STAT 637
Download as PDF
Generalized Linear Models
Statistics
College of Computational, Mathematical & Physical Sciences
Course Description
Generalized linear models framework, binary data, polytomous data, log-linear models.
When Taught
Winter
Min
3
Fixed/Max
3
Fixed
3
Fixed
0
Title
Write a GLM
Learning Outcome
For any exponential family of distributions, write a GLM in the random/link/systematic component framework.
Title
Identify the canonical link
Learning Outcome
Determine the canonical link for any distribution in the exponential family.
Title
Fit GLM using software
Learning Outcome
Fit (using frequentist and Bayesian methods) and choose an appropriate generalized linear model for binary, ordered categorical, unordered categorical, and count response variables using R, SAS, and WinBUGS/OpenBUGS/JAGS.
Title
Mathematically solve and compute the MLE's for coefficients of any basic GLM
Learning Outcome
Reproduce (for any distribution in the exponential family) score equations, Fisher information, and write out the form of the iterative reweighted least squares algorithm for finding maximum likelihood estimates of the coefficients.
Title
Evaluate a fitted GLM
Learning Outcome
Evaluate the validity/appropriateness of the chosen model using model diagnostics such as residual plots and deviance.
Title
Identify model weaknesses and strengths
Learning Outcome
Identify weaknesses and strengths in the chosen model for a given data set.
Title
Predict and provide confidence intervals
Learning Outcome
Make predictions and determine confidence intervals using the fitted model.
Title
Identify and account for overdispersion
Learning Outcome
Identify when overdispersion is present in a given data set and ways to account for overdispersion in the model.
Title
Fit and interpret output from a non-standard GLM
Learning Outcome
Fit using R and/or SAS and interpret the output from a generalized linear mixed model, zero-inflated model, gamma regression model, and GLM's for dependent data.
