  
  
• Inference mean and variance of a normally distributed variable.   (up-datd Aug 25)
  
  • R code for graphs of Gamma and Inverse Gamma Distributions.
  • R anorexia data example.
  • Anorexia data
  • Practice:
    • Getting what you pay for data I pulled this from web and added some variables. Information about the data: SAT data -- getting what you pay for; Data are from 1994-95; Data source: Deborah Guber, Depart Political Science, U of Vermont;
    • Rmarkdown Getting What Paid For (html)
      
    • Rmd file for Rmarkdown

• MCMC:  Gibbs Sampling
  • Little function for Gibbs of mean and variance of normally distirbuted variable. An example is included.
  • R code for mean and sigma to test jags installed properly. This estimates the mean and variance for the anorexia data set.
  • Anorexia data
  • R markdown analysis of anorexia data.  (.html)   up-dated 9.26.2022
    
  • Rmarkdown for anorexia data (.rmd)   up-dated 9.26.2022
    
  • R script from R markdown (.R)  up-dated 9.26.2022
    
  • Practice: Getting What you Paid For
    • Getting what you pay for data I pulled this from web and added some variables. Information about the data: SAT data -- getting what you pay for; Data are from 1994-95; Data source: Deborah Guber, Depart Political Science, U of Vermont;
    • Rmarkdown to get you started. You will have to write some code for this one
    • Rmd file that you can add to or modify
    • What we did in lecture (sept 24, 2021)
    • Utilities file


•  Bayesian Linear Regression
  • Rmarkdown example using NELS for one school. (html) This illustrates use of jags within R, simple normal linear regression, missing data, using t-distribution, assessing convergence, and some model evaluation.
    
  • Nels data for one school. (txt)
  • Rmd that creates NELS markdown (rmd)
  • Anorexia example  (r script)   Illustrates a categorical predictor.
    
  • Anorexia data (txt)
  • Missing data (txt) downloaded from  https://gist.github.com/richarddmorey/4aaee5418766d5d1da4d36ab8e61a82b   This is also shown in the NELS example.
  • Practice: Getting What you Paid For
    
    • Getting what you pay for data I pulled this from web and added some variables. Information about the data: SAT data -- getting what you pay for; Data are from 1994-95; Data source: Deborah Guber, Depart Political Science, U of Vermont;
    • Rmarkdown to get you started.  (html) You will have to write some code for this one
    • Rmd file that you can add to or modify  (rmd)  You can use this to save your work
      
  
  
  • Multiple Linear Regression
    • Nels example
      • NELS data for one shools (txt)
        
      • Rmarkdown for NELS example (html)
      • Rmarkdown source (rmd)
      • Bayesian Model Averaging (html).  The Nels and the Getting what you paid for data sets are used as examples
        
      • Bayesian Model Averaging (rmd)
        
    • Practice: Getting What you Paid For
      
      • Getting what you pay for data I pulled this from web and added some variables. Information about the data: SAT data -- getting what you pay for; Data are from 1994-95; Data source: Deborah Guber, Depart Political Science, U of Vermont;
      • Rmarkdown to get you started.  (html) You will have to write some code for this one
      • Rmd file that you can add to or modify  (rmd)   You can use this to save your work
      • R markdown Carolyn's version   (overly complex models look good but are bad).
      
      
  
  
• Multilevel (heirarchical) Linear --- (up-dated 10.24.2022)
  • Anorexia example
    • Anorexia rmarkdown (html)
    • R script pulled from rmarkdown rmd file   (R)
    • Rmd file for rmarkdown
    • Anorexia Data (wide format).
    • Anorexia Data (long format).
  • NELS example (nonrandom sample of 23 schools out of 1003 available)
    • Rmarkdown html for nels example. (html)
    • R script for fitting models to nels data. (r)
    • Rmarkdown  nels hlm (rmd)
    • Data: 23 schools from nels.
    • R package brms illustrated using nels data. This is running stan under the hood. The package can do alot more than is illustrated here and Hamletonian Sampling will be discussed in subsequent lecture. See top of R script for more information.
  • Logistic regression examples
    • R script for multilevel logistic regression. This uses data set with 5 items and actually is an IRT model.
    • 10 General Social Survey Vocabulary data. Includes 10 items and some possible predictors. We will only use 5 items.

     

• Metropolis Hastings .   
  R code:
  • R script of metropolis for mean of normal.  "metroLogNorm"
    
  • R function that illustrates Metropolis algorithm. This requires a fixed value of sigma and estimates distribution for mean. The algorithm creates plots at each iteration. To make it run faster, delete the graphing commands.  "metropolis_log_with_examples.txt"
  • Anorexia data analyzed by Metropolis algorithm. Approximates the posteriors of just the mean with known variance and approximates posteriors of both mean and variance.
  • R script for tunning.
  • R function that uses Metropolis algorithm for mean and variance of normal. This version works well for variables regardless of mean or scale. Need tuning to get a good proposal (jump) standard deviation. Note that starting values for the mean should be between min(y) and max(y) for algorithm to work properly.
  • Getting what you pay for data I pulled this from web and added some variables. Information about the data: SAT data -- getting what you pay for; Data are from 1994-95; Data source: Deborah Guber, Depart Political Science, U of Vermont;
  • Some code to help with practice problem. Approximates the posteriors of just the mean with known variance and approximates posteriors of both mean and variance.
  • DBDA2E-utilities.txt. These are a set of functions from Krischke's text, Doing Bayesian Data Analysis, edition 2. I pulled this off the text web-site and put it into a stand alone txt file. This re-produce graphics in the text; however, more things are available in the coda package.

• Hamiltonian, Stan, and a little brms draft)
  Nels Example:
  • The Nels data for 23 schools
    
  • Mean and Variance.html and Rmd file
  • Simple linear regression.html and Rmd file
  • Multiple regression .html , Rmd file, and r script
    
  • Multilevel models.html (brms and stan code)  and Rmd file
    

• Logistic Regression
  R code:
  • R code for Medical school admission data: gpa and gmat
  • Medical school admission data: gpa and gmat
  • Addmision data from UCLA web-site. (admission, gre, gpa and rank of school graduating from)....if you want to try fitting models to another data set.
  • Fatal police shooting data (from Washington Post)
  • Fatal police shooting markdown using brms (html)
    



• Student Presentations:
  • November 17:    Jacki will present "Bayesian models of utterance duration for participant speech: A study examining how relatedness between two entities impacts speaking durations using BRMS" 
    
  • November 29
  • December  1
  • December  6
  • December 8 
  
  
  


• Homework 1 ---
  • Homework assignment 1 (thru Sept 1)    e-mail to anderson.UofI@gmail.com
  • Answer key1
• Homework 2 ---
  • Homework assignment2  (due Tuesday Sept 13)  e-mail to anderson.UofI@gmail.com
    
  • Answer key2 in R markdown html
    
• Homework 3 ---
  • Install jags program and the R packages rjags, runjags, and jagsUI.
    
  • Test that installation is correct by running R-script using this data set.

   

• Homework 4:  install STAN, rstan and brms