Ecology 563—Lecture Outlines

Lecture 1 (Wednesday, August 22): Review of simple linear regression. Multiple linear regression. Analysis of variance.

Lecture 2 (Monday, August 27): Introduction to R. Analysis of variance with three categorical predictors.

Lecture 3 (Wednesday, August 29): Assessing homogeneity of variance in analysis of variance models. Predictive simulation for assessing model fit.

Lecture 4 (Wednesday, September 5): Graphs of analysis of variance models.

Lecture 5 (Monday, September 10): Difference-adjusted confidence intervals. Dynamite plots.

Lecture 6 (Wednesday, September 12): Analyzing randomized complete block designs using mixed effects models.

Lecture 7 (Monday, September 17): Randomized block designs (continued). Testing for block interactions. Crossed random effects.

Lecture 8 (Wednesday, September 19): Producing an interaction plot using lattice.

Lecture 9 (Monday, September 24): Analysis of covariance.

Lecture 10 (Wednesday, September 26): Split plot designs.

Lecture 11 (Monday, October 1): Repeated measures designs.

Lecture 12 (Wednesday, October 3): Introduction to likelihood theory.

Lecture 13 (Monday, October 8): Likelihood ratio tests and Wald tests. Choosing a probability model.

Lecture 14 (Wednesday, October 10): Fitting the Poisson distribution to data using maximum likelihood.

Lecture 15 (Monday, October 15): Testing the fit of a Poisson distribution. The negative binomial distribution.

Lecture 16 (Wednesday, October 17): Fitting the negative binomial distribution to data. Poisson regression.

Lecture 17 (Monday, October 22): Goodness of fit of a Poisson model. Plotting surfaces. Negative binomial regression.

Lecture 18 (Wednesday, October 24): Negative binomial regression. Comparing regression models with likelihood ratio tests.

Lecture 19 (Monday, October 29): AIC for model selection.

Lecture 20 (Wednesday, October 31): Model selection with variable transformations.

Lecture 21 (Monday, November 5): Goodness of fit for count models with continuous predictors.

Lecture 22 (Wednesday, November 7): Analysis of covariance, random effects, and offsets in Poisson regression.

Lecture 23 (Monday, November 12): Introduction to Bayesian estimation, WinBUGS, and JAGS.

Lecture 24 (Wednesday, November 14): Bayesian diagnostics and credible intervals. Bayesian Poisson regression model.

Lecture 25 (Monday, November 19): Random effects models from a Bayesian perspective.

Lecture 26 (Monday, November 26): Logistic regression.

Lecture 27 (Wednesday, November 28): Goodness of fit for logistic regression. Odds ratios.

Lecture 28 (Monday, December 3): Graphics for logistic regression.

Lecture 29 (Wednesday, December 5): Logistic regression with a binary response.

Course Home Page