Adrian Brasoveanu

Generalized linear (mixed) models etc.

Sat 11 February 2012 by Adrian Brasoveanu

The last 2 scripts introduce generalized linear (mixed) models and some extensions:

  1. First script: bayes-winbugs-jags-5.r; contents:

    • generalized linear models
    • Poisson “t-test” (simulated data, R analysis, WinBUGS / JAGS analysis)
    • binomial “t-test” (simulated data, R analysis, WinBUGS / JAGS analysis)
    • binomial ANCOVA (simulated data, R analysis, WinBUGS / JAGS analysis)
    • binomial GLMM (simulated data, R analysis, WinBUGS / JAGS analysis)

  2. Second script: bayes-winbugs-jags-6.r; contents:

    • GLMMs that take into account inter-annotator disagreement (simulated data, R analysis, WinBUGS / JAGS analysis)
    • ordinal probit “t-test” (based on joint work with Jakub Dotlacil): simulated data for an ordinal probit “t-test”, i.e., an ordinal probit regression with only one predictor (a factor with 2 levels); frequentist analysis in R using the “ordinal” package; Bayesian analysis using WinBUGS / JAGS